Search

Query rewriting is one of the most effective techniques for coping with poorly written queries before passing them down to the query optimizer. Manual rewriting is not scalable, as it is error-prone and requires deep expertise. Similarly, traditional query rewriting algorithms can only handle a small subset of queries: rule-based techniques do not generalize to new query patterns and synthesis-based techniques cannot handle complex queries. Fortunately, the rise of Large Language Models (LLMs), equipped with broad general knowledge and advanced reasoning capabilities, has created hopes for solving some of these previously open problems. In this paper, we present GenRewrite, the first holistic system that leverages LLMs for query rewriting. We introduce the notion of Natural Language Rewrite Rules (NLR2s), and use them as hints to the LLM but also a means for transferring knowledge from rewriting one query to another, and thus becoming smarter and more effective over time. We present a novel counterexample-guided technique that iteratively corrects the syntactic and semantic errors in the rewritten query, significantly reducing the LLM costs and the manual effort required for verification. GenRewrite speeds up 22 out of 99 TPC queries (the most complex public benchmark) by more than 2x, which is 2.5x--3.2x higher coverage than state-of-the-art traditional query rewriting and 2.1x higher than the out-of-the-box LLM baseline., Comment: 12 pages

Thalassemia is a heritable blood disorder which is the outcome of a genetic defect causing lack of production of hemoglobin polypeptide chains. However, there is less understanding of the precise frequency as well as sharing in these areas. Knowing about the frequency of thalassemia occurrence and dependable mutations is thus a significant step in preventing, controlling, and treatment planning. Here, Political Tangent Search Optimizer based Transfer Learning (PTSO_TL) is introduced for thalassemia detection. Initially, input data obtained from a particular dataset is normalized in the data normalization stage. Quantile normalization is utilized in the data normalization stage, and the data are then passed to the feature fusion phase, in which Weighted Euclidean Distance with Deep Maxout Network (DMN) is utilized. Thereafter, data augmentation is performed using the oversampling method to increase data dimensionality. Lastly, thalassemia detection is carried out by TL, wherein a convolutional neural network (CNN) is utilized with hyperparameters from a trained model such as Xception. TL is tuned by PTSO, and the training algorithm PTSO is presented by merging of Political Optimizer (PO) and Tangent Search Algorithm (TSA). Furthermore, PTSO_TL obtained maximal precision, recall, and f-measure values of about 94.3%, 96.1%, and 95.2%, respectively.

Recommendation system services have become crucial for users to access personalized goods or services as the global e-commerce market expands. They can increase business sales growth and lower the cost of user information exploration. Recent years have seen a signifi-cant increase in researchers actively using user reviews to solve standard recommender system research issues. Reviews may, however, contain information that does not help consumers de-cide what to buy, such as advertising or fictitious or fake reviews. Using such reviews to offer suggestion services may reduce the effectiveness of those recommendations. In this research, the recommendation in e-commerce is developed using passer learning optimization based on Bi-LSTM to solve that issue (PL optimized Bi-LSTM). Data is first obtained from the product recommendation dataset and pre-processed to remove any values that are missing or incon-sistent. Then, feature extraction is performed using TF-IDF features and features that support graph embedding. Before submitting numerous features with the same dimensions to the Bi-LSTM classifier for analysis, they are integrated using the feature concatenation approach. The Collaborative Bi-LSTM method employs these features to determine if the model is a recommended product. The PL optimization approach, which efficiently adjusts the classifier's parameters and produces an extract output that measures the f1-score, MSE, precision, and recall, is the basis of this research's contributions. As compared to earlier methods, the pro-posed PL-optimized Bi-LSTM achieved values of 88.58%, 1.24%, 92.69%, and 92.69% for dataset 1, 88.46%, 0.48%, 92.43%, and 93.47% for dataset 2, and 92.51%, 1.58%, 91.90%, and 90.76% for dataset 3.

Scheduling and Channel Access at the MAC layer of the IoT network plays a pivotal role in enhancing the performance of IoT networks. State-of-the-art Omni-directional antenna based application data transmission has relatively less achievable throughput in comparison with directional antenna based scheduling protocols. To enhance the performance of the IoT networks, this paper propose a distributed one-hop scheduling algorithm called Directional Scheduling protocol for constrained deterministic 6TiSCH-IoT network. With this, in-creased number of IoT nodes can have concurrent application data transmission with efficient spatial reuse. This in-turn results in higher number of cell allocation to the one-hop IoT nodes during data transmission. The proposed algorithm makes use of through directional transmissions avoids head of line blocking.

Visible light communication (VLC) is a promising solution to satisfy the extreme demands of emerging applications. VLC offers bandwidth that is orders of magnitude higher than what is offered by the radio spectrum, hence making best use of the resources is not a trivial matter. There is a growing interest to make next generation communication networks intelligent using AI based tools to automate the resource management and adapt to variations in the network automatically as opposed to conventional handcrafted schemes based on mathematical models assuming prior knowledge of the network. In this article, a reinforcement learning (RL) scheme is developed to intelligently allocate resources of an optical wireless communication (OWC) system in a HetNet environment. The main goal is to maximise the total reward of the system which is the sum rate of all users. The results of the RL scheme are compared with that of an optimization scheme that is based on Mixed Integer Linear Programming (MILP) model., Comment: 6 pages, 2 Figures, Conference

Programming languages are incredibly versatile, enabling developers to create applications and programs that suit their individual requirements. This article introduces a new language called Cesno, designed from the ground up to offer an advanced, user-friendly, and easy-to-use programming environment. Cesno's syntax is similar to other popular languages, making it simple to learn and work with. It incorporates features from other languages, such as syntactic sugar, a built-in library, support for functional programming, object-oriented program-ming, dynamic typing, a type system, and a variety of function parameters and restrictions. This article will explore the design of Cesno's grammar, provide a brief overview of how Cesno processes and compiles code, and provide exam-ples of what Cesno's code looks like and how it can aid in development., Comment: 20 pages, 1 tables

Economic Load Dispatch depicts a fundamental role in the operation of power systems, as it decreases the environmental load, minimizes the operating cost, and preserves energy resources. The optimal solution to Economic Load Dispatch problems and various constraints can be obtained by evolving several evolutionary and swarm-based algorithms. The major drawback to swarm-based algorithms is premature convergence towards an optimal solution. Fitness Dependent Optimizer is a novel optimization algorithm stimulated by the decision-making and reproductive process of bee swarming. Fitness Dependent Optimizer (FDO) examines the search spaces based on the searching approach of Particle Swarm Optimization. To calculate the pace, the fitness function is utilized to generate weights that direct the search agents in the phases of exploitation and exploration. In this research, the authors have carried out Fitness Dependent Optimizer to solve the Economic Load Dispatch problem by reducing fuel cost, emission allocation, and transmission loss. Moreover, the authors have enhanced a novel variant of Fitness Dependent Optimizer, which incorporates novel population initialization techniques and dynamically employed sine maps to select the weight factor for Fitness Dependent Optimizer. The enhanced population initialization approach incorporates a quasi-random Sabol sequence to generate the initial solution in the multi-dimensional search space. A standard 24-unit system is employed for experimental evaluation with different power demands. Empirical results obtained using the enhanced variant of the Fitness Dependent Optimizer demonstrate superior performance in terms of low transmission loss, low fuel cost, and low emission allocation compared to the conventional Fitness Dependent Optimizer. The experimental study obtained 7.94E-12., Comment: 42 pages

This paper provides a summary of available technologies required for implementing indoor laser-based wireless networks capable of achieving aggregate data-rates of terabits per second as widely accepted as a sixth generation (6G) key performance indicator. The main focus of this paper is on the technologies supporting the near infrared region of the optical spectrum. The main challenges in the design of the transmitter and receiver systems and communication/networking schemes are identified and new insights are provided. This paper also covers the previous and recent standards as well as industrial applications for optical wireless communications (OWC) and LiFi., Comment: 7 pages, 7 figures

Transformers achieve state-of-the-art performance for natural language processing tasks by pre-training on large-scale text corpora. They are extremely compute-intensive and have very high sample complexity. Memory replay is a mechanism that remembers and reuses past examples by saving to and replaying from a memory buffer. It has been successfully used in reinforcement learning and GANs due to better sample efficiency. In this paper, we propose \emph{Transformer with Memory Replay} (TMR), which integrates memory replay with transformer, making transformer more sample-efficient. Experiments on GLUE and SQuAD benchmark datasets show that Transformer with Memory Replay achieves at least $1\%$ point increase compared to the baseline transformer model when pretrained with the same number of examples. Further, by adopting a careful design that reduces the wall-clock time overhead of memory replay, we also empirically achieve a better runtime efficiency., Comment: Accepted to AAAI 2022

Unmanned Aerial Vehicles (UAVs) are poised to play a central role in revolutionizing future services offered by the envisioned smart cities, thanks to their agility, flexibility, and cost-efficiency. UAVs are being widely deployed in different verticals including surveillance, search and rescue missions, delivery of items, and as an infrastructure for aerial communications in future wireless networks. UAVs can be used to survey target locations, collect raw data from the ground (i.e., video streams), generate computing task(s) and offload it to the available servers for processing. In this work, we formulate a multi-objective optimization framework for both the network resource allocation and the UAV trajectory planning problem using Mixed Integer Linear Programming (MILP) optimization model. In consideration of the different stake holders that may exist in a Cloud-Fog environment, we minimize the sum of a weighted objective function, which allows network operators to tune the weights to emphasize/de-emphasize different cost functions such as the end-to-end network power consumption (EENPC), processing power consumption (PPC), UAVs total flight distance (UAVTFD), and UAVs total power consumption (UAVTPC). Our optimization models and results enable the optimum offloading decisions to be made under different constraints relating to EENPC, PPC, UAVTFD and UAVTPC which we explore in detail. For example, when the UAVs propulsion efficiency (UPE) is at its worst (10% considered), offloading via the macro base station is the best choice and a maximum power saving of 34% can be achieved. Extensive studies on the UAVs coverage path planning (CPP) and computation offloading have been conducted, but none has tackled the issue in a practical Cloud-Fog architecture in which access, metro and core layers are considered in the service offloading in a distributed architecture like the Cloud-Fog.

Recent years have witnessed a remarkable development in communication and computing systems, mainly driven by the increasing demands of data and processing intensive applications such as virtual reality, M2M, connected vehicles, IoT services, to name a few. Massive amounts of data will be collected by various mobile and fixed terminals that will need to be processed in order to extract knowledge from the data. Traditionally, a centralized approach is taken for processing the collected data using large data centers connected to a core network. However, due to the scale of the Internet-connected things, transporting raw data all the way to the core network is costly in terms of the power consumption, delay, and privacy. This has compelled researchers to propose different decentralized computing paradigms such as fog computing to process collected data at the network edge close to the terminals and users. In this paper, we study, in a Passive Optical Network (PON)-based collaborative-fog computing system, the impact of the heterogeneity of the fog units capacity and energy-efficiency on the overall energy-efficiency of the fog system. We optimized the virtual machine (VM) placement in this fog system with three fog cells and formulated the problem as a mixed integer linear programming (MILP) optimization model with the objective of minimizing the networking and processing power consumption of the fog system. The results indicate that in our proposed architecture, the processing power consumption is the crucial element to achieve energy efficient VMs placement.

The Internet of Things (IoT) is gaining momentum in its quest to bridge the gap between the physical and the digital world. The main goal of the IoT is the creation of smart environments and self-aware things that help to facilitate a variety of services such as smart transport, climate monitoring, e-health, etc. Huge volumes of data are expected to be collected by the connected sensors/things, which in traditional cases are processed centrally by large data centers in the core network that will inevitably lead to excessive transportation power consumption as well as added latency overheads. Instead, fog computing has been proposed by researchers from industry and academia to extend the capability of the cloud right to the point where the data is collected at the sensing layer. This way, primitive tasks that can be hosted in IoT sensors do not need to be sent all the way to the cloud for processing. In this paper we propose energy efficient embedding of machine learning (ML) models over a cloud-fog network using a Mixed Integer Linear Programming (MILP) optimization model. We exploit virtualization in our framework to provide service abstraction of Deep Neural Networks (DNN) layers that can be composed into a set of VMs interconnected by virtual links. We constrain the number of VMs that can be processed at the IoT layer and study the impact on the performance of the cloud fog approach.

Data centers based on Passive Optical Networks (PONs) can offer scalability, low cost and high energy-efficiency. Application in data centers can use Virtual Machines (VMs) to provide efficient utilization of the physical resources. This paper investigates the impact of VM placement on the energyefficiency in a PON-based data center architecture that utilizes cascaded Arrayed Waveguide Grating Routers (AWGRs). In this paper, we develop a Mixed Integer Linear Programming (MILP) optimization model to optimize the VM placement in the proposed PON-based data center architecture. This optimization aims to minimize the power consumption of the networking and computing by placing the VMs and their demands in the optimum number of resources (i.e., servers and networking devices) in the data center. We first minimize the processing power consumption only and then we minimize the processing and networking power consumption. The results show that a reduction in the networking power consumption by up to 75% is achieved when performing joint minimization of processing and networking power consumption compared to considering the minimization of the processing power consumption only.

The use of Passive Optical Networks (PONs) in modern and future data centers can provide energy efficiency, high capacity, low cost, scalability, and elasticity. This paper introduces a passive optical network design with 2-tier cascaded Arrayed Waveguide Grating Routers (AWGRs) to connect groups of racks (i.e. cells) within a data center. This design employs a Software-Defined Networking (SDN) controller to manage the routing and assignment of the networking resource while introducing multiple paths between any two cells to improve routing, load balancing and resilience. We provide benchmarking results for the power consumption to compare the energy efficiency of this design to state-of-the-art data centers. The results indicate that the cascaded AWGRs architecture can achieve up to 43% saving in the networking power consumption compared to Fat-Tree data center architecture.

There is a continuous growth in demand for time sensitive applications which has shifted the cloud paradigm from a centralized computing architecture towards distributed heterogeneous computing platforms where resources located at the edge of the network are used to provide cloud-like services. This paradigm is widely known as fog computing. Virtual machines (VMs) have been widely utilized in both paradigms to enhance the network scalability, improve resource utilization, and energy efficiency. Moreover, Passive Optical Networks (PONs) are a technology suited to handling the enormous volumes of data generated in the access network due to their energy efficiency and large bandwidth. In this paper, we utilize a PON to provide the connectivity between multiple distributed fog units to achieve federated (i.e. cooperative) computing units in the access network to serve intensive demands. We propose a mixed integer linear program (MILP) to optimize the VM placement in the federated fog computing units with the objective of minimizing the total power consumption while considering inter-VM traffic. The results show a significant power saving as a result of the proposed optimization model by up to 52%, in the VM-allocation compared to a baseline approach that allocates the VM requests while neglecting the power consumption and inter-VMs traffic in the optimization framework.

The rapid growth of time-sensitive applications and services has driven enhancements to computing infrastructures. The main challenge that needs addressing for these applications is the optimal placement of the end-users demands to reduce the total power consumption and delay. One of the widely adopted paradigms to address such a challenge is fog computing. Placing fog units close to end-users at the edge of the network can help mitigate some of the latency and energy efficiency issues. Compared to the traditional hyperscale cloud data centres, fog computing units are constrained by computational power, hence, the capacity of fog units plays a critical role in meeting the stringent demands of the end-users due to intensive processing workloads. In this paper, we aim to optimize the placement of virtual machines (VMs) demands originating from end-users in a fog computing setting by formulating a Mixed Integer Linear Programming (MILP) model to minimize the total power consumption through the use of a federated architecture made up of multiple distributed fog cells. The obtained results show an increase in processing capacity in the fog layer and a reduction in the power consumption by up to 26% compared to the Non-Federated fogs network.

Massive amounts of data are expected to be generated by the billions of objects that form the Internet of Things (IoT). A variety of automated services such as monitoring will largely depend on the use of different Machine Learning (ML) algorithms. Traditionally, ML models are processed by centralized cloud data centers, where IoT readings are offloaded to the cloud via multiple networking hops in the access, metro, and core layers. This approach will inevitably lead to excessive networking power consumptions as well as Quality-of-Service (QoS) degradation such as increased latency. Instead, in this paper, we propose a distributed ML approach where the processing can take place in intermediary devices such as IoT nodes and fog servers in addition to the cloud. We abstract the ML models into Virtual Service Requests (VSRs) to represent multiple interconnected layers of a Deep Neural Network (DNN). Using Mixed Integer Linear Programming (MILP), we design an optimization model that allocates the layers of a DNN in a Cloud/Fog Network (CFN) in an energy efficient way. We evaluate the impact of DNN input distribution on the performance of the CFN and compare the energy efficiency of this approach to the baseline where all layers of DNNs are processed in the centralized Cloud Data Center (CDC)., Comment: arXiv admin note: text overlap with arXiv:2105.03221

Deep Neural Networks (DNNs) have served as a catalyst in introducing a plethora of next-generation services in the era of Internet of Things (IoT), thanks to the availability of massive amounts of data collected by the objects on the edge. Currently, DNN models are used to deliver many Artificial Intelligence (AI) services that include image and natural language processing, speech recognition, and robotics. Accordingly, such services utilize various DNN models that make it computationally intensive for deployment on the edge devices alone. Thus, most AI models are offloaded to distant cloud data centers (CDCs), which tend to consolidate large amounts of computing and storage resources into one or more CDCs. Deploying services in the CDC will inevitably lead to excessive latencies and overall increase in power consumption. Instead, fog computing allows for cloud services to be extended to the edge of the network, which allows for data processing to be performed closer to the end-user device. However, different from cloud data centers, fog nodes have limited computational power and are highly distributed in the network. In this paper, using Mixed Integer Linear Programming (MILP), we formulate the placement of DNN inference models, which is abstracted as a network embedding problem in a Cloud Fog Network (CFN) architecture, where power savings are introduced through trade-offs between processing and networking. We study the performance of the CFN architecture by comparing the energy savings when compared to the baseline approach which is the CDC.