Search

Secure wireless device identification is necessary if we want to ensure that any transmitted data reach only a desired receiver. However the fact that wireless communications are by nature broadcast creates unique challenges such as identity theft, eavesdropping for data interception, jamming attacks to disrupt legitimate transmissions, etc. This paper proposes a new integrated radioprint framework (IRID) that has two main components. First, we propose a machine learning-based radio identification solution that relies on hardware variabilities of internal components of the transmitter caused during manufacturing, allowing us to achieve passive device identification. Second, we introduce a new kind of covert channel, based on variations in the emitted signal strength, which allows us to implement unique active device identification. We evaluate our proposed framework on an experimental test-bed of 20 identical WiFi devices. Although our experiments deal only with IEEE 802.11b, the approach can easily be extended to any wireless protocol. The experimental results show that our proposed solution can differentiate between network devices with accuracy in excess of 99% on the basis of a standard-compliant implementation.

Syslog parsing is of vital importance for the detection, diagnosis and prediction of network device failures in a datacenter. A common approach to syslog parsing is to extract templates from historical syslogs, after which syslogs are matched to these templates. To address the problems in the existing syslog parsing techniques, we propose a novel framework, Craftsman, which identifies frequent combinations of (syslog) words and then applies them as templates. Craftsman empirically extracts templates accurately, is extremely efficient in template matching, and naturally supports incremental learning. To compare the performance of Craftsman and three other template learning techniques designed for network devices, we experiment them on two-years' worth of syslogs collected from network devices deployed across 10+ datacenters of a tier-one service provider. The experiments demonstrate that Craftsman achieves a close-to-one accuracy (as measured by rand index), and improves the computational efficiency by 6.88 to 10.25 times in template matching, and by 730 to 6847 times in syslog parsing. It also improves the accuracy (as measured by F1 measure) of failure prediction by 13.07% to 188%. In addition, we demonstrate Craftsman's superior generality by comparing it with three widely-applied log parsing methods over five large log datasets collected from servers, distributed systems and applications.

The low-latency advantages of fog computing can be applied to solve high transmission latency problems of many network architectures in Internet of Vehicles. Therefore, this paper studies the application of fog computing in Internet of Vehicles. Considering that the fog network equipment deployed in Internet of Vehicles is relatively scattered, a new network architecture is proposed, which integrates cloud computing, fog computing and software defined network and other technologies. The proposed framework uses software defined network to centrally control fog network and obtains equipment performance of fog network. Furthermore, the optimal load balancing strategy is developed by communication overhead and other information. Based on time delay modeling of fog network, we study the time delay modeling of cloud-fog network and the energy consumption modeling of fog network. In addition, this paper models the selection process of data transmission network and data calculation execution server of delay-tolerant data as a partially observable Markov decision process optimization strategy in software defined Internet of Vehicles. By observing the state of system, current storage makes optimal decisions on data transmission and selection of computing nodes, thereby minimizing system overhead. Simulation results show that the proposed scheme can effectively reduce transmission delay and system overhead, improve data calculation efficiency.

Software Defined Network (SDN) is a flexible paradigm that provides support for a variety of data-intensive applications with real-world smart Internet of Things (IoT) devices. This emerging architecture updates with the managing ability and network control. Still, the benefits are challenging to achieve due to the presence of intruder flow into the network. The research topic of intrusion detection and prevention system (IDPS) has grasped the attention to reduce the effect of intruders. Distributed Denial of Service (DDoS) is a targeted attack that develops malicious traffic is flooded into a particular network device. These intruders also involve even with legitimate network devices, the authenticated device will be compromised to inject malicious traffic. In this paper, we investigate the involvement of intruders in three-Tier IDPS with regard to user validation, packet validation and flow validation. Not all the authentication users can be legitimate, since they are compromised, so that the major contribution is to identify all the compromised devices by knee analysis of the packets. Routers are the edge devices employed in first tier which is responsible to validate the IoT user with RFID tag and encrypted signature. Then the authenticated user's packets are submitted into second tier with switches that validates the packets using type-II fuzzy filtering. Then the key features are extracted from packets and they are classified into normal, suspicious and malicious. The mismatched packets are analyzed in controllers which maintain two queues as suspicious and normal. Then suspicious queue packets are classified and predicted using deep learning method. The proposed work is experimented in OMNeT++ environment and the performances are evaluated in terms of intruder Detection Rate, Failure Rate, Delay, Throughput and Traffic Load.

Recent developments in mobile and wireless networks have paved the way for them to become a fabric of society and the economy. The ever-increasing penetration rate of mobile telephony and wireless broadband data access, and the ubiquity of WiFi are just a few examples of this phenomenon. While multihop wireless networks (e.g., WiMax, LTE-A, ad hoc, sensor, and mesh networks) offer many advantages, such as enhanced capacity, extended communication range, deployment, and operational flexibility, they usually lack provisioning for network robustness and do not, in general, withstand network equipment failures. Network failures may have drastic effects on network performance and hinder network operation. The capability of a network to deliver data successfully in a timely manner and continue its services despite the presence of failures and attacks is referred to as survivability, which is an important system design and operational characteristic that must be provisioned.

This article focuses on plug & play network protocols - SSDP and WSD and security aspects. These protocols facilitate installation and deployment of new network devices in local networks. Implementation of these protocols is simple but lacks any security features. Therefore, malicious user or intruder can easily misuse them to collect sensitive data and files. As these protocols are also implemented in MS Windows, implementation of these protocols and possible attacks using fake devices deployed in local network is described.

Software Defined Wide Area Network (SD-WAN) was originally proposed as an alternative solution to redesign the architecture of the WAN. Like its technology precursor Software Defined Networking, SD-WAN was aiming at simplifying the management and operation of the networks (with a particular focus on WAN scenarios) by decoupling the networking hardware from its control programs and using software and open APIs to abstract the infrastructure and manage the connectivity and the services. The SD-WAN architecture leverages SDN principles to securely build interconnections between users and the applications hosted in the clouds or in remote branches, by leveraging any combination of transport services With this paper we shed some light on the SD-WAN scenario and describe an open-source implementation which can be taken as reference. We call this architecture EveryWAn.It has been designed with SDN and NFV principles in mind, and leverages Cloud best practices to deliver to the WAN customers and the MSP the same benefits and the agility of the Cloud service providers. Moreover, we strongly believe in the openness of the SDN/NFV paradigms which can ease the development of new services and can foster the innovation in the SD-WAN deployments.

Advancement in network attacks requires strong and growing security mechanisms. Internet of Things (IoT) is the evolving technology connected billion of devices right now and it builds on a set of network devices therefore it is under serious threat concern. Identifying attacks is crucial and critical task. The authors propose a hybrid DL driven approach to detect the attacks, one is Cuda Deep Neural Network Long Short-Term Memory (CuDNNLSTM) and another is Long Short-Term Memory (LSTM) on kitsune dataset. There is alarming situation for protection of all the smart systems in terms of security. In this paper we implemented LSTM and cuDNN LSTM networks to identify attack. Results show that our technique cuDNNLSTM outperforms in comparison of deep learning technique LSTMs that shows 99.79% accuracy on 6GB dataset approx. (2S0lac) records.

The process of network management has always been complicated and challenging in traditional networks. Network operators in traditional networks have to cope with unavoidable constraints of low level vendor specific configurations to implement network policies on different networking devices from multiple vendors. Despite many previous proposals to make networks easier to manage, there were still several complicated and scalability issues remained unresolved particularly in scenarios where multivendor networking devices are deployed over large networks. This rigid behavior of vendor specific underlying infrastructure devices configuration and maintenance results in very few possibilities for innovation, enhancement, and improvement since the networking devices have generally been closed and proprietary. This lack of coherence in different vendor specific networking infrastructure devices was acting as a point of main hindrance in making the network management process a simple and easy to operate for network operators. The future avionics communications network being heterogeneous wireless communications network as presented in Future Communications Infrastructure (FCI) document also foresees similar network management issues.The paradigm of Software Defined Networking (SDN) proposes an effective way of tackling the issues in network management by separating the control and management plane from the data plane. The core idea of SDN is to keep networking devices i.e. switches and routers in the forwarding or data plane, responsible for simply forwarding data packets. A logically centralized software program i.e. SDN controller will be responsible of all the intelligent work of control plane operations. It also allows the network to be more flexible and programable. Using this paradigm, the SDN introduces new routes of innovations and opportunities for network management and configuration methods. In this paper an SDN based network management architecture is presented for future avionics communication network based on FCI. This paper also presents a comparison of network management process in traditional and SDN based architecture with the underlying configuration and management protocols i.e. SNMP, OF-Config, NetConf, RestConf and Yang model. The issues in the state-of-the-art network management such as configurations and scalability issues are highlighted with alternative solutions in SDN based architecture. The SDN based network management functions are applied to future avionics communications network architecture. Some example scenarios have also been demonstrated for network management functions such as configuration/reconfiguration of infrastructure layers devices using SDN controller with a global view of network.

In recent years, Internet Service Providers (ISPs) are expected to enable various practical services. To meet the requirements of services, the infrastructure of networks has become more and more complex. In telecom networks, the complex infrastructure implies that it would be difficult to analyze the root causes and to locate the faults. In the telecom companies, network maintenance staffs need to spend a lot of time to trace the root cause and solve the network problems. An intelligent fault location approach allows ISPs to be cost-effective, and can assist humans in decision-making and increase automation. To automatically locate the faults, we apply both the Ant Colony Optimization (ACO) algorithm and fuzzy logic methods, and the main contributions of this paper are threefold: (1) we apply the pheromones of the ACO algorithm to quantify the risks that network devices might fail; (2) based on the risks, we leverage fuzzy logic, including the fuzzy relation matrix and the max-min composition method, to infer the fault location; (3) for improving autonomous network, we implemented and evaluated the proposed intelligent fault location approach using the real data in telecom networks.

In the course of network operations, telecommunications carriers must have accurate topology information of the network related to the failure to identify quickly causes of service failures and determine their impacts. However, telecommunications carrier networks are divided into multiple layers according to their roles, and each layer has a different management system, making it difficult to detect the topology information between different layers. Therefore, there is a need for a technology that can assure accurate topology information of the multiple layers network. We propose a new topology discovery method based on the consistency of the traffic of mutually connected interfaces. We verify the effectiveness of the proposed method using traffic data from network equipment in a commercial network and show that the proposed method is capable of detecting topologies with high accuracy.

Over the years, the need for communication networks capable of providing an ever-increasing set of services has grown. In order to satisfy user requirements and provide guarantees of reliability of the network itself, efficient techniques are required for analysis, evaluation and design. For this reason, the need arises to have models able to represent the peculiar characteristics of network traffic and to produce reliable predictions of its behavior in an adequate period of time. Therefore, network traffic prediction plays an important role by supporting many practical applications, ranging from network planning and provisioning to security. Several works so far have focused on building app-specific models. However, this choice produces multiple models that need to be properly managed and deployed across network devices. Therefore, in this paper, we explore different training strategies to reduce the number of models, adopting the Markov Chains to model mobile video apps traffic at packet-level. We discuss and experimentally evaluate the prediction effectiveness of the proposed approaches by comparing the performance of app models with models trained on a specific category of video apps and a model trained on the mix of all video traffic.

Traffic measurement provides fundamental statistics for network management functions. To implement the measurement modules on the data plane for real-time query response, modern sketches are designed to work with limited on-die memory allocation from network processors and collect traffic statistics in epochs of a preset length. To handle real-time queries at arbitrary times over traffic in a preceding period ${T}$ (called ${T}$ -queries), the prior art sets the epoch length to ${T \over n}$ and keeps the measurement results in a window of $n - 1$ past epochs to support approximate ${T}$ -queries. Such an approach however drastically increases the memory cost or decreases the accuracy in the query results if the memory allocation is fixed. In this paper, motivated by the concept of offloading in today's edge-cloud computing, we propose a collaborative edge-center traffic measurement model, where the traffic measurement modules at all network devices form the edge, which offloads the traffic measurement results to a measurement center possibly hosted in a datacenter. The center synthesizes the measurements from the past epochs and sends the aggregate results back to the measurement modules to support T-queries. We conduct experiments using real traffic traces to evaluate the performance of the proposed edge-center measurement model. The experimental results demonstrate that the proposed designs significantly outperform the prior art.

MPI provides nonblocking point-to-point and one-sided communication models to help applications achieve communication and computation overlap. These models provide the opportunity for MPI to offload data transfer to low level network hardware while the user process is computing. In practice, however, MPI implementations have to often handle complex data transfer in software due to limited capability of network hardware. Therefore, additional asynchronous progress is necessary to ensure prompt progress of these software-handled communication. Traditional mechanisms either spawn an additional background thread on each MPI process or launch a fixed number of helper processes on each node. Both mechanisms may degrade performance in user computation due to statically occupied CPU resources. The user has to fine-tune the progress resource deployment to gain overall performance. For complex multiphase applications, unfortunately, severe performance degradation may occur due to dynamically changing communication characteristics and thus changed progress requirement. This paper proposes a novel Dynamic Asynchronous Progress Stealing model, called Daps, to completely address the asynchronous progress complication. Daps is implemented inside the MPI runtime. It dynamically leverages idle MPI processes to steal communication progress tasks from other busy computing processes located on the same node. The basic concept of Daps is straightforward; however, various implementation challenges have to be resolved due to the unique requirements of interprocess data and code sharing. We present our design that ensures high performance while maintaining strict program correctness. We compare Daps with state-of-the-art asynchronous progress approaches by utilizing both microbenchmarks and HPC proxy applications.

With computers' growth, network-based technology, including advanced communication features, Internet of Things (IoT), automation, and upcoming fifth generation (5G) mobile technology, network security has become challenging to secure applications, systems, and networks. Rapid increase of network devices has created many new attacks and therefore presented significant difficulties for network security to identify threats correctly. Intrusion detection systems (IDSs) guarantee the network's confidentiality, integrity, and availability by monitoring network traffic and blocking any potential intrusions. Despite significant research efforts, IDS still confronts many difficulties in increasing detection efficiency and decreasing false alarm rates. Intrusion detection systems are using machine learning and deep learning-based IDS to identify intrusions throughout the network as quickly as possible. This paper identifies the idea of IDS and the following details the taxonomy developed based on the prominent Machine Learning (ML) and Deep Learning (DL) methods used in NIDS system design. An in-depth analysis of NIDS-based papers is discussed to outline the benefits and weaknesses of the various options. New technology, including ML and DL, and current advances in these NIDS technologies are described with the methodology, assessment metrics, and dataset selections. Through highlighting the existing research difficulties with the longterm scope of the NIDS study to improve machine learning and deep learning-based NIDS. Many novel techniques are using to deal with Intrusion detection systems. However, most are not quick enough to adapt to cyber security defense systems' dynamic and complex nature as the threats surface is growing exponentially with different devices' interfaces. This paper proposes a review of various Intrusion detection system (IDS) capabilities and assets using deep learning techniques. It also suggests a novel idea to automatically adapt the network intrusion detection of the cyber defense architecture to automatically reduce the false alarm rate and optimize the time for detection processes.

Anonymous communication technology has been proposed to conceal the identity and communication relationship of both parties in communication, mitigating the threats of communication surveillance. However, the traditional anonymous communication scheme is designed on the traditional network architecture, network devices have limited control over the network, which leads to the inefficiency of anonymous communication. Software Defined Networks (SDN) is a novel network architecture that manages network through controller. It has the characteristics of high efficiency and flexibility. However, in recent years, researches about anonymous communication of SDN exist many challenges, such as limitation of scenarios and lack of anonymity. To address these challenges, this paper, inspired by pseudonym changing, proposes a pseudonym-based anonymous routing mechanism under multi-controller SDN architecture, in which pseudonym-changing is used for hiding the identity of the communicating parties. Besides, to avoid routing error caused by address conflicts, an effective hash checking method is proposed to avoid anonymous address conflicts. Based on that, we also present an anonymity enhanced scheme that employs phantom routing to hide the sender in the routing path and a multicast mechanism to prevent traffic analysis attacks. Anonymity analysis and experiment show that this scheme can provide strong anonymity protection for distributed SDN without much time cost, and has good practicability.

Internet of Things (IoT) technologies and the deficiency of Internet Protocol (IP) addresses due to the increasing number of internet devices have brought the use of Internet Protocol Version 6 (IPv6) with a larger addressing structure. Spectrum scarcity and inefficient spectrum using, as well as lack of address, is an important problem in the consumption of resources on the network. Cognitive Radio Networks (CRN) technology has been introduced in order to prevent these problems and to use the existing spectrum band more efficiently. With CRN, it is intended to be used by unlicensed users when there is no communication in the spectrum bands which are assigned to licensed users. Routing is vital to the communication of network devices. RPL algorithm is a routing protocol used in IoT networks. In this study, a CR-enabled routing function will be defined as an Objective Function (OF) on the RPL algorithm used for IoT devices. In the current IoT networks, devices communicate on a single frequency and do not perform the frequency switching function. The proposed routing objective function chooses the routing path, considering the switching cost. The proposed frequency switching aware RPL algorithm will be compared with the RPL (Pure RPL) in terms of performance metrics such as energy consumption and energy efficiency.

Remote production is an emerging concept for outside broadcasting (OB) enabled using Internet Protocol (IP)-based production systems. Because multi-channel uncompressed video signals are transmitted to the broadcasting station without editing, expensive OB vans and editing crews are not required to be dispatched to the event venue. Therefore, the cost for OB should be substantially reduced. Although long-distance transmissions of uncompressed video and time synchronization of distributed IP-video transceivers are challenging, the application of optical networks is promising. The network equipment needs to be configured accordingly to utilize optical networks; however, production crews are not familiar with the network configuration. In this paper, we propose a remote production system that configures the network equipment as well as the IP-video transceivers in accordance with the requirements of video transmissions. We also report a proof-of-concept implementation for 8K production. The optical transponders as well as the IP-video transceivers were configured by selecting a sender and a receiver in the graphical user interface, and uncompressed 8K video was transmitted over the dynamically created optical path. In addition, another optical path could be created for seamless protection. The results of this study demonstrate that the system enables users to utilize optical networks without being aware of the network configurations.

Network Softwarization, the process by which network equipment's are being replaced by software running in a cloud environment, is playing an important role in the transformation of next-generation networks starting with 5G. In this environment, the use of AI/ML aided network automation to perform management tasks is vital to provide a more reliable and cost-effective network. An aspect in which AI/ML can play an important role is on the quick diagnose and track of root causes of anomalies. In this paper, we propose a system capable of automating root cause analysis in a cellular network scenario. By collecting log files from negative-impacting events occurring throughout the whole network levels, we are able to find the correlation between them according to a series of defined rules and track down the root cause using a graph-based approach to dependencies

L2VPN AToM (Any Transport over MPLS) is an ethernet-based private communication service that can connect networks in different geographical locations but seems to be on the same network logically through MPLS networks on the same bridge domain. L2VPN AToM technology is a consideration in enterprise networks to manage the availability of data sources centrally, safely, and quickly with other branch offices. L2VPN AToM becomes inefficient and inflexible in managing large networks formed between the head office and branch offices which must be configured manually one by one as many as the number of branch offices to be connected. In managing the L2VPN AToM network configuration, it can be done centrally to improve network efficiency by using the SDN architecture. However, this architecture requires a long time in the transition process and considering the costs incurred to replace conventional network devices that are already operating. For the solution, Hybrid SDN (Software Defined Network) network technology is needed as a solution to centrally manage conventional networks. Hybrid SDN Network is a technology that separates the control plane and the data plane by utilizing conventional network devices to be applied to the SDN architecture. This research used ansible as a controller that will distribute conventional network configuration centrally and an ONOS controller as a traffic management service for L2VPN AToM traffic. The research result shows that Hybrid SDN networks are better than conventional networks with different average values of throughput in 3.12%, 2.12% of delay, and 0.3% packet loss.

Counselors are guides and intimate friends for the healthy growth of college students. Counselors' work efficiency has a direct impact on the overall efficiency of school student management. Due to many factors, such as the arrangement of college counselors, the working mechanism of students, the number of students and the proportion of college counselors, the efficiency of student management in many colleges and universities is low. At the same time, the number of counselors can not meet the actual needs of the complex student management. Data center can be understood as data centralized centralized processing center. It usually consists of one or more computer clusters and supporting network equipment, storage equipment, security equipment, power system, management and software, etc. This paper studies the information system of counselor's work management based on database and data center.

Inter-core crosstalk due to the presence of multiple cores is one of the major issues to be taken care of in space division multiplexing based elastic optical networks (SDM-EONs). Again due to the random occurrence of spectral fragmentations in online SDM-EON, many high-priority connections get blocked. The underlying SDM-EON also suffers from ample data loss even if a single link in the network fails. Survivability is ensured in this paper by using multipath based approach. Again, survivability issue deserves enough redundancy in the network devices which again increases energy consumption in the network. Multipath based survivability is used in this paper. To address the aforementioned issues simultaneously, this paper proposes a novel energy-efficient and crosstalk-aware multipath based survivable routing, spectrum and core allocation scheme ECM-P-RSCA, for prioritized traffic in online SDM-EONs. Extensive simulation results prove the efficacy of ECM-P-RSCA over a non-prioritized similar scheme in terms of various network parameters such as bandwidth blocking, energy consumption, spectral occupation rate, crosstalk generated per slot ratio etc. It is also observed that with increase in number of cores in SDM-EON, crosstalk per slot ratio increases.

Configuring network devices is a main task of network operators. However, understanding and consistently updating network configuration files (config) is not an easy task especially in a large-scale and complicated networks. In this paper, we propose a semantic approach to provide better understanding of such config files, different from syntax based approaches. The key idea of the work is to extract semantics of blocks of the config files by document embedding techniques in NLP. This extraction enables us to understand context of config blocks with semantic similarity metrics instead of syntax similarity ones. Furthermore, this approach can be naturally extended to additional technical documents such as vendor’s manual documents to add more specific information on the semantics of configs. We first discuss the quality of the obtained semantics for several embedding techniques, by using clustering evaluations. We next demonstrate the effectiveness of our approach with two case studies with real network configs: (1) similar config block detection and (2) automatic labeling of config block with vendor’s documents.

Modern programmable network hardware enables in-network computing-pushing increasingly-complex logic into the network to improve the performance, flexibility and reliability of network services. But the current network programming paradigm is constrained to programming a single network device at a time. The lack of support for in-network programs that use several and heterogeneous network hardware simultaneously constrains the scale and behaviour of in-network programs. Dataplane Disaggregation is a new paradigm that addresses this problem. It distributes computations across programmable network hardware including switches and smart NICs. This paradigm transforms a monolithic in-network program into a distributed system executing on possibly heterogeneous resources. The goal of this demo is to make an accessible presentation of Dataplane Disaggregation to the wider distributed systems community. This is intended to stimulate discussion on effective ways to program distributed and heterogeneous systems. Our demo is based on the Flightplan system prototype. Flightplan is open-source and comes with detailed documentation and support scripts, yet it requires some effort to set up and run. This impedes its study by others. Our demo runs completely in the browser and does not burden viewers with any installation effort at all. The technical contribution of this demo consists of a customised visualisation of Flightplan experiments. Moreover, the demo is well-suited to virtual events—as is being planned for ICDCS'21—since it can be run independently and asynchronously by viewers of the demo. This is especially helpful for viewers with slow or intermittent Internet connections. We make the demo's source code freely available online for use by others, including researchers who want to build similar demos.

Data logs from network devices are primary data to understand the current status of operational networks. However, since many and heterogeneous devices generate network logs, extracting information on the network status from such logs is not an easy task in network operation, e.g., root cause analysis of network events. Though multi-variate time-series based log analyses extract correlation structure of the logs, identifying causality of the network logs is still a complex and challenging problem. The state of the art algorithm called the PC algorithm had been applied to network log analysis, but it has two fundamental limitations; (1) Generated graphs still have many undirected edges, and (2) Edges have no weight (whether plausible causality or not). To overcome these two limitations, in this paper, we rely on MixedLiNGAM to network log analysis; This algorithm produces weighted DAGs from a set of multivariate log time series. In order to show the effectiveness of the proposed method, we apply MixedLiNGAM to a set of syslog data collected at a research and education network in Japan, and then compare output causal graphs generated by MixedLiNGAM and the PC algorithm. Our result demonstrates that obtained weighted directional edges help better understand the root cause of the network events.

Edge computing is an attractive architecture to efficiently provide compute resources to many applications that demand specific QoS requirements. The edge compute resources are in close geographical proximity to where the applications’ data originate from and/or are being supplied to, thus avoiding unnecessary back and forth data transmission with a data center far away. This paper describes a federated edge computing system in which compute resources at multiple edge sites are dynamically aggregated together to form distributed super-cloudlets and best respond to varying application-driven loads. In its simplest form a super-cloudlet consists of compute resources available at two edge computing sites or cloudlets that are (temporarily) interconnected by dedicated optical circuits deployed to enable low-latency and high-rate data exchanges. A super-cloudlet architecture is experimentally demonstrated over the largest public OpenROADM optical network testbed up to date consisting of commercial equipment from six suppliers. The software defined networking (SDN) PROnet Orchestrator is upgraded to both concurrently manage the resources offered by the optical network equipment, compute nodes, and associated Ethernet switches and achieve three key functionalities of the proposed super-cloudlet architecture, i.e., service placement, auto-scaling, and offloading.

Advances in persistent memory and networking hardware are changing the architecture of storage systems and data management services in datacenters. Distributed, one-sided RDMA access to memory-resident data shows tremendous improvements in throughput, latency and server CPU utilization of storage servers. However, the silent nature of one-sided I/O simultaneously creates new challenging problems for providing QoS in such systems. In this paper, we propose Haechi, a work-conserving, token-based QoS mechanism to guarantee reservations and limits in storage systems that provide one-sided I/O services. Haechi decouples QoS enforcement into a QoS engine at the client and a QoS monitor at the data node. It leverages adaptive token dispatch, token conversion, and silent I/O reporting to guarantee the reservations of distributed clients while maintaining high server utilization. Empirical evaluations on the Chameleon cluster, with different reservation distributions and I/O access patterns, show that Haechi is successful in providing differentiated QoS with negligible overhead for token management.

The advantages of online learning are very significant. With the popularization of network technology and the development of network hardware equipment and mobile terminals, the development of technology provides a foundation for the rapid development of online learning. Due to the outbreak of the COVID-19 epidemic in 2020, classroom teaching cannot be carried out. Therefore, many schools use online platforms to implement online teaching. From the traditional face-to-face teaching as the main body, online teaching supplements, to a single online teaching form. At present, online teaching mainly includes three forms: live broadcast, recorded broadcast and online self-directed learning. At the same time, a large amount of student activity data is generated on the teaching platform. Take the online teaching data of colleges and universities in the first half of 2020 as an example, with the help of the mining tool RapidMiner to mine and analyze teaching data, student click-through rates and student performance data. Deeply analyze the implementation of online teaching and the mechanism of various influencing factors, and use logistic regression algorithms to predict whether students will pass the exam. Through student learning: On the online learning platform, students' learning content is the same, but the difference is their learning behavior on the platform. The click-through rate reflects the learning behavior of students in the data, and the level of performance is closely related to the degree of active learning of students.

An experimental network environment plays an important role to examine new systems and protocols. We have developed an experimental network construction tool called LiONv1 (Lightweight On-Demand Networking, ver.1). LiONv1 satisfies the following four requirements: programmer-friendly configuration file based on Infrastructure as Code, multiple virtualization technologies for virtual nodes, physical topology conscious virtual node placement, and L3 protocol agnostic virtual networks. None of existing experimental network environments satisfy all the four requirements. In this paper, we develop LiONv2 which satisfies three more requirements: diversity of available network devices, Internet-scale deployment, and disaggregation of network configuration and device configuration. LiONv2 employs NETCONF and YANG to achieve diversity of available network devices and Internet-scale deployment. LiONv2 also defines two YANG models which disaggregate network configuration and device configuration. LiONv2 is implemented in Go and C languages with public libraries for Go. Measurement results show that construction time of a virtual network is irrelevant to the number of virtual nodes if a single virtual node is created per physical node.

With the emergence of programmable network devices that match the performance of fixed function devices, several recent projects have explored in-network computing, where the processing that is traditionally done outside the network is offloaded to the network devices. In-network computing has typically been applied to network functions (e.g., load balancing, NAT, and DNS), caching, data reduction/aggregation, and coordination/consensus functions. In some cases it has been used to accelerate stream-processing tasks that involve small payloads and simple operations. In this work we focus on leveraging in-network computing for stream processing of scientific datasets with large payloads that require complex operations such as floating-point computations and logarithmic functions. We demonstrate in-network computing for a real-world scientific application performing streaming normalization of a 2-D image from a light source experiment. We discuss the challenges we encountered and potential approaches to address them.

Network Policy management is a tedious and laborious task because of scale and dynamic changes in the network. The advent of Softwarized Networks has led to a renewed interest in intent-based network policy management. Intent-based Networking provides a structured way of specifying the intent of policies which are automatically translated and compiled into network device configuration. While this top-down approach of policy intent to policy configuration has worked well for cloud-native infrastructures such as data centers, it has not seen much adoption in legacy networks. We believe one of the primary reasons for this is the semantic gap between policy intents and policy configurations. The problem is further exacerbated by the heterogeneity, scale-on-the-fly, fragmentation, and lack of structure in non-intent native networks. We introduce Policy Intent Inference (PII) System to bridge the semantic gap with its advanced inference layer that extracts the policy intents from policy configurations fragmented over disparate network devices. We adopt a bottom-up approach to extract all policies within network devices, abstract them into a structured data model, and with the use of clustering and information retrieval techniques, build an optimal solution to extract network-wide policy intents from the underlying network that eases policy management especially policy troubleshooting, reducing the configuration clutter and reducing the time taken to compile and resolve conflicts in policies.

To provide the predictability required by emerging applications, operators typically rely on policing and/or shaping at the edge to ensure that tenants do not use excess bandwidth that was not accounted for. One of the promises of 6G is to deploy applications with strict predictability requirements across subnets and even over the Internet, where policing cannot be implemented in the end hosts. This paper presents an empirical study of the ability of modern programmable network devices to implement predictable traffic policing in the network. We find out that none of the five investigated hardware switches can provide accurate traffic policing, a key requirement for providing predictable service to applications. We observe that the switches let applications send more than what they should be allowed to, reaching up to 60% and 100% relative error for the rate and burst parameters. We further uncover the fact that switches cannot police arbitrarily low bursts, e.g., not less than 13 kilobit for one of our switches. We investigate how such limitations impact the performance of state-of-the-art solutions for predictable latency such as Chameleon. We observe that, for ensuring its predictable guarantees, Chameleon rejects around 50% of the tenants it could accommodate if switches were perfect, hence decreasing by the same ratio the revenue for the operator. Based on these observations, we discuss solutions toward more accurate and predictable policing in wide-area networks.

In the power distribution Internet of Things environment, the execution efficiency of user tasks is low when smart node resources are limited. In order to solve this problem, this paper designs an edge computing network architecture under the power distribution Internet of Things environment. The architecture includes three types of devices: smart nodes, network devices, and edge computing nodes. The execution mode of the computing task of the smart node is modeled, the local computing model and the remote computing model are designed, and the task execution time model and energy consumption model are established respectively, as well as the objective function of the edge node resource allocation problem. The four key elements of state space, action set, reward function and search mechanism for solving the optimal resource allocation problem under Q- Learning theory are designed. A Q-Learning-based edge node resource allocation algorithm is proposed, and it is verified that the algorithm in this paper can improve the execution efficiency of user tasks.

Packet processing tasks in network functions issue memory requests to understand the packet information, update the packet content, and search the databases, which requires high-performance memory systems. While network functions virtualization (NFV) is expected to reduce the cost of network infrastructure by replacing dedicated network equipment with commercial off-the-shelf (COTS) hardware and virtual network functions (VNFs), VNF performance suffers from the poor memory systems that lack function-dedicated memories and memory parallelism in COTS servers. While several works presented parallel memories for packet processing based on 3 dimensional (3D)-stacked dynamic random access memories (DRAMs), data transfer latency between the processors and memories are not considered. Although there are processing-in-memory (PIM) architectures that offload a part of processing in memories to reduce data transfers, the majority of processing is still in the processors, which requires data transfers for multiple packet processing tasks. This paper proposes a memory network architecture using 3D-stacked DRAMs to increase throughput and reduce accumulated latency when there are multiple packet processing tasks. Packets that enter the memory network receive packet processing at each 3D-stacked DRAM without data transfers between the processors and memories. The evaluation results show that the proposed architecture increases throughput and reduces accumulated latency for memory accesses and data transfers when there are multiple packet processing tasks, compared to the conventional architecture with 3D-stacked DRAM-based parallel memory, where every memory access requires data transfers.

Current bandwidth demands are encouraging the exploration of optical frequency comb generators and flexible modulation formats to enable very high-capacity transmission beyond the C-band, which can be augmented with existing real-time digital electronic signal processing for pre-emphasis and post-impairment compensation at very high clock speeds. But for exploitation and deployment in commercial networks these devices will require support for remote management embedded with service providers’ operation and business-support systems. However, installed network management systems must deal with a range of dissimilar network devices. This diversity spans across electronic packet switches, optical circuit switches, and monitoring instrumentation for telemetry, ranging from legacy to state-of-the-art models. Software defined networking (SDN) flexible management approach unlocks exciting possibilities to jointly exploit the full capabilities of digital electronic packet switching and the many degrees of freedom presented by analogue optical EM carriers. In this paper, we will expose some of these possibilities, where these technologies can, through SDN, be reimagined to enable flexible high-capacity systems. We will be revisiting the potential for multi-carrier transmitters, and utilising analogue methods to monitor transmitter performance. We will also show how existing protocols can be used to support both legacy and state-of-the-art SDN-enabled devices, incorporating to management operating systems such as ONOS, showing that a smooth transition to fully automated networks with closed-loop control is now a real prospect.

Nowadays, Health is the most crucial part of one’s life, Health care is one of the prominent sectors which play a vital role in the day-to-day life. This work discusses the automation of the health care sector using noteworthy technologies like Wireless Sensor Networking (WSN), Intranet topologies and Web development. Apart from innovation and automation, In the health care sector, this work shows a unique approach with the help of RSSI, Dual-band frequencies and adaptive n triangle algorithm which are an integral part of WSN. This work is a thoughtful combination of WSN, intranet & web development which ensures a typical Security that protects from intruders. This work proposes both hardware and software-based approach, where the hardware part consists of Single Board Computers and networking devices. In the software part, there are a heap of languages and tools used likewise HTML, CSS, PHP, SaaS, JavaScript and for database management MySQL is used. This is a structural work that creates a webserver using the intranet topologies where a dynamic website is hosted over the SBC. This website consists of appointment booking, doctors scheduling, medical screening, internal navigation in the hospital with the WSN, RSSI and dual-band technologies, medical facilities and many more. Finally, this work shows an adaptive & innovative solution that can amplify the efficiency of the health sector.

Cloud computing offers plenty of services having benefits of cost cutting, flexibility, availability, elasticity and pay per use for cloud users and centralized control, safety and management for Cloud Service Providers (CSP). Out of several service models, Infrastructure-as-a-Service (IaaS) preludes by offering access to computing resources like CPUs, servers, network devices through software like APIs, UIs and GUIs over the internet. Along with numerous merits of IaaS, there exist several security and privacy issues and threats to Confidentiality, Integrity and Authentication (CIA) triad. In this paper, we explore security and privacy issues related to IaaS components through rigorous study and determine counter measures for the same. Furthermore, with the help of MITRE ATT&CK knowledge base, a Model for IaaS Security and Privacy: MISP framework is proposed. The framework is exhibited as a multidimensional structure, each dimension having different parameters. This leads to addition of important features currently missing in the existing models. The proposed framework enhances security and privacy in IaaS model and guides for safer adoption of the delivery model by organizations and enterprises.

With current Traditional / Legacy networks, the reliance on manual intervention to solve a variety of issues be it primary operational functionalities like addressing Link-failure or other consequent complexities arising out of existing solutions for challenges like Link-flapping or facing attacks like DDoS attacks is substantial. This physical and manual approach towards network configurations to make significant changes result in very slow updates and increased probability of errors and are not sufficient to address and support the rapidly shifting workload of the networks due to the fact that networking decisions are left to the hands of physical networking devices. With the advent of Software Defined Networking (SDN) which abstracts the network functionality planes, separating it from physical hardware – and decoupling the data plane from the control plane, it is able to provide a degree of automation for the network resources and management of the services provided by the network. This paper explores some of the aspects of automation provided by SDN capabilities in a Mesh Network (provides Network Security with redundancy of communication links) which contribute towards making the network inherently intelligent and take decisions without manual intervention and thus take a step towards Intelligent Automated Networks.

Railway networking systems are critical infrastructures that must support fast, reliable and low delay communications. Technologies still used in those infrastructures---such as GSM-R, evolving into LTE-R are becoming more complex, yet more flexible, and evolving to "software defined" architectures. The technologies presented and explored in this work are expected to change the future of these types of critical systems. The main goal of this work is to study the key benefits of using the SDN model to control the next generation railways networking infrastructures. The safety, security and correctness properties of SDN controllers in high availability railway networks will be analyzed, for compliance with the European Rail Traffic Management System (ERTMS)/European Train Control System (ETCS) specifications, and in the context of a real project being deployed in a Portuguese Railway by Thales Portugal. From the analysis of the project requirements and the selected network equipment, it was possible to evaluate and propose adequate methods to automatically derive network re-configuration strategies, namely in case of failure events---e.g., preventing packet loss affecting vital railway traffic signaling procedures---in order to reduce field intervention and complexity in those infrastructures.

Recently, RF fingerprinting has become an arousing and emerging technology in identifying multiple wireless devices. The method is also believed to have a strong impact on its applications in the wireless security system. Security has always been a critical issue for wireless devices including in the application of Wireless Local Area Network (WLAN). For instance, Media Access Control (MAC) spoofing which is a malicious technique of changing a factory-assigned MAC address of a Network Interface Card (NIC) installed in a device. Due to this issue, this study suggests on making use of a network device’s unique RF fingerprint obtained from its raw baseband IQ samples to identify the transmitting radio. For WLAN, as RF fingerprinting is a physical layer security implementation, WLAN physical layer protocol data unit (PPDU) which contains L-LTF in preamble is extracted. Particularly, the RF fingerprinting process includes deep learning of convolutional neural network (CNN) as a classifier. The neural network is used to train a model by tuning and test-validation test before finalizing it as a final model for classification method for a security system.

Distributed Denial of Service (DDoS) attacks became a true threat to network infrastructure. DDoS attacks are capable of inflicting major disruption to the information communication technology infrastructure. DDoS attacks aim to paralyze networks by overloading servers, network links, and network devices with illegitimate traffic. Therefore, it is important to detect and mitigate DDoS attacks to reduce the impact of DDoS attacks. In traditional networks, the hardware and software to detect and mitigate DDoS attacks are expensive and difficult to deploy. Software-Defined Network (SDN) is a new paradigm in network architecture by separating the control plane and data plane, thereby increasing scalability, flexibility, control, and network management. Therefore, SDN can dynamically change DDoS traffic forwarding rules and improve network security. In this study, a DDoS attack detection and mitigation system was built on the SDN architecture using the random forest machine-learning algorithm. The random forest algorithm will classify normal and attack packets based on flow entries. If packets are classified as a DDoS attack, it will be mitigated by adding flow rules to the switch. Based on tests that have been done, the detection system can detect DDoS attacks with an average accuracy of 98.38% and an average detection time of 36 ms. Then the mitigation system can mitigate DDoS attacks with an average mitigation time of 1179 ms and can reduce the average number of attack packets that enter the victim host by 15672 packets and can reduce the average number of CPU usage on the controller by 44,9%.

Networking devices with programmable data planes, such as P4 programmable devices, are gaining more popularity because of the flexibility they provide in describing the packet processing behavior. Despite this attained flexibility, the performance of these devices can be the Achilles' heel in case the desired performance level is not met. To this end, we evaluate the performance of three state-of-the-art P4 devices focusing on the following properties: (i) the device's processing latency as a function of a scaled number of flows; (ii) the device's response time in reaction to control plane commands. The scalability analysis shows that different devices have different limits on the maximum number of flows they can support. On the other hand, the device's response time to control plane commands is found to be in milliseconds, which is three orders of magnitude larger when compared to the measured data plane's packet processing latency.

In this paper we study anomaly detection methods for home IoT devices. Specifically, we address unsupervised one-class learning methods due to their ability to learn deviations from a single normal class. In a home IoT environment, this consideration is crucial as supervised methods would result in a burden on many non-technical consumers which could hinder their effectiveness. For our study, we develop a home IoT network monitoring tool, and we illustrate network attacks against a variety of typical home IoT devices. As a result, we propose measures that could aid home consumers in defending ever-increasing home IoT networks.

The technological advancement of the Internet of Things (IoT) devices in our world today has become beneficial to many users but has security issues that are left unattended. IoT devices have the ability to connect to other devices on the internet to transmit and share data from anywhere. Hence, the need to secure these devices as they improve the quality of life comfort. Research shows that about 70% of IoT devices are easy to hack. Therefore, an efficient mechanism is highly needed to safeguard these devices, especially in smart homes. This paper proposes a novel deep learning-based anomaly detection approach to predict cyberattacks on smart home IoT network devices and learn new outliers as they occur over time using IoT network intrusion datasets. The proposed model is based on long-term memory architecture, which achieves a significant accuracy improvement compared to the existing state-of-the-art anomaly detection models for IoT networks in smart homes.

Publisher Copyright: IEEE The fifth-generation (5G) cellular network is expected to provide sub-meter positioning accuracy without draining the battery of user equipment. As a solution, ultra-dense network (UDN) deployment and network-based positioning were proposed. However, the openness of UDN and the vulnerability of network devices (e.g., access nodes) make it easy for attackers to poison such a positioning system. However, no existing work explores how to overcome this issue. This paper concentrates on jamming and collusion attacks in the network based positioning system. Specifically, we design a novel scheme that contains three functional modules to erase the influence of these attacks. A truth discovery module applies a clustering-based method aiming to generate the most approximate position value and find out suspicious signals. Based on neural network models, we further develop an attack detection module and an attack tracing module to perceive attacked user equipment and locate malicious or attacked access nodes. Through simulation, we conduct extensive experiments to illustrate the effectiveness of our scheme. The result shows high detection and tracing accuracy with very simple neural network models, which also implies the potential of our proposed scheme in practical deployment.

3GPP Release 16 will freeze the 2.1GHz FDD NR enhanced 40M large bandwidth standard in July 2020. At present, a small number of terminals have experimental capability. In the 3.5GHz TDD NR network with 100M bandwidth, how to use 2.1GHz FDD NR has become a hot issue in the industry. This paper compares the coverage and capacity of 2.1GHz FDD NR and 3.5GHz TDD NR through link budget and theoretical calculation; compares the uplink and downlink coverage of the two systems through single station pull-out experiment; selects the existing network with 2.1GHz FDD NR and 3.5GHz TDD NR deployed at the same site as the experimental site, and analyzes the uplink and downlink networking capacity of the two systems through Driving Test (DT). Considering the influence of the number of transmitting antennas of existing terminals and the transmitting power of network equipment on the network planning, the network capacity of this experiment includes 2.1GHz 4T4R and 3.5G 64TR, the terminal capacity includes 2.1GHz 1T4R, 2.1GHz 2T4R and 3.5GHz 2T4R, and the power consumption of network equipment involves 2.1GHz: 4×40W and 4×60W; 3.5GHz: 160W and 200W. At present, there is no literature about the existing network experiment of multi-power consumption and multiterminal type, so this paper has important reference significance for operators to deploy 2.1GHz+3.5GHz network.

A vulnerability scanner is a computer program designed to assess computers, networks or applications for known weaknesses. It is a tool for reconnaissance and information gathering with an emphasis on simplicity. It will do everything from fetching DNS records, retrieving WHOIS information, obtaining TLS data, detecting WAF presence and up to threaded directory busting and subdomain enumeration. Every scan output to a corresponding file. At most of all vulnerability scanner scans are independent and do not rely on each other result it utilizes python's asyncio to run most scans asynchronously. Our tool supports Tor /proxy for anonymous routing. It uses default wordlists (for URL fuzzing and subdomain discovery) enumeration. This vulnerability scanner helps you scan your IP address ranges to discover open ports and other security vulnerabilities specific to network devices.

To guarantee data persistence, storage workloads (such as key-value stores and databases) typically use a synchronous protocol that places the network and server stack latency on the critical path of request processing. The use of the fast and byte-addressable persistent memory (PM) has helped mitigate the storage overhead of the server stack; yet, networking is still a dominant factor in the end-to-end latency of request processing. Emerging programmable network devices can reduce network latency by moving parts of the applications' compute into the network (e.g., caching results for read requests); however, for update requests, the client still has to stall on the server to commit the updates, persistently. In this work, we introduce in-network data persistence that extends the data-persistence domain from servers to the network, and present PMNet, a programmable data plane (e.g., switch or NIC) with PM for persisting data in the network. PMNet logs incoming update requests and acknowledges clients directly without having them wait on the server to commit the request. In case of a failure, the logged requests act as redo logs for the server to recover. We implement PMNet on an FPGA and evaluate its performance using common PM workloads, including key-value stores and PM-backed applications. Our evaluation shows that PMNet can improve the throughput of update requests by 4.31X on average, and the 99th-percentile tail latency by 3.23X.

Computing and networking equipment power most of the applications we use daily. Therefore, dependability of these systems is of utmost importance. The impact of the neutron induced soft errors on the AMD EPYC™ 7002 Series processor is examined in this paper. The architecture of the processor and fault/error handling mechanisms are briefly presented. The experimental setup, used at Los Alamos Neutron Science Center (LANSCE) for soft error characterization, is described and the test results are analyzed. Two workloads are employed in the accelerated measurements, the high performance Linpack (HPL) benchmark and the STREAM benchmark. The neutron impact is quantified by the mean-time to failure (MTTF). The AMD EPYC 7002 MTTF is also compared against the MTTF of the previous generation of processors, AMD EPYC™ 7001, and confidence intervals are derived. The OS error logs are collected throughout the experiment. The measurement results are discussed.