arXiv subjects

Soumaya Cherkaoui

Publications and source records attributed to Soumaya Cherkaoui.

72 records · Page 4Linked to original sources

arXiv2022

Network slicing for vehicular communications: a multi-agent deep reinforcement learning approach

This paper studies the multi-agent resource allocation problem in vehicular networks using non-orthogonal multiple access (NOMA) and network slicing. To ensure heterogeneous service requirements for different vehicles, we propose a network slicing architecture. We focus on a non-cellular network scenario where vehicles communicate by the broadcast approach via the direct device-to-device interface. In such a vehicular network, resource allocation among vehicles is very difficult, mainly due to (i) the rapid variation of wireless channels among highly mobile vehicles and (ii) the lack of a central coordination point. Thus, the possibility of acquiring instantaneous channel state information to perform centralized resource allocation is precluded. The resource allocation problem considered is therefore very complex. It includes not only the usual spectrum and power allocation, but also coverage selection (which target vehicles to broadcast to) and packet selection (which network slice to use). This problem must be solved jointly since selected packets can be overlaid using NOMA and therefore spectrum and power must be carefully allocated for better vehicle coverage. To do so, we provide a optimization approach and study the NP-hardness of the problem. Then, we model the problem using multi-agent Markov decision process. Finally, we use a deep reinforcement learning (DRL) approach to solve the problem. The proposed DRL algorithm is practical because it can be implemented in an online and distributed manner. We show that our approach is robust and efficient when faced with different variations of the network parameters and compared to centralized benchmarks.

cs.NI↗

arXiv2022

Electrical Load Forecasting Using Edge Computing and Federated Learning

In the smart grid, huge amounts of consumption data are used to train deep learning models for applications such as load monitoring and demand response. However, these applications raise concerns regarding security and have high accuracy requirements. In one hand, the data used is privacy-sensitive. For instance, the fine-grained data collected by a smart meter at a consumer's home may reveal information on the appliances and thus the consumer's behaviour at home. On the other hand, the deep learning models require big data volumes with enough variety and to be trained adequately. In this paper, we evaluate the use of Edge computing and federated learning, a decentralized machine learning scheme that allows to increase the volume and diversity of data used to train the deep learning models without compromising privacy. This paper reports, to the best of our knowledge, the first use of federated learning for household load forecasting and achieves promising results. The simulations were done using Tensorflow Federated on the data from 200 houses from Texas, USA.

cs.CE↗

arXiv2022

Towards a Scalable and Trustworthy Blockchain: IoT Use Case

Recently, blockchain has gained momentum as a novel technology that gives rise to a plethora of new decentralized applications (e.g., Internet of Things (IoT)). However, its integration with the IoT is still facing several problems (e.g., scalability, flexibility). Provisioning resources to enable a large number of connected IoT devices implies having a scalable and flexible blockchain. To address these issues, we propose a scalable and trustworthy blockchain (STB) architecture that is suitable for the IoT; which uses blockchain sharding and oracles to establish trust among unreliable IoT devices in a fully distributed and trustworthy manner. In particular, we design a Peer-To-Peer oracle network that ensures data reliability, scalability, flexibility, and trustworthiness. Furthermore, we introduce a new lightweight consensus algorithm that scales the blockchain dramatically while ensuring the interoperability among participants of the blockchain. The results show that our proposed STB architecture achieves flexibility, efficiency, and scalability making it a promising solution that is suitable for the IoT context.

cs.CR↗

arXiv2022

Massive IoT Access With NOMA in 5G Networks and Beyond Using Online Competitiveness and Learning

This paper studies the problem of online user grouping, scheduling and power allocation in beyond 5G cellular-based Internet of things networks. Due to the massive number of devices trying to be granted to the network, non-orthogonal multiple access method is adopted in order to accommodate multiple devices in the same radio resource block. Different from most previous works, the objective is to maximize the number of served devices while allocating their transmission powers such that their real-time requirements as well as their limited operating energy are respected. First, we formulate the general problem as a mixed integer non-linear program (MINLP) that can be transformed easily to MILP for some special cases. Second, we study its computational complexity by characterizing the NP-hardness of different special cases. Then, by dividing the problem into multiple NOMA grouping and scheduling subproblems, efficient online competitive algorithms are proposed. Further, we show how to use these online algorithms and combine their solutions in a reinforcement learning setting to obtain the power allocation and hence the global solution to the problem. Our analysis are supplemented by simulation results to illustrate the performance of the proposed algorithms with comparison to optimal and state-of-the-art methods.

cs.NI↗

arXiv2022

Data-Quality Based Scheduling for Federated Edge Learning

FEderated Edge Learning (FEEL) has emerged as a leading technique for privacy-preserving distributed training in wireless edge networks, where edge devices collaboratively train machine learning (ML) models with the orchestration of a server. However, due to frequent communication, FEEL needs to be adapted to the limited communication bandwidth. Furthermore, the statistical heterogeneity of local datasets' distributions, and the uncertainty about the data quality pose important challenges to the training's convergence. Therefore, a meticulous selection of the participating devices and an analogous bandwidth allocation are necessary. In this paper, we propose a data-quality based scheduling (DQS) algorithm for FEEL. DQS prioritizes reliable devices with rich and diverse datasets. In this paper, we define the different components of the learning algorithm and the data-quality evaluation. Then, we formulate the device selection and the bandwidth allocation problem. Finally, we present our DQS algorithm for FEEL, and we evaluate it in different data poisoning scenarios.

cs.DC↗

arXiv2022

Prediction and Detection of FDIA and DDoS Attacks in 5G Enabled IoT

Security in the fifth generation (5G) networks has become one of the prime concerns in the telecommunication industry. 5G security challenges come from the fact that 5G networks involve different stakeholders using different security requirements and measures. Deficiencies in security management between these stakeholders can lead to security attacks. Therefore, security solutions should be conceived for the safe deployment of different 5G verticals (e.g., industry 4.0, Internet of Things (IoT), etc.). The interdependencies among 5G and fully connected systems, such as IoT, entail some standard security requirements, namely integrity, availability, and confidentiality. In this article, we propose a hierarchical architecture for securing 5G enabled IoT networks, and a security model for the prediction and detection of False Data Injection Attacks (FDIA) and Distributed Denial of Service attacks (DDoS). The proposed security model is based on a Markov stochastic process, which is used to observe the behavior of each network device, and employ a range-based behavior sifting policy. Simulation results demonstrate the effectiveness of the proposed architecture and model in detecting and predicting FDIA and DDoS attacks in the context of 5G enabled IoT.

cs.CR↗

arXiv2022

Network Slicing with MEC and Deep Reinforcement Learning for the Internet of Vehicles

The interconnection of vehicles in the future fifth generation (5G) wireless ecosystem forms the so-called Internet of vehicles (IoV). IoV offers new kinds of applications requiring delay-sensitive, compute-intensive and bandwidth-hungry services. Mobile edge computing (MEC) and network slicing (NS) are two of the key enabler technologies in 5G networks that can be used to optimize the allocation of the network resources and guarantee the diverse requirements of IoV applications. As traditional model-based optimization techniques generally end up with NP-hard and strongly non-convex and non-linear mathematical programming formulations, in this paper, we introduce a model-free approach based on deep reinforcement learning (DRL) to solve the resource allocation problem in MEC-enabled IoV network based on network slicing. Furthermore, the solution uses non-orthogonal multiple access (NOMA) to enable a better exploitation of the scarce channel resources. The considered problem addresses jointly the channel and power allocation, the slice selection and the vehicles selection (vehicles grouping). We model the problem as a single-agent Markov decision process. Then, we solve it using DRL using the well-known DQL algorithm. We show that our approach is robust and effective under different network conditions compared to benchmark solutions.

cs.NI↗

arXiv2022

An IoT Blockchain Architecture Using Oracles and Smart Contracts: the Use-Case of a Food Supply Chain

The blockchain is a distributed technology which allows establishing trust among unreliable users who interact and perform transactions with each other. While blockchain technology has been mainly used for crypto-currency, it has emerged as an enabling technology for establishing trust in the realm of the Internet of Things (IoT). Nevertheless, a naive usage of the blockchain for IoT leads to high delays and extensive computational power. In this paper, we propose a blockchain architecture dedicated to being used in a supply chain which comprises different distributed IoT entities. We propose a lightweight consensus for this architecture, called LC4IoT. The consensus is evaluated through extensive simulations. The results show that the proposed consensus uses low computational power, storage capability and latency.

cs.NI↗

arXiv2022

Matching-based Service Offloading for Compute-less Driven IoT Networks

With the advent of the Internet of Things (IoT) and 5G networks, edge computing is offering new opportunities for business model and use cases innovations. Service providers can now virtualize the cloud beyond the data center to meet the latency, data sovereignty, reliability, and interoperability requirements. Yet, many new applications (e.g., augmented reality, virtual reality, artificial intelligence) are computation-intensive and delay-sensitivity. These applications are invoked heavily with similar inputs that could lead to the same output. Compute-less networks aim to implement a network with a minimum amount of computation and communication. This can be realized by offloading prevalent services to the edge and thus minimizing communication in the core network and eliminating redundant computations using the computation reuse concept. In this paper, we present matching-based services offloading schemes for compute-less IoT networks. We adopt the matching theory to match service offloading to the appropriate edge server(s). Specifically, we design, WHISTLE, a vertical many-to-many offloading scheme that aims to offload the most invoked and highly reusable services to the appropriate edge servers. We further extend WHISTLE to provide horizontal one-to-many computation reuse sharing among edge servers which leads to bouncing less computation back to the cloud. We evaluate the efficiency and effectiveness of WHISTLE with a real-world dataset. The obtained findings show that WHISTLE is able to accelerate the tasks completion time by 20%, reduce the computation up to 77%, and decrease the communication up to 71%. Theoretical analyses also prove the stability of the designed schemes.

cs.NI↗

arXiv2021

How Far Can We Go in Compute-less Networking: Computation Correctness and Accuracy

Emerging applications such as augmented reality and tactile Internet are compute-intensive and latency-sensitive, which hampers their running in constrained end devices alone or in the distant cloud. The stringent requirements of such application drove to the realization of Edge computing in which computation is offloaded near to users. Compute-less networking is an extension of edge computing that aims at reducing computation and abridging communication by adopting in-network computing and computation reuse. Computation reuse aims to cache the result of computations and use them to perform similar tasks in the future and, therefore, avoid redundant calculations and optimize the use of resources. In this paper, we focus on the correctness of the final output produced by computation reuse. Since the input might not be identical but similar, the reuse of previous computation raises questions about the accuracy of the final results. To this end, we implement a proof of concept to study and gauge the effectiveness and efficiency of computation reuse. We are able to reduce task completion time by up to 80% while ensuring high correctness. We further discuss open challenges and highlight future research directions.

cs.NI↗

arXiv2021

Service Function Chaining in MEC: A Mean-Field Game and Reinforcement Learning Approach

Multi-access edge computing (MEC) and network virtualization technologies are important enablers for fifth-generation (5G) networks to deliver diverse applications and services. Services are often provided as fully connected virtual network functions (VNF)s, through service function chaining (SFC). However, the problem of allocating SFC resources at the network edge still faces many challenges related to the way VNFs are placed, chained and scheduled. In this paper, to solve these problems, we propose a game theory-based approach with the objective to reduce service latency in the context of SFC at the network edge. The problem of allocating SFC resources can be divided into two subproblems. 1) The VNF placement and routing subproblem, and 2) the VNF scheduling subproblem. For the former subproblem, we formulate it as a mean field game (MFG) in which VNFs are modeled as entities contending over edge resources with the goal of reducing the resource consumption of MEC nodes and reducing latency for users. We propose a on a reinforcement learning-based technique, where the Ishikawa-Mann learning algorithm (IMLA) is used. For the later subproblem we formulate it as a matching game between the VFNs and an edge resources in order to find the execution order of the VNFs while reducing the latency. To efficiently solve it, we propose a modified version of the many-to-one deferred acceptance algorithm (DAA), called the enhanced multi-step deferred acceptance algorithm (eMSDA). To illustrate the performance of the proposed approaches, we perform extensive simulations. The obtained results show that the proposed approaches outperform the benchmarks other state-of-the-art methods.

cs.NI↗

arXiv2021

A Network-based Compute Reuse Architecture for IoT Applications

The tremendous advancements in the Internet of Things (IoT) increasingly involve computationally intensive services. These services often require more computation resources than can entirely be satisfied on local IoT devices. Cloud computing is traditionally used to provide unlimited computation resources at distant servers. However, such remote computation may not address the short-delay constraints that many of today's IoT applications require. Edge computing allows offloading computing close to end users to overcome computation and delay issues. Nonetheless, the edge servers may suffer from computing inefficiencies. Indeed, some IoT applications are invoked multiple times by multiple devices. These invocations are often used with the same or similar input data, which leads to the same computational output (results). Still, the edge server willfully executes all received redundant tasks. In this work, we investigate the use of the computation reuse concept at the edge server. We design a network-based computation reuse architecture for IoT applications. The architecture stores previously executed results and reuses them to satisfy newly arrived similar tasks instead of performing computation from scratch. By doing so, we eliminate redundant computation, optimize resource utilization, and decrease task completion time. We implemented the architecture and evaluated its performance both at the networking and application levels. From the networking perspective, we reach up to an 80\% reduction in task completion time and up to 60\% reduction in resource utilization. From the application perspective, we achieve up to 90\% computation correctness and accuracy.

cs.NI↗

arXiv2020

Design and Evaluation of a Receiver for Wired Nano-Communication Networks

In this paper, we propose a bio-inspired receiver, which detects the electrons transmitted through a nanowire, then, it converts the detected information into a blue light using bioluminescence. Using light allows the designed receiver to also act as a relay for the nearest gateway (photo-detector). We simulate the construction of the nanowire, present its electrical characteristics and calculate its maximum throughput for a better design of the receiver. The designed receiver contains two parts, a part that detects the transmitted electrons, which we model by using an equivalent circuit, and a part that converts the detected electrons into a blue light. We derive the analytical expressions of the equivalent circuit's components, and we calculate the emitted photons for each electrical pulse detected. We also propose modulation techniques that guaranty an effective decoding of the information. We send a binary message and we follow the electron detection process of the proposed receiver until light emission and we calculate the Bit Error Rate (BER) to evaluate the performance of the designed receiver. The results of this study show that the designed receiver can accurately detect the electrons sent through a conductive nanowire in wired nano-communication networks, and that it can also act as a relay for the nearest gateway.

cs.ET↗

arXiv2020

A Physical Channel Model for Wired Nano-Communication Networks

In this paper, we propose a new end-to-end system for wired nano-communication networks using a self-assembled polymer. The self-assembly of a polymer creates a channel between the transmitter and the receiver in the form of a conductive nanowire that uses electrons as carriers of information. We derive the channel's analytical model and its master equation to study the dynamic process of the polymer self-assembly. We validate the analytical model with numerical and Monte-Carlo simulations. Then, we approximate the master equation by a one-dimensional Fokker-Planck equation and we solve this equation analytically and numerically. We formulate the expressions of the polymer elongation rate, its diffusion coefficient and the nullcline to study the distribution and the stability of the self-assembled nanowire. This study shows promising results for realizing stable polymer-based wired nanonetworks that can achieve high throughput.

cs.ET↗

arXiv2019

Toward a Wired Ad Hoc Nanonetwork

Nanomachines promise to enable new medical applications, including drug delivery and real time chemical reactions' detection inside the human body. Such complex tasks need cooperation between nanomachines using a communication network. Wireless Ad hoc networks, using molecular or electromagnetic-based communication have been proposed in the literature to create flexible nanonetworks between nanomachines. In this paper, we propose a Wired Ad hoc NanoNETwork (WANNET) model design using actin-based nano-communication. In the proposed model, actin filaments self-assembly and disassembly is used to create flexible nanowires between nanomachines, and electrons are used as carriers of information. We give a general overview of the application layer, Medium Access Control (MAC) layer and a physical layer of the model. We also detail the analytical model of the physical layer using actin nanowire equivalent circuits, and we present an estimation of the circuit component's values. Numerical results of the derived model are provided in terms of attenuation, phase and delay as a function of the frequency and distances between nanomachines. The maximum throughput of the actin-based nanowire is also provided, and a comparison between the maximum throughput of the proposed WANNET, vs other proposed approaches is presented. The obtained results prove that the proposed wired ad hoc nanonetwork can give a very high achievable throughput with a smaller delay compared to other proposed wireless molecular communication networks.

cs.ET↗

arXiv2019

Performance Enhancement of Diffusion-based Molecular Communication with Photolysis

Inter-Symbol Interference (ISI) is the main challenge of bio-inspired diffusion-based molecular communication. In real biological systems, the degradation of the remaining molecules from a previous transmission is used to mitigate ISI. While most prior works have proposed the use of enzymes to catalyze the molecule degradation, enzymes also degrade the molecules carrying the information, which drastically decreases the signal strength. In this paper, we propose the use of photolysis reactions, which use the light to instantly transform the emitted molecules so they are no longer recognized after their detection. The light is emitted at an optimal time, allowing the receiver to detect as many molecules as possible, which increases both the signal strength and ISI mitigation. A lower bound expression on the expected number of the observed molecules at the receiver is derived. The bit error probability expression is also formulated. Both the expected number of observed molecules and the bit error expressions are validated with simulation results, which show a visible enhancement when using photolysis reactions. The performance of the proposed method is evaluated using the Interference-to-Total-Received molecules metric (ITR) and the derived bit error probability.

cs.ET↗

arXiv2019

Design and Evaluation of Self-Assembled Actin-Based Nano-Communication

The tremendous progress in nanotechnology over the last century, makes it possible to engineer tiny nanodevices, which they need a nano-communication network to interact. Two solutions are proposed in literature to create a nano-communication system, either by using the classical electromagnetic paradigm with Terahertz band, or using the bio-inspired molecular communication. However, Terahertz is suffering from molecular absorption and scattering losses at nano level, and the achievable throughput of molecular communication is very low. In this paper, we propose a new solution to establish a wired nano-communication. Self-assembled actin-based is a new method that takes advantage of actin filaments self-assembly to create a nano wire between a transmitter and a receiver, and use electrons as information carriers. VPython framework is used in this paper to perform stochastic simulations of the nano wire formation. The algorithms used for the simulations are presented. The stability of the constructed nano wire is analyzed, and the error probability is calculated. Self-assembled actin-based method promises a fast and stable nano-communication system with a very high achievable throughput.

cs.ET↗

arXiv2017

RSU Cloud and its Resource Management in support of Enhanced Vehicular Applications

We propose Roadside Unit (RSU) Clouds as a novel way to offer non-safety application with QoS for VANETs. The architecture of RSU Clouds is delineated, and consists of traditional RSUs and specialized micro-datacenters and virtual machines (VMs) using Software Defined Networking (SDN). SDN offers the flexibility to migrate or replicate virtual services and reconfigure the data forwarding rules dynamically. However, frequent changes to service hosts and data flows not only result in degradation of services, but are also costly for service providers. In this paper, we use Mininet to analyze and formally quantify the reconfiguration overhead. Our unique RSU Cloud Resource Management (CRM) model jointly minimizes reconfiguration overhead, cost of service deployment and infrastructure routing delay. To the best of our knowledge, we are the first to utilize this approach. We compare the performance of purist approach to our Integer Linear Programming (ILP) model and our innovative heuristic for the CRM technique and discuss the results. We will show the benefits of a holistic approach in Cloud Resource Management with SDN.

cs.NI↗