Search

Eurasian Jays (Garrulus glandarius) typically store seeds on the ground in shallow caches, promoting tree recruitment. However, speculation exists that Eurasian Jays occasionally store a portion of seeds in microhabitats unsuitable for proper germination. Here, we report that unexpected caching sites in Eurasian Jays can be much more widespread than previously considered and despite their accidental character it seems to be a durable aspect of Eurasian Jay's hoarding behavior. Out of 259 removed acorns of Pedunculate Oak (Quercus robur), we localized 31 consumed and 222 stored acorns. Six experimental acorns (3% of stored acorns) were found stored by jays in unexpected caching sites: (i) above the ground on individuals of Scots Pine (Pinus sylvestris), (ii) inside the woody stems of Reynoutria sp. individuals, (iii) in a rotten trunk, and (iv) among ruin debris. Our findings suggest the need to revise our understanding of so-called unexpected caching in Eurasian Jays. This highlights a previously overlooked aspect of oak-jay interactions, offering a valuable piece to the puzzle. [ABSTRACT FROM AUTHOR]

Modern cloud-native OLAP databases adopt a storage-disaggregation architecture that separates the management of computation and storage. A major bottleneck in such an architecture is the network connecting the computation and storage layers. Computation pushdown is a promising solution to tackle this issue, which offloads some computation tasks to the storage layer to reduce network traffic. This paper presents FlexPushdownDB (FPDB), where we revisit the design of computation pushdown in a storage-disaggregation architecture, and then introduce several optimizations to further accelerate query processing. First, FPDB supports hybrid query execution, which combines local computation on cached data and computation pushdown to cloud storage at a fine granularity. Within the cache, FPDB uses a novel Weighted-LFU cache replacement policy that takes into account the cost of pushdown computation. Second, we design adaptive pushdown as a new mechanism to avoid throttling the storage-layer computation during pushdown, which pushes the request back to the computation layer at runtime if the storage-layer computational resource is insufficient. Finally, we derive a general principle to identify pushdown-amenable computational tasks, by summarizing common patterns of pushdown capabilities in existing systems, and further propose two new pushdown operators, namely, selection bitmap and distributed data shuffle. Evaluation on SSB and TPC-H shows each optimization can improve the performance by 2.2 × , 1.9 × , and 3 × respectively. [ABSTRACT FROM AUTHOR]

Solving constraint satisfaction problems often involves a large amount of redundant exploration stemming from the existence of subproblems whose information can be reused for other subproblems. Subproblem dominance is a general notion of reusability that arises when one subproblem imposes more constraints on the remaining part of the search than another subproblem and allows the search to reuse the solutions of the dominating subproblem for the dominated subproblem. The search can exploit subproblem dominance by storing the subproblems that have been explored in a cache and abandoning the current subproblem whenever the cache contains a subproblem that dominates it. While using caching makes it possible to solve problems where subproblem dominance arises orders of magnitude faster, storing all of these subproblems can require a substantial amount of memory, making it impractical in many cases. This paper analyses the dominance between different subproblems for various constraint problems, revealing that only a relatively small number of subproblems dominate other subproblems. Based on these findings, two types of strategies are proposed for reducing the number of subproblems stored in the cache: limiting the number of subproblems that can be stored in the cache and periodically cleaning up the cache. An experimental evaluation demonstrates that these strategies provide an effective instrument for reducing the memory consumption of caching, allowing it to be used on a larger scale. However, there is a trade-off between saving memory and reducing redundant exploration, as removing subproblems from the cache may prevent dominance from being detected for certain subproblems. [ABSTRACT FROM AUTHOR]

Content-Centric Networking (CCN) has emerged as the most convenient architecture for efficient traffic management in contrast to the IP-based Internet. The in-network caching characteristic of CCN reduces server load and traffic in the network. Furthermore, it enhances end-user Quality-of-Service (QoS) by reducing content retrieval delay. Towards this, the proposed research focuses on the in-network caching capability of CCN-enabled IoT networks to improve content distribution and reduction of load from servers. In CCN-enabled IoT networks, content caching can be performed in any node of the fog layer that exists between the cloud server and IoT devices. To effectively utilize the available caching resources, it is crucial to determine the suitable fog node during content placement decisions. In this direction, a novel fuzzy hyper-edge clustering and content popularity-based caching scheme is proposed for CCN-based IoT networks. The proposed fuzzy clustering scheme dynamically partitions the network into overlapping clusters based on node connectivity. The proposed scheme overcomes the limitations of existing techniques where the number of clusters needs to be fixed initially. The proposed scheme considers the cluster information and content access frequency parameters for content placement decisions. Using the proposed heuristics, the scheme cooperatively caches the popular contents in the fog nodes near IoT devices. The performance of the proposed strategy is examined using extensive simulations on a realistic network configuration. Experiments are performed on the standard Abilene topology, and performance is measured using metrics such as cache hit ratio, average network hop count, and average network delay on cache sizes 50 and 100. The simulation results are recorded at 1, 250, 500, 750, 1000, 1250, 1500, 1750, and 2000 Simulation Time Units (STU). The results show that the proposed caching solution outperforms recent state-of-the-art techniques such as LCE, PDC, CPNDD, HPHC, and CSDD, making it suitable for CCN-enabled IoT networks. [ABSTRACT FROM AUTHOR]

IoT networks can provide many benefits and opportunities, although their implementation poses challenges. Cloud-only storage of IoT data would be very costly and time-consuming. In this paper, a new scheme is proposed for caching IoT content on the edge with SDN-based processing capability. The proposed scheme considers a global SDN controller, which coordinates cache decisions across the entire IoT network. The Moth-Flame Optimization-Cluster Head Selection (MFO-CHS) algorithm is used to cluster devices where the selected cluster heads send the IoT data to the edge nodes for caching. In addition, by utilizing edge caching capabilities and using MFO to select and cache the appropriate contents on edge nodes, the proposed Moth-Flame Optimization-Edge Caching (MFO-EC) algorithm can provide data with lower latency on upcoming requests. Caching can also help ensure reliability and availability since intermittent connections and power limitations affect IoT devices. Caching decisions regarding IoT characteristics are not made intelligently in the default caching scheme for maximizing device longevity and managing the possibility that content producers may become unreachable. This scheme considers several metrics, and the proposed moth-flame optimization (MFO) algorithms, MFO-CHS, and MFO-EC algorithms, which are nature-inspired paradigms for the edge caching problem called "MFO-SDN-EC", Moth-Flame Optimization-Software-defined Networking -Edge Caching, are used to select the best options regarding considered criteria and improve the QoS in the SDN based IoT environment. Based on simulations, our proposed caching method can reduce energy consumption by 45%, decrease the average response time by 49%, and also increase cache-hit rates. Furthermore, our results demonstrate our algorithm's superiority over several current approaches in terms of assessment measures. [ABSTRACT FROM AUTHOR]

Reducing end-to-end latency is a key requirement for efficient and reliable new services offered by next-generation mobile networks. In this context, it is critical for mobile network operators (MNOs) to enable faster communications over backhaul transport networks between next-generation base stations and core networks. However, MNOs will need to make new investments and optimize many points of their current transport infrastructure to serve next-generation services well. In addition, even if MNOs make these investments, there may always be faults and performance degradation in transport networks. This paper presents a new approach to reduce the dependence of MNOs services on the quality of transport networks and rely on software updates on radio access network and core network components. A hyper text transfer protocol (HTTP)-based user plane that can be cached and accelerated is proposed, making it an ideal solution to combat transport problems in next-generation mobile networks. Numerical tests validate our proposed approach and underscore the significant improvements in transfer time, throughput, and overall performance achieved by leveraging HTTP caching and acceleration techniques. More specifically, GPRS tunneling protocol-user plane (GTP-U) is, on average, 35% slower than HTTP, with the performance difference increasing as the data size grows, primarily due to additional overhead and GTP-U encapsulation time. Additionally, HTTP caching with a size of 20 MB provides a 9.5% acceleration in data transfer time, with an average increase of approximately 9% when the data size exceeds 20 MB. [ABSTRACT FROM AUTHOR]

Today, the rapid development, large volume, and global access of multimedia applications have demanded the shifting of network functionality from the central server to the near user. In recent times, Edge Computing (EC) and Information Centric Networking (ICN) have been presented as arising advances for content dissemination near the end user. The EC aims to provide content locally by reducing the burden of the core networks, while ICN allows content routing and forwarding based on content names directly. The inherent in-network caching feature of ICN facilitates caching by intermediate network nodes. The combined use of EC and ICN can efficiently handle content dissemination and ultimately improves user experience. In this regards, an ICN based edge caching scheme has been proposed for handling multimedia big data traffic in IoT based smart cities, while incorporating four caching attributes in its proposed design. Firstly, a layered network architecture has been presented that offers Device-to-Device (D2D) communication and ICN support at the application layer of Base station (BS) for utilizing caching of the requested content at edge of the network. Secondly, a decision on caching of contents at network nodes in layered network architecture has been presented based on various centrality measures, which supports efficient caching. Thirdly, this work offers caching of content near the delivery path in ICN network tiers, while leveraging near path caching for fast content dissemination. Lastly, reproactive caching where proactive caching is followed by reactive caching for controlling the network traffic during peak hours has been integrated in to the design model. The performance of the proposed scheme has been evaluated by conducting simulations in Icarus- an ICN caching simulator against various caching benchmark schemes. The results received from the experiments have shown significant performance improvement of our proposed scheme for different performance metrics including cache hit ratio, content retrieval delay, content path stretch, and internal link load. [ABSTRACT FROM AUTHOR]

Data analysis workflows in High Energy Physics (HEP) read data written in the ROOT columnar format. Such data has traditionally been stored in files that are often read via the network from remote storage facilities, which represents a performance penalty especially for data processing workflows that are I/O bound. To address that issue, this paper presents a new caching mechanism, implemented in the I/O subsystem of ROOT, which is independent of the storage backend used to write the dataset. Notably, it can be used to leverage the speed of high-bandwidth, low-latency object stores. The performance of this caching approach is evaluated by running a real physics analysis on an Intel DAOS cluster, both on a single node and distributed on multiple nodes. [ABSTRACT FROM AUTHOR]

Due to the advent of IoT and the increasing interest of billions of Internet users towards video contents, a huge multimedia flows has been generated, and as a consequence, a massive load is applied on the underlying core network. This change can affect the network stability and lead to potential performance degradation (such as congestion and delays). This is because multimedia flows are hungry in bandwidth, and also the classical routing protocols currently used in IoT core network (like OSPF) are not adapted yet to support the heavy and the large scale of multimedia traffics with a good quality of service (QoS). In this paper, we introduce the multicommodity-based routing by proposing two contributions, Maximum Concurrent Flow Protocol (MCFPr) and Cache-based Maximum Concurrent Flow (C-MCF). They are conceived based on the Maximum Concurrent Flow approach in order to optimize the routing of multimedia data in the backbone of IoT networks. Both contributions are studied and compared with the state-of-art approaches under different scenarios showing good results, especially in the number of data packets sent (improvement by 50%), and in the transmission time (50% faster compared to the majority), which makes them promising solutions for a rapid and efficient routing in IoT core networks. [ABSTRACT FROM AUTHOR]

Behavioral plasticity can be described as the ability to adjust behavior depending on environmental information. We used a food-storing (caching) paradigm, during which individuals either ate or cached food under different conditions, to investigate whether they could adjust their caching behavior when observed by conspecifics and heterospecifics and which social cues they used to elicit these behavioral changes. We examined the location and number of caches made by two corvid species differing in sociality: highly social pinyon jays (Gymnorhinus cyanocephalus) and less social Clark's nutcrackers (Nucifraga columbiana). Although pinyon jays cached a similar amount of food across conditions, they allocated significantly more caches to areas less accessible to the observer. Nutcrackers, however, significantly reduced the number of seeds cached when another nutcracker was present in comparison to when they cached alone. Both species relied on different social cues to elicit re-caching: pinyon jays responded to the amount of time the observer spent close to the caching locations, whereas nutcrackers responded to the amount of time the observer spent pilfering their caches. The differences in cache protection behaviors and the social cues eliciting them may be explained by the species' social organization. Pinyon jays may only adjust their caching behavior when necessary, as they are often surrounded by other individuals. Being less social, Clark's nutcrackers reduce their caching when observed, as they have more opportunities to cache alone and may resort to additional cache protection when experiencing pilferage. Overall, our results provide insight into understanding how pressures associated with the social environment may influence foraging behaviors. Significance statement: To maximize resources, Corvidae will hide food for later consumption and seek out the hidden food of others. These birds also subvert this ecological game of "hide-and-seek" by re-hiding food that other birds know about. We demonstrate that two corvid species initiate "hide-and-seek" in response to different social information. Social pinyon jays re-hide their food after another bird approaches their hiding spots, a proactive response suited for species living in groups, in which attributing food theft to a specific individual may be difficult. Less-social Clark's nutcrackers re-hide food only after seeing another bird steal from them, a reactive response suited for species that typically have more opportunities for privacy when hiding food. We demonstrate corvids adapt to the risk posed by birds "seeking" their food, though which behaviors of the seeker are deemed risky differ between species and are shown to align with ecological demands. [ABSTRACT FROM AUTHOR]

Information-Centric Networking (ICN) is an emerging paradigm that allows users to retrieve content items securely, independently of their location. Therefore, an item may be stored in a location outside the administrative realm of its owner (e.g., cache, CDN node). In this paper, we propose a solution that allows these 3rd party storage nodes to verify that a user is authorized to access a a particular content item. We consider an SDN-based ICN deployment and we leverage Verifiable Credentials to build chains of trust, as well as to express users' capabilities. With our solution, users can prove authorization using a single message that can be integrated into a content request. Additionally, verifying entities do not have to store any secret. Our solutions support delegation, and it is lightweight. [ABSTRACT FROM AUTHOR]

We consider a setting where applications, such as websites or games, need causal access to objects available in geo-replicated cloud data stores. Common ways of implementing causal consistency involve hiding objects while waiting for their dependencies or waiting for server replicas to synchronize. To minimize delays and retrieve objects faster, applications may try to reach different server replicas at once. This entails a cost because providers charge for each reading request, including reading misses where the causal copy of the object is unavailable. Therefore, latency and cost are conflicting goals, which we control by selecting where to read and when. We formulate this challenge as a multi-criteria optimization problem and propose five non-dominated reading strategies, four of which are Pareto optimal, in a setting constrained to two server replicas. We validate these solutions on the following real cloud storage services: AWS S3, DynamoDB and MongoDB. Savings of as much as 50% on reading costs, with no significant or even a positive impact on latency, demonstrate that both clients and cloud providers could benefit from richer services compatible with these retrieval strategies. [ABSTRACT FROM AUTHOR]

It is natural to generalize the online k\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$k$$\end{document}-Server problem by allowing each request to specify not only a point p, but also a subset S of servers that may serve it. To date, only a few special cases of this problem have been studied. The objective of the work presented in this paper has been to more systematically explore this generalization in the case of uniform and star metrics. For uniform metrics, the problem is equivalent to a generalization of Paging in which each request specifies not only a page p, but also a subset S of cache slots, and is satisfied by having a copy of p in some slot in S. We call this problem Slot-Heterogenous Paging. In realistic settings only certain subsets of cache slots or servers would appear in requests. Therefore we parameterize the problem by specifying a family S⊆2[k]\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}\subseteq 2^{[k]}$$\end{document} of requestable slot sets, and we establish bounds on the competitive ratio as a function of the cache size k and family S\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}$$\end{document}:If all request sets are allowed (S=2[k]\{∅}\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}=2^{[k]}\setminus \{\emptyset \}$$\end{document}), the optimal deterministic and randomized competitive ratios are exponentially worse than for standard Paging (S={[k]}\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}=\{[k]\}$$\end{document}).As a function of |S|\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$|{\mathcal {S}}|$$\end{document} and k, the optimal deterministic ratio is polynomial: at most O(k2|S|)\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$O(k^2|{\mathcal {S}}|)$$\end{document} and at least Ω(|S|)\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\Omega (\sqrt{|{\mathcal {S}}|})$$\end{document}.For any laminar family S\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}$$\end{document} of height h, the optimal ratios are O(hk) (deterministic) and O(h2logk)\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$O(h^2\log k)$$\end{document} (randomized).The special case of laminar S\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}$$\end{document} that we call All-or-One Paging extends standard Paging by allowing each request to specify a specific slot to put the requested page in. The optimal deterministic ratio for weighted All-or-One Paging is Θ(k)\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\Theta (k)$$\end{document}. Offline All-or-One Paging is NP\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\mathbb{N}\mathbb{P}$$\end{document}-hard. Some results for the laminar case are shown via a reduction to the generalization of Paging in which each request specifies a set P\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$P$$\end{document} of pages, and is satisfied by fetching any page from P\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$P$$\end{document} into the cache. The optimal ratios for the latter problem (with laminar family of height h) are at most hk (deterministic) and hHk\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$hH_k$$\end{document} (randomized).If all request sets are allowed (S=2[k]\{∅}\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}=2^{[k]}\setminus \{\emptyset \}$$\end{document}), the optimal deterministic and randomized competitive ratios are exponentially worse than for standard Paging (S={[k]}\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}=\{[k]\}$$\end{document}).As a function of |S|\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$|{\mathcal {S}}|$$\end{document} and k, the optimal deterministic ratio is polynomial: at most O(k2|S|)\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$O(k^2|{\mathcal {S}}|)$$\end{document} and at least Ω(|S|)\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\Omega (\sqrt{|{\mathcal {S}}|})$$\end{document}.For any laminar family S\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}$$\end{document} of height h, the optimal ratios are O(hk) (deterministic) and O(h2logk)\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$O(h^2\log k)$$\end{document} (randomized).The special case of laminar S\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$${\mathcal {S}}$$\end{document} that we call All-or-One Paging extends standard Paging by allowing each request to specify a specific slot to put the requested page in. The optimal deterministic ratio for weighted All-or-One Paging is Θ(k)\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\Theta (k)$$\end{document}. Offline All-or-One Paging is NP\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\mathbb{N}\mathbb{P}$$\end{document}-hard. [ABSTRACT FROM AUTHOR]

Reproduction is an energetically expensive activity for both sexes. However, if males and females differ in their annual timing of reproduction, such that peak investment for one sex occurs during a more resource-limited period, there is an opportunity for sex-specific selection to act on the acquisition of energetic resources. Both male and female North American red squirrels (Tamiasciurus hudsonicus) cache conifer cones, although males typically have larger caches than females. Peak energetic investment in reproduction occurs for males during the mating season in winter and early spring (when squirrels rely almost exclusively on cached resources) and for females during lactation (which can align with fresh food availability). We provide evidence that suggests sex differences in cache size are likely driven by a stronger positive connection between cached resources and components of fitness for males than for females. Specifically, males with larger caches have greater siring success than males with smaller caches, whereas for females, only early breeding females experience a positive effect of cache size on the number of recruits produced. We also show that males sire pups and females give birth earlier in the year if they have larger caches compared with squirrels of the same sex with smaller caches. Sexual selection can thus extend beyond traits directly connected to mating behavior, and can act on traits related to acquiring resources needed to fuel reproduction that are expressed months or years in advance of breeding efforts. Significance statement: The timing and energetic requirements of reproduction are often different for males and females which could drive different life history strategies between the sexes. Red squirrels in the southwest Yukon, Canada cache white spruce cones in autumn, which serve as their primary food source until fresh food becomes available during summer. We measured the size of squirrel caches and subsequently monitored their reproduction to test whether the influence of stored food differs for males and females. We confirmed that males have larger caches than females and show that this is likely driven by a stronger positive association of cache size and components of fitness for males than for females. These findings highlight that the strength of selection can differ on the homologous traits of males and females leading to sex-specific extended phenotypes. [ABSTRACT FROM AUTHOR]

In today's data landscape, data streams are well represented. This is mainly due to the rise of data-intensive domains such as the Internet of Things (IoT), Smart Industries, Pervasive Health, and Social Media. To extract meaningful insights from these streams, they should be processed in real time, while solving an integration problem as these streams need to be combined with more static data and their domain knowledge. Ontologies are ideal for modeling this domain knowledge and facilitate the integration of heterogeneous data within data-intensive domains such as the IoT. Expressive reasoning techniques, such as OWL2 DL reasoning, are needed to completely interpret the domain knowledge and for the extraction of meaningful decisions. Expressive reasoning techniques have mainly focused on static data environments, as it tends to become slow with growing datasets. There is thus a mismatch between expressive reasoning and the real-time requirements of data-intensive domains. In this paper, we take a first step towards bridging the gap between expressivity and efficiency while reasoning over high-velocity IoT data streams for the task of event enrichment. We present a structural caching technique that eliminates reoccurring reasoning steps by exploiting the characteristics of most IoT streams, i.e., streams typically produce events that are similar in structure and size. Our caching technique speeds up reasoning time up to thousands of times for fully fledged OWL2 DL reasoners and even tenths and hundreds of times for less expressive OWL2 RL and OWL2 EL reasoners. [ABSTRACT FROM AUTHOR]

Avoiding problems such as packet loss in the transport network is crucial for mobile network providers to offer high-quality services reliably and without interruptions. In this paper, we propose and compare three different transmission strategies, namely Caching, Network Coding (NC) and Repetition enabled transmission in the User Plane (UP) of mobile backhaul for network operators to prevent such performance degradation. In the proposed NC-enabled transmission method, NC provides robustness to transport network failures such that no further retransmission is required by the User Equipment (UE) compared to conventional approaches where UE applications perform retransmissions. The proposed scheme requires only a minor modification to the packet structure of the UP protocol, which requires a small development effort and no new extensions to the current UE standard features. We also discuss their placement in the O-RAN protocol stack and in the core network, and propose a new architecture that can utilize caching, repetition and NC features in the mobile network architecture. Our simulation results show that an exact 1% packet loss ratio in the backhaul link results in an additional total transmission time of 59.44% compared to the normal GPRS Tunneling Protocol-User Plane (GTP-U) transmission. Applying NC at a rate of 1% and 2% reduces this value to 52.99% and 56.26%, respectively, which is also better than the total transmission time of some previously studied dynamic replication schemes while keeping the bandwidth utilization at low rates. On the cache side, a reduction in latency of about 20% can be achieved with a cache size of 100 MB. At the end of the paper, we summarize some of the benefits and limitations of using these three strategies in UP of mobile backhaul networks. [ABSTRACT FROM AUTHOR]

The rapid increase of mobile devices has made user mobility one of the important factors affecting the cache. With the development of energy harvesting technology, the cache must consider not only the quality of service but also the energy consumption, so the classic popular cache-based strategy is not the optimal strategy. For the above problems, this article proposes an optimization algorithm for user and small base station (SBS) caching strategies based on energy harvesting and mobility in cellular networks and device-to-device (D2D) scenarios. Considering the mobility of users and their social relationship, the cost function of users and SBS are respectively defined in combination with the cost of file transmission. The user's cost function includes its own cost and the cost of its "friends", while the SBS cost function is the cost of the entire system, and then the two caching problems are constructed as integer programming problems with cost minimization as the optimization goal. It is proved that the optimization objective function has the monotone submodular property and combined with the cache space and energy constraint, a greedy algorithm is proposed to optimize the caching strategy of users and SBS in turn. The simulation results show that the algorithm proposed in this paper can reduce the cost of transmission and make better use of cache and energy resources. [ABSTRACT FROM AUTHOR]

The hippocampal formation (HF) processes spatial memories for cache locations in food-hoarding birds. Hoarding is a seasonal behavior, and seasonal changes in the HF have been described in some studies, but not in others. One potential reason is that birds may have been sampled during the seasonal hoarding peak in some studies, but not in others. In this study, we investigate the seasonal changes in hoarding and HF in willow tits (Poecile montanus). We compare this to seasonal changes in HF in a closely related non-hoarding bird, the great tit (Parus major). Willow tits near Oulu, Finland, show a seasonal hoarding peak in September and both HF volume and neuron number show a similar peak. HF neuronal density also increases in September, but then remains the same throughout winter. Unexpectedly, the great tit HF also changes seasonally, although in a different pattern: the great tit telencephalon increases in volume from July to August and decreases again in November. Great tit HF volume follows suit, but with a delay. Great tit HF neuron number and density also increase from August to September and stay high throughout winter. We hypothesize that seasonal changes in hoarding birds' HF are driven by food-hoarding experience (e.g., the formation of thousands of memories). The seasonal changes in great tit brains may also be due to experience-dependent plasticity, responding to changes in the social and spatial environment. Large-scale experience-dependent neural plasticity is therefore probably not an adaptation of food-hoarding birds, but a general property of the avian HF and telencephalon. [ABSTRACT FROM AUTHOR]

Although pigeons do not naturally cache and recover food items as found in members of the corvid and parid families, an operant analog of food caching and recovery in pigeons was studied in four experiments. Pigeons were trained to peck a caching key that added a fixed increment of time to the final duration of reinforcement obtained by pecking a payoff key. The same key served as the caching and payoff keys in Experiment 1, but separate caching and payoff keys were used in Experiments 2–4. In Experiments 2–3, each peck on a left red caching key added 0.5 s of reinforcement earned by pecking a right white payoff key. In Experiment 4, red or green caching keys appeared on different trials, with 0.5 s of reinforcement earned for pecking the red key and 1.0 s of reinforcement earned for pecking the green key. Pigeons showed an increased number of pecks on the caching key over ten sessions in Experiments 1–3 and more pecks on the green caching key than on the red caching key in Experiment 4. [ABSTRACT FROM AUTHOR]

Minimizing transaction latency and network traffic is pivotal in large-scale Internet of Things (IoT) applications. This paper investigates the fundamentals of distributed caching, cache coordination, network function virtualization, fog computing, and software-defined networking to avoid service loss and enhance quality of experience (QoE) in IoT applications. We visualize caching as a virtual network function (VNF) and use fog nodes to persistently host a large number of micro-caches as VNFs in the vicinity of their interest locations. We formulate the cache placement and migration process as a multi integer linear programming (MILP) problem. Firstly, we propose a cache consensus function to decide whether a content needs caching or not. Secondly, we propose a fuzzy inference based algorithm to solve the MILP problem for dynamic placement and migration of micro-caches at appropriate locations in geographically co-located 5G radio access networks. Another significant contribution of the proposed scheme is the inter-RAN cooperation among micro-caches to augment service quality by mitigating network traffic. Simulation results show the superiority of the proposed scheme over existing approaches. [ABSTRACT FROM AUTHOR]

In most storage systems, the storage nodes store data on a local filesystem. Thus, unless they have a dedicated caching layer, they benefit from the usual filesystem cache in the host's free memory. However, in erasure-coded storage systems, caching is effective only if all the systematic fragments corresponding to an object are in the cache. In this work, we propose a new caching policy adapting traditional methods to erasure-coded storage systems. The main idea of our solution is to cache a full object rather than fragments object. A simulation-based evaluation showed that our full replica solution is able to improve the cache hit ratio and reduce the cache waste ratio compared to the traditional caching method. Moreover, experimental evaluation has been conducted. It indicates that our implementation not only validates the previous results but also shows that cache hits on full replicas have a better request response time. [ABSTRACT FROM AUTHOR]

As one key enabler of Intelligent Transportation System (ITS), Vehicular Ad Hoc Network (VANET) has received remarkable interest from academia and industry. The emerging vehicular applications and the exponential growing data have naturally led to the increased needs of communication, computation and storage resources, and also to strict performance requirements on response time and network bandwidth. In order to deal with these challenges, Mobile Edge Computing (MEC) is regarded as a promising solution. MEC pushes powerful computational and storage capacities from the remote cloud to the edge of networks in close proximity of vehicular users, which enables low latency and reduced bandwidth consumption. Driven by the benefits of MEC, many efforts have been devoted to integrating vehicular networks into MEC, thereby forming a novel paradigm named as Vehicular Edge Computing (VEC). In this paper, we provide a comprehensive survey of state-of-art research on VEC. First of all, we provide an overview of VEC, including the introduction, architecture, key enablers, advantages, challenges as well as several attractive application scenarios. Then, we describe several typical research topics where VEC is applied. After that, we present a careful literature review on existing research work in VEC by classification. Finally, we identify open research issues and discuss future research directions. [ABSTRACT FROM AUTHOR]

We report an observation at Jhalana Leopard Reserve (JLR), Jaipur, India. On 16 March 2019, we saw a female walking up the mountain while calling her two, 4-month-old, male and female cubs. This allowed several safari jeeps to park in the shade of nearby Acacia trees. Two Striped Hyenas (Hyaena hyaena) approached and sniffed at the base of one of the trees near the parked jeeps. Upon seeing the Hyaenas, the female ran down the mountain, passed between the jeeps, and climbed into the tree. That is when we noticed the body of the female cub at a height of approximately 4.5 m. The female licked the body of the cub for several minutes and then picked it up in her mouth, climbed down from the tree, passed again between the jeeps, and walked up the mountain towards a dense stand of Thor (Euphorbia caducifolia), a thorny cactus. Our observations display how a mother leopard that has lost a cub refuses to abandon the carcass, cached it in a tree, and when discovered by scavengers removed it to a thicket of cacti. We consider the behavior towards her dead cub, and subsequent caching when discovered by other animals, to be the first evidence for thanatological expression in leopards. [ABSTRACT FROM AUTHOR]

Database engines and file systems have been using prefetching and caching technologies for decades to enhance the performance of I/O-intensive applications. When future data access needs to be accelerated, prefetching methods often provide gains depending on the latency of the entire system by loading primary memory elements. Its execution time, where the data level prefetching rules are set, has to be much improved, as they are challenging to optimize, comprehend, and manage. This paper aims to introduce a novel distributed file system (DFS) model through dynamic prefetching, that includes four processes such as (1) Identification of popular files, (2) Estimation of support value for a file block, (3) Extraction of frequent block access patterns, and (4) Matching algorithm. At first, the input files are given to the first phase (i.e.), identification of popular sizes, where the popular files are identified. The support value of the file blocks that correspond to popular files is calculated in the second stage. Then, the extraction of frequent block access patterns is done in the third phase. At last, in the matching algorithm, the identification or prediction of frequent access pattern of the query is done by the optimized Neural Network (NN). Here, the weight of NN is optimally tuned by the Harmonic Mean based Grey Wolf Optimization (HMGWO) Algorithm.The proposed NN + HMGWO model produces reduced FPR values with good quality, which are 70.84%, 73.86%, 70.51%, 62.90%, 55.76%, 78.63%, and 73.86%, respectively, in comparison to other standard models like NN + WOA, NN + GWO, NN + PSO, NN + FF, FBAP, NN, and SVM. Lastly, the effectiveness of a chosen scheme is compared to other current methods in terms of delay analysis, latency analysis, hit ratio analysis, and correspondingly. [ABSTRACT FROM AUTHOR]

The Mars 2020 mission seeks to conduct a new scientific exploration on the surface of Mars. The Perseverance Rover will be sent to the surface of the Jezero Crater region to study its habitability, search for biosignatures of past life, acquire and cache samples for potential return, and prepare for possible human missions. To enable these objectives, an innovative Sampling and Caching Subsystem (SCS) has been developed and tested to allow the Perseverance Rover to acquire and cache rock core and regolith samples, prepare abraded rock surfaces, and support proximity science instruments. The SCS consists of the Robotic Arm (RA), the Turret and Corer, and the Adaptive Caching Assembly (ACA). These elements reside and interact both inside and outside of the Perseverance Rover to enable surface interactions, sample transfer, and caching. The main body of the Turret consists of the Coring Drill (Corer) with a Launch Abrading Bit initially installed prior to launch. Mounted to the Turret main structure are two proximity science instruments, SHERLOC and PIXL, as well as the Gas Dust Removal Tool (gDRT) and the Facility Contact Sensor (FCS). These work together with the RA to provide the sample acquisition, abraded surface preparation, and proximity science functions. The ACA is a network of assemblies largely inside the front belly of the Rover, which combine to perform the sample handling and caching functions of the mission. The ACA primarily consists of the Bit Carousel, the Sample Handling Assembly (SHA), End Effector (EE), Sample Tubes and their Sample Tube Storage Assembly (STSA), Seals and their Dispenser, Volume, and Tube Assembly (DVT), the Sealing Station, the Vision Station, the Cover Parking Lot, and additional supporting hardware. These components attach to the Caching Component Mounting Deck (CCMD) that is integrated with the Rover interior. This work describes these major elements of the SCS, with an emphasis on the functionality required to perform the set of tasks and interactions required by the subsystem. Key considerations of contamination control and biological cleanliness throughout the development of these hardware elements are also discussed. Additionally, aspects of testing and validating the functionality of the SCS are described. Early prototypes and tests matured the designs over several years and eventually led to the flight hardware and integrated testing in both Earth ambient and Mars-like environments. Multiple unique testbed venues were developed and used to enable testing from low-level mechanism operation through end-to-end sampling and caching interactions with the full subsystem and flight software. Various accomplishments from these testing efforts are highlighted. These past and ongoing tests support the successful preparations of the SCS on its pathway to operations on Mars. [ABSTRACT FROM AUTHOR]

In modern large-scale distributed systems, analytics jobs submitted by various users often share similar work, for example scanning and processing the same subset of data. Instead of optimizing jobs independently, which may result in redundant and wasteful processing, multi-query optimization techniques can be employed to save a considerable amount of cluster resources. In this work, we introduce a novel method combining in-memory cache primitives and multi-query optimization, to improve the efficiency of data-intensive, scalable computing frameworks. By careful selection and exploitation of common (sub)expressions, while satisfying memory constraints, our method transforms a batch of queries into a new, more efficient one which avoids unnecessary recomputations. To find feasible and efficient execution plans, our method uses a cost-based optimization formulation akin to the multiple-choice knapsack problem. Extensive experiments on a prototype implementation of our system show significant benefits of worksharing for both TPC-DS workloads and detailed micro-benchmarks. [ABSTRACT FROM AUTHOR]

Recently Internet of Everything has emerged as integration of various IoT machines to which cloud computing provide storage to data and processing power to the geographically distributed IoT devices. In order to boost the efficiency of the system and Quality of Service(QoS), fog layer is added in the existing cloud infrastructure. Due to continuous increase in the time sensitive applications, reduction in latency is a crucial issue in the fog computing paradigm. Therefore, the main objective of this work is to reduce the latency in fog computing. To achieve this objective, popularity based caching is performed in this work by majorly focusing on the interest of the users. In this context, first clustering of the IoT devices is performed on the basis of their interests and distance between them using spectral clustering technique and then each cluster is mapped with the fog node such that caching of the popular files is done effectively. To further reduce the latency, in case of cache miss, the Device to Device (D2D) communication is used. Finally, association rules are also used to predict the future demands of the IoT devices. Performance analysis of the proposed scheme shows that the proposed method outperforms the other existing caching methods. [ABSTRACT FROM AUTHOR]

Decision trees are among the most popular classification models in machine learning. Traditionally, they are learned using greedy algorithms. However, such algorithms pose several disadvantages: it is difficult to limit the size of the decision trees while maintaining a good classification accuracy, and it is hard to impose additional constraints on the models that are learned. For these reasons, there has been a recent interest in exact and flexible algorithms for learning decision trees. In this paper, we introduce a new approach to learn decision trees using constraint programming. Compared to earlier approaches, we show that our approach obtains better performance, while still being sufficiently flexible to allow for the inclusion of constraints. Our approach builds on three key building blocks: (1) the use of AND/OR search, (2) the use of caching, (3) the use of the CoverSize global constraint proposed recently for the problem of itemset mining. This allows our constraint programming approach to deal in a much more efficient way with the decompositions in the learning problem. [ABSTRACT FROM AUTHOR]

Location-based services are an important category of context-aware computing, which play an important role in providing the continuous, local and spatially confined information systems very efficiently and accurately to their clients. The key component in location-based services is the current location of a mobile user. Thus, to protect mobile users' location and their other information to an untrusted party with consideration of minimal waiting time, Optimal Mobility Aware Cache data Pre-fetching and Replacement policy (OMCPR) is being proposed here. In this continuous location-based services model, the system introduces a mediator namely Anonymizer by employing the prefetching facility for spatial K-anonymity that resides in between the user and Query Analyser to form a cloaking region using mobile user inputs (data freshness, the contribution rate of cell's cache and location). It provides high-quality lossless location-based services by the utilization of the frequent pattern mining of mobile users' trajectories to forecast their next position as per mobility and multiple constraints. A client–server based queueing model is used to simulate the proposed OMCPR platform. It provides higher privacy protection than the current state of the art strategies available, also minimizes the overhead of the LBS server and waiting time of mobile users by the addition of the prefetching facilities to Anonymizer. [ABSTRACT FROM AUTHOR]

While neural network models keep scaling in depth and computational requirements, biologically accurate models are becoming more interesting for low-cost inference. Coupled with the need to bring more computation to the edge in resource-constrained embedded and IoT devices, specialized ultra-low power accelerators for spiking neural networks are being developed. Having a large variance in the models employed in these networks, these accelerators need to be flexible, user-configurable, performant and energy efficient. In this paper, we describe CyNAPSE, a fully digital accelerator designed to emulate neural dynamics of diverse spiking networks. Since the use case of our implementation is primarily concerned with energy efficiency, we take a closer look at the factors that could improve its energy consumption. We observe that while majority of its dynamic power consumption can be credited to memory traffic, its on-chip components suffer greatly from static leakage. Given that the event-driven spike processing algorithm is naturally memory-intensive and has a large number of idle processing elements, it makes sense to tackle each of these problems towards a more efficient hardware implementation. With a diverse set of network benchmarks, we incorporate a detailed study of memory patterns that ultimately informs our choice of an application-specific network-adaptive memory management strategy to reduce dynamic power consumption of the chip. Subsequently, we also propose and evaluate a leakage mitigation strategy for runtime control of idle power. Using both the RTL implementation and a software simulation of CyNAPSE, we measure the relative benefits of these undertakings. Results show that our adaptive memory management policy results in up to 22% more reduction in dynamic power consumption compared to conventional policies. The runtime leakage mitigation techniques show that up to 99.92% and at least 14% savings in leakage energy consumption is achievable in CyNAPSE hardware modules. [ABSTRACT FROM AUTHOR]

Host-side flash caching emerges as an effective solution for improving the performance of virtual machines (VMs) in cloud computing environment. However, for VMs with the commonly used Copy-on-Write (COW) virtual disks, flash caching in fact has negative impacts since it brings lots of unnecessary cache writes, hurting both the VM performance and the flash endurance. This paper presents COWCache, a COW-aware caching solution that addresses this problem by co-designing flash caching with COW-based virtual disks. First, COWCache designs a new architecture that bridges the semantic gap between flash caching and virtual disk management for realizing the VMs' real data locality. Second, it separately manages COW metadata with fine-grained caching and journaling to improve the metadata caching efficiency. Third, it provides a novel decoupled Copy-on-Write mechanism, which decouples the amplified data requests from the critical I/O path and only admits the data with real VM locality into flash cache. COWCache also introduces a new data structure, the virtual cache map, to mitigate the memory footprint overhead for indexing the cached data in flash. Evaluations show that COWCache improves the application performance by up to 122.7% and reduces the flash cache writes by up to 78.5% compared to traditional flash caching solutions. [ABSTRACT FROM AUTHOR]

In Peer-to-Peer (P2P) network systems, content (object) delivery between nodes is often required. One way to study such a distributed system is by defining games, which involve selfish nodes that make strategic choices on replicating content in their local limited memory (cache) or accessing content from other nodes for a cost. These Selfish Replication games have been introduced in Chun et al. (2004) for nodes that do not have any capacity limits, leaving the capacitated problem, i.e. Capacitated Selfish Replication (CSR) games, open. In this work, we first form the model of the CSR games, for which we perform a Nash equilibria analysis. In particular, we focus on hierarchical networks, given their extensive use to model communication costs of content delivery in P2P systems. We present an exact polynomial-time algorithm for any hierarchical network, under two constraints on the utility functions: 1) "Nearer is better", i.e. the closest the content is to the node the less its access cost is, and 2) "Independence of irrelevant alternatives", i.e. aggregation of individual node preferences. This generalization represents a vast class of utilities and more interestingly allows each of the nodes to have simultaneously completely different functional forms of utility functions. In this general framework, we present CSR games results on arbitrary networks and outline the boundary between intractability and effective computability in terms of the network structure, object preferences, and the total number of objects. Moreover, we prove that the problem of equilibria existence becomes NP-hard for general CSR games. By adding some constraints in the number of objects and their preferences, we show that the equilibrium can be found in polynomial time. Finally, we introduce the fractional version of CSR games (F-CSR) to represent content distribution. We prove that equilibrium exists for every F-CSR game, but it is PPAD-complete. [ABSTRACT FROM AUTHOR]

5G definition falls broadly into order of achievable data rate and reduction in end-to-end latency. Thanks to emerging technologies many features are available in the 5G design to detect, control and avoid congestion in the backhaul networks. In fact, 5G results from the conjunction of several recent technological developments, chief among them the re-purposing of next generation of wireless networks for large-scale functional connectivity and carrying of massive heterogeneous contents. For instance, information centric networks, as a promising candidate for the wireless caching architecture, can cache the contents and prohibits traffic avalanche entering the backhaul via content-based networking. The main objective of this paper is to minimize latency in 5G backhaul networks. The contribution of this paper is a twofold: (a) a distributed algorithm at the back-haul switches is proposed to detect and handle the congestion temporarily and locally with considering the fairness, IP friendliness, latency and convergence time. (b) an SDN-based centralized algorithm is proposed to treat the congestion via dynamic route selection, load-balancing, the orchestration of heterogeneous RBS components. [ABSTRACT FROM AUTHOR]

Named Data Networking (NDN) and Software Defined Networking (SDN) are two new and highly innovative paradigms. In fact, they are used to solve the problems of current Internet architecture. As the NDN architecture is currently under development, it needs a robust routing protocol, an effective cache replacement strategy and a fast forwarding process to be improved. In this paper, we propose novel forwarding, caching and routing approaches for NDN based on SDN (FCR-NS). In fact, we introduce a new NDN architecture, based on the SDN paradigm and on a routing protocol totally managed by SDN controller. In our solution, we use the new cache replacement policy, which calculates the popularity of local data in the switches, and the bloom filter structure, in order to make the forwarding strategy very fast. Our architecture is completely free from the current Internet architecture and uses only NDN messages. Thereby, it offers a complete separation between the control and data planes as it is based on the SDN network. The experiments, that were carried out with the ndnSIM simulator, have clearly shown the efficiency of our solution, which allows accelerating the actual deployment of the NDN architecture in a real Internet network. [ABSTRACT FROM AUTHOR]

High bandwidth demand is incited by online video streaming that has become a fundamental of many consumers' lives. To provide the best user experience taking into account the user device and the network available bandwidth, different new technologies have been proposed. MPEG Dynamic Adaptive Streaming over HTTP (DASH) is considered among the most used technology of video delivery nowadays. DASH standard is based on rate adaptation on the client side. However, to enhance the DASH delivery there is a growing need for new network architecture. Two main trends are investigated in the literature: integration of DASH over ICN/CCN architecture which allows in-network caching, and performing DASH streaming over SDN architecture to control network delivery. In this paper, we discuss the necessity and feasibility of a new hybrid architecture based on the combination of SDN and CCN to provide assisted DASH-aware networking which enables networks configuration according to the requirements of end users, network administrators and Internet service providers. Hence, our architecture allows the improvement of the Quality of Experience and the Quality of Service thanks to the SDN and CCN processes integrated. [ABSTRACT FROM AUTHOR]

Content-centric networking (CCN) is gradually becoming the alternative approach to the traditional Internet architecture through enlightening information (content) distribution on the Internet with content names. The growing rate of Internet traffic has adapted a content-centric architecture to better serve the user requirement of accessing a content. For enhancing content delivery, ubiquitous in-network caching is utilized to store a content in each and every router by the side of the content delivery path. From the study, it is evaluated that a better performance can be achieved when caching is done by a subset of CRs instead of all CRs in a content delivery path. Motivated by this, we proposed an adaptive neuro-fuzzy inference system-based caching (ANFIS-BC) scheme for CCN to improve the cache performance. The proposed ANFIS-BC scheme utilizes the feature of centrality-measures for selection of a router for caching in a network. Our results demonstrated that the ANFIS-BC scheme consistently achieves better caching gain across the multiple network topologies. [ABSTRACT FROM AUTHOR]

In content delivery networks (CDNs), caches are resources that must be allocated. For that purpose, videos' popularity knowledge helps to make efficient decisions about which videos should be cached. Thus, we must be able to anticipate future needs in terms of requested videos. To do this, we rely on the requests history. This paper focuses on predicting the videos' popularity: the daily number of requests. For that purpose, we propose a two-level prediction approach. At the first level, the experts compute the videos' popularity, each expert using its own prediction method with its own parameters. At the second level, the forecasters select the best experts and build a prediction based on the predictions provided by these experts. The prediction accuracy is evaluated by a loss function as the discrepancy between the prediction value and the real number of requests. We use real traces extracted from YouTube to compare different prediction methods and determine the best parameter tuning for experts and forecasters. The goal is to find the best trade-off between complexity and accuracy of the prediction methods used. Finally, we apply these prediction methods to caching. Prediction methods are compared in terms of cache hit ratio and update ratio. The gain brought by this two-level prediction approach is compared with that obtained by a single prediction level. The results show that the choice of a two-level prediction approach is justified. [ABSTRACT FROM AUTHOR]

Recently, Information-centric networking (ICN) has flourished research interest. One common and important feature of ICN is that has built-in caching capability, which means that every node can cache content along the content delivery path. To improve the transmission efficiency of content dissemination, we propose an efficient caching scheme for ICN, which is named as NCPP-based caching scheme. In our proposed caching scheme, we use the definition of node-content pass probability (NCPP), which taking both node utilization ratio and popularity of content into consideration, to decide whether the node needs to cache the content. In addition, the reasonable resource allocation can also improve the performance of ICN. Therefore, we propose a NUR-based resource allocation scheme, which uses the definition of node utilization radio (NUR). We compare the server hit ratio of random caching scheme and the proposed caching scheme by simulation. Our results show that our proposed scheme has smaller server hit ratio than random caching scheme. Furthermore, our proposed caching scheme depends on the number of requests. [ABSTRACT FROM AUTHOR]

For location-based services (LBS), the path with the shortest travel time is much more meaningful than the one with the shortest network distance, as it considers the live traffics in road networks. Usually, there are two ways for an LBS provider to provide the shortest travel-time paths for its queries, i.e., computing by itself or retrieving from external Web mapping services. However, both of these two ways are expensive, like costly computation and long latency. To accelerate shortest path query processing, we design an effective cache of shortest travel-time paths for LBS providers in this paper. Unlike the conventional path caching techniques, where the caches are only suitable for distance-based paths, our proposed cache is dynamic and can support travel-time-based paths. More importantly, a new cache operation, namely path join, is devised to estimate the path information for a query based on the cached paths, when the cache can not answer the query directly. Experimental results on a real Web mapping service and datasets confirm the effectiveness of the proposed techniques. [ABSTRACT FROM AUTHOR]

In distinction to today's IP-based, host-bound, Internet architecture, content-centric networking (CCN) emphasizes content by making it instantly addressable and routable. CCN has attracted attention in the research community as a means to cope with the increasing rate of Internet traffic. The host-to-host architecture is demonstrated to be inefficient in content distribution with a lot of bandwidth waste, and it is intricate to set up the network service because of the TCP/IPs location-dependence. CCN is a future Internet architecture which is directed to disentangle the above problems by location-independent content naming and world-wide content caching in a content router. An efficient caching is essential to reduce the delay and to enhance the performance of the network. In addition, a good cache replacement scheme is also necessary to decide which content should reside in the cache and which one should be evicted. The traditional caching replacement strategies schemes such as FIFO, LRU and MRU etc. are not updated as adaption of CCN from host-to-host Internet architecture. Before making replacement, a replacement strategy must performs the calculation of popularity of a content, local popularity of a content (intra-domain network), expected probability respective of demand for a content and instantaneous hit ratio. The traditional and existing popularity based cache replacement strategies do not consider mentioned key points. Therefore in this paper, we present a novel popularity based content eviction scheme for CCN with evaluation of local popularity of a content using the betweenness-centrality concept. The simulation results recommend that our proposed scheme can reliably accomplish the better performance across the other approaches proposed in this field. [ABSTRACT FROM AUTHOR]

Named data networking (NDN) has promising advantages, however, it is hard to deploy because of the lack of special hardware to support it. Besides, the lack of specific routing schema also restrains the advantages of NDN. To solve the problems of deployment and routing, we come up with the source routing schema over protocol-oblivious forwarding (POF) for NDN. POF is able to directly carry NDN packets without over IP because it provides an adaptable and programmable forwarding plane by defining a generic flow instruction set. Source routing is a flexible and scalable routing schema and provides the flexible and efficient implementation for the future network. The centralized management of the source routing schema over POF can provide the following properties: (i) quickly responding to the change of network, and (ii) forwarding the Interest packet to the best cache node. Experiments show that the source routing schema over POF for NDN can reduce more than 50% of the networking traffic flow and increase the cache hit rate by up to 25% more than the baseline schemas. Thus, the source routing schema over POF could be an implementation plan for NDN. [ABSTRACT FROM AUTHOR]

In this paper, we interest in web cache replacement policies namely “frequency-aware” policies that provide, generally, the best results in term of data movement reduction in the network. For the simple reason that they take into account one of the most significant web traffic characteristic “the access frequency”. However, the access frequency suffers from two main problems namely one-timer documents existence and cache pollution. Therefore, our aim is to replace the traditional frequency with a relative frequency; calculated using the access number and the document lifetime in the cache. Although the idea already exists in the literature, we strive to validate the relative frequency efficiency for the web proxy replacement policies. In this work, we implement three replacement policies namely least frequently used (LFU), least frequently used with dynamic aging (LFU-DA) and Greedy dual size frequency (GDSF). As well, their versions enhanced with relative frequency namely LFRU, LFRU-DA and GDSFR respectively are implemented and evaluated using synthetic and real workload. The simulation results show that the relative frequency is more effective, in terms of hit rate and byte hit rate, than the access number; i.e., the traditional frequency. Moreover, the simulation proves that the relative frequency solves the access frequency problems. [ABSTRACT FROM AUTHOR]

Content-centric networking (CCN) is gradually becoming an alternative approach to the conventional Internet architecture through the distribution of enlightening information (named as content) on the Internet. It is evaluated that the better performance can be achieved by caching is done on a subset of content routers instead of all the routers in the content delivery path. The subset of a content router must be selected in a manner such that maximum cache performance can be achieved. Motivated by this, we propose a Centrality-measures based algorithm (CMBA) for selection of an appropriate content router for caching of the contents. The Centrality-measures are based on the question: ”Who are the most important or central content router in the network for the caching of contents?”. We found that our novel CMBA could improve content cache performance along the content delivery path by using only a subset of available content routers. Our results recommend that our proposed work consistently achieves better caching gain across the multiple network topologies. [ABSTRACT FROM AUTHOR]

We introduce the subset assignment problem in which items of varying sizes are placed in a set of bins with limited capacity. Items can be replicated and placed in any subset of the bins. Each (item, subset) pair has an associated cost. Not assigning an item to any of the bins is not free in general and can potentially be the most expensive option. The goal is to minimize the total cost of assigning items to subsets without exceeding the bin capacities. The subset assignment problem models the problem of managing a cache composed of banks of memory with varying cost/performance specifications. The ability to replicate a data item in more than one memory bank can benefit the overall performance of the system with a faster recovery time in the event of a memory failure. For this setting, the number n of data objects (items) is very large and the number d of memory banks (bins) is a small constant (on the order of 3 or 4). Therefore, the goal is to determine an optimal assignment in time that minimizes dependence on n. The integral version of this problem is NP-hard since it is a generalization of the knapsack problem. We focus on an efficient solution to the LP relaxation as the number of fractionally assigned items will be at most d. If the data objects are small with respect to the size of the memory banks, the effect of excluding the fractionally assigned data items from the cache will be small. We give an algorithm that solves the LP relaxation and runs in time O(3dd+1poly(d)nlog(n)log(nC)log(Z)), where Z is the maximum item size and C the maximum storage cost. [ABSTRACT FROM AUTHOR]

Clusters with caching DSMs deliver programmability and performance by supporting shared-memory programming model and tolerating communication latency of remote fetches via caching. The input of a data parallel program is partitioned across machines in the cluster while the DSM transparently fetches and caches remote data as needed by the application. Irregular applications are challenging to parallelize because the input related data dependences that manifest at runtime require the use of speculation for efficiently exploiting parallelism. By speculating that there are no cross iteration dependences, multiple iterations of a data parallel loop are executed in parallel using locally cached copies of data; the absence of dependences is validated before committing the speculatively computed results. In this paper we show that in irregular data-parallel applications, while caching helps tolerate long communication latencies, using a value read from the cache in a computation can lead to misspeculation, and thus aggressive caching can degrade performance due to increased misspeculation rate. To limit misspeculation rate we present optimizations for distributed speculation on caching based DSMs that decrease the cost of misspeculation check and speed up the re-execution of misspeculated recomputations. These optimizations give speedups of 2.24× for graph coloring, 1.71× for connected components, 1.88× for community detection, 1.32× for shortest path, and 1.74× for pagerank over baseline parallel executions. [ABSTRACT FROM AUTHOR]

We study the smoothness of paging algorithms. How much can the number of page faults increase due to a perturbation of the request sequence? We call a paging algorithm smooth if the maximal increase in page faults is proportional to the number of changes in the request sequence. We also introduce quantitative smoothness notions that measure the smoothness of an algorithm. We derive lower and upper bounds on the smoothness of deterministic and randomized demand-paging and competitive algorithms. Among strongly-competitive deterministic algorithms, LRU matches the lower bound, while FIFO matches the upper bound. Well-known randomized algorithms such as PARTITION, EQUITABLE, or MARK are shown not to be smooth. We introduce two new randomized algorithms, called SMOOTHEDLRU and LRU-RANDOM. SMOOTHED-LRU allows sacrificing competitiveness for smoothness, where the trade-off is controlled by a parameter. LRU-RANDOM is at least as competitive as any deterministic algorithm but smoother. [ABSTRACT FROM AUTHOR]

Internet traffic volume is increasing and this causes scalability issues in content delivery. This problem can be addressed with different types of caching solutions. The incentives of different stakeholders to pay for these solutions are not known. However, it has been identified that Internet service providers (ISPs) need to be involved in the process of cache deployment due to their ownership of the network. This work evaluates a new business model where ISPs charge content providers (CPs) for a caching service because CPs benefit from more efficient content distribution. We provide conditions for sustainable paid in-network caching and their numerical evaluation in order to aid strategic decision-making by CPs, ISPs, and Cloud storage providers (CSPs). Although ISP caching as a paid service may not be an equilibrium, it turns out to be Pareto optimal at the right pricing. This encourages cooperation between CPs and ISPs. CSPs may choose cache friendly physical locations for their facilities in order to provide the necessary capacity to the ISPs. However, the required amounts are in all likelihood too small to be an incentive for the CSPs. ISP caching as a paid service can be an equilibrium when future benefits are considered and when the ISPs terminate caching-related improvements of service quality for clients who do not pay for caching. [ABSTRACT FROM AUTHOR]

The major challenge in a mobile ad hoc network lies in providing data to the desiring mobile nodes as and when required. Caching tends to increase data availability in a wireless ad hoc environment. Caching if employed along with clustering can bring about significant benefits in terms of information availability and information retrieval in an ad hoc environment. Clustering is highly employed in MANETs to bind together network nodes into clusters. Here we propose a Collaborative Clustering approach for Cooperative Caching (4C) in a mobile ad hoc network which improves overall cache maintenance and decreases message exchange overhead. It also increases the rate at which data is retrieved by reducing access latency. In addition it intends to decrease heavy traffic near the data server. In this work, all the cluster nodes within a cluster cooperate for caching and all the cluster heads in the entire network collaborate for efficient cache maintenance. Moreover clients can opt for registration with its respective cluster heads to receive recent updates of the cached information. Data Server pushes updates to the registered clients through cluster heads. [ABSTRACT FROM AUTHOR]

Modern information retrieval systems use several levels of caching to speedup computation by exploiting frequent, recent or costly data used in the past. Previous studies show that the use of caching techniques is crucial in search engines, as it helps reducing query response times and processing workloads on search servers. In this work we propose and evaluate a static cache that acts simultaneously as list and intersection cache, offering a more efficient way of handling cache space. We also use a query resolution strategy that takes advantage of the existence of this cache to reorder the query execution sequence. In addition, we propose effective strategies to select the term pairs that should populate the cache. We also represent the data in cache in both raw and compressed forms and evaluate the differences between them using different configurations of cache sizes. The results show that the proposed Integrated Cache outperforms the standard posting lists cache in most of the cases, taking advantage not only of the intersection cache but also the query resolution strategy. [ABSTRACT FROM AUTHOR]