Edge Servers Research Articles

A Cascaded Multi-Agent Reinforcement Learning-Based Resource Allocation for Cellular-V2X Vehicular Platooning Networks.

The platooning of cars and trucks is a pertinent approach for autonomous driving due to the effective utilization of roadways. The decreased gas consumption levels are an added merit owing to sustainability. Conventional platooning depended on Dedicated Short-Range Communication (DSRC)-based vehicle-to-vehicle communications. The computations were executed by the platoon members with their constrained capabilities. The advent of 5G has favored Intelligent Transportation Systems (ITS) to adopt Multi-access Edge Computing (MEC) in platooning paradigms by offloading the computational tasks to the edge server. In this research, vital parameters in vehicular platooning systems, viz. latency-sensitive radio resource management schemes, and Age of Information (AoI) are investigated. In addition, the delivery rates of Cooperative Awareness Messages (CAM) that ensure expeditious reception of safety-critical messages at the roadside units (RSU) are also examined. However, for latency-sensitive applications like vehicular networks, it is essential to address multiple and correlated objectives. To solve such objectives effectively and simultaneously, the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) framework necessitates a better and more sophisticated model to enhance its ability. In this paper, a novel Cascaded MADDPG framework, CMADDPG, is proposed to train cascaded target critics, which aims at achieving expected rewards through the collaborative conduct of agents. The estimation bias phenomenon, which hinders a system's overall performance, is vividly circumvented in this cascaded algorithm. Eventually, experimental analysis also demonstrates the potential of the proposed algorithm by evaluating the convergence factor, which stabilizes quickly with minimum distortions, and reliable CAM message dissemination with 99% probability. The average AoI quantity is maintained within the 5-10 ms range, guaranteeing better QoS. This technique has proven its robustness in decentralized resource allocation against channel uncertainties caused by higher mobility in the environment. Most importantly, the performance of the proposed algorithm remains unaffected by increasing platoon size and leading channel uncertainties.

A WSN and vision based smart, energy efficient, scalable, and reliable parking surveillance system with optical verification at edge for resource constrained IoT devices

As urbanization accelerates, the demand for efficient parking surveillance solutions has increased. However, existing solutions often face challenges related to energy consumption, scalability, and reliability. This paper introduces a smart hybrid parking surveillance system integrating wireless sensor networks (WSNs) with vision based solution at the edge for resource constrained IoT devices to address these challenges. The solution leverages WSNs for periodic readings of parking space occupancy and introduces a low power sleep mode in the network for energy efficiency, along with optical verification strategies using computer vision models like R-CNN and Faster R-CNN FPN on ResNet50 and MobileNetv2 backbones for distinguishing between true and false positives in the WSN data for a greater accuracy in parking space occupancy. The system utilizes edge for computing on edge servers resulting in increased responsiveness of the system, reduced data transmission and real time processing of data. The proposed solution is formulated in such a way that it automatically switches between WSN and vision based sensing resulting in less energy consumption and longer lifespan of the system without compromising on accuracy. Through experimental results it is observed that models trained on the MobileNetv2 backbone demonstrated at least twice faster for both processing the images and training compared to those models trained on the ResNet backbone. On the other hand, both Faster R-CNN FPN (input resolution: 1440) and R-CNN (input resolution: 128) models trained on the MobileNetv2 backbone have slightly lower accuracies than the same models trained on the ResNet50 backbone.

Mobility-aware parallel offloading and resource allocation scheme for vehicular edge computing

Vehicle edge computing (VEC) enhances the distributed task processing capability within intelligent vehicle-infrastructure cooperative systems (i-VICS) by deploying servers at the network edge. However, the proliferation of onboard sensors and the continual emergence of new applications have exacerbated the inadequacy of wireless spectrum resources and edge server resources, while the high mobility of vehicles reduces reliability in task processing, resulting in increased communication and task processing delays. To address these challenges, we propose a mobile-aware Many-to-Many Parallel (MTMP) offloading scheme that integrates: a) millimeter-wave (mmWave) and cellular vehicle-to-everything (C-V2X) to mitigate excessive communication delays; and b) leveraging the underutilized resources of surrounding vehicles and parallel offloading to mitigate excessive task processing delays. To minimize the average completion delay of all tasks, this paper formulates the objective as a min-max optimization problem and solves it using the maximum entropy method (MEM), the Lagrange multiplier method, and an iterative algorithm. Extensive experimental results demonstrate the superior performance of the proposed scheme in comparison with other baseline algorithms. Specifically, our proposal achieves a 47 % reduction in task completion delay under optimal conditions, a 31.3 % increase in task completion rate, and a 30 % decrease in program runtime compared to the worst-performing algorithm.

Failure-aware resource provisioning for hybrid computation offloading in cloud-assisted edge computing using gravity reference approach

This paper tackles the challenges of computation offloading in the cloud–edge paradigm. Although many solutions exist for enhancing the server’s computational and communication efficiency, they mainly focus on reducing latency and often neglect the impact of overlapping multi-request processing on scheduling reliability. Additionally, these approaches do not account for the preemptive characteristics of applications running in the VMs that lead to higher energy consumption. We propose a novel hybrid integer multi-objective dynamic decision-making approach enhanced with the gravity reference point method. This method determines the proportion of computations executed on cloud servers versus those handled locally on edge servers. Our hybrid approach leverages the gravitational potential reference point and crowding degrees to improve the characteristics of whale populations, addressing the limitations of the traditional whale algorithm, which depends on individual whales’ varying foraging behaviors influenced by a random probability number. By evaluating the crowding level around the prey, the foraging behavior of individual whales is adjusted to enhance the algorithm’s convergence speed and optimization accuracy, thereby increasing its reliability. The results show that our hybrid computation offloading model significantly improves time latency by 76.45%, energy efficiency by 63.12%, reliability by 82%, quality of service by 83.78%, distributor throughput by 87.31%, asset availability by 73.05%, and guarantee ratio by 89.72% compared to traditional offloading methods.

A hybrid Bi-level management framework for caching and communication in Edge-AI enabled IoT

The proliferation of IoT devices has led to a surge in network traffic, resulting in higher energy usage and response delays. In-network caching has emerged as a viable solution to address this issue. However, caching IoT data faces two key challenges: the transient nature of IoT content and the unknown spatiotemporal content popularity. Additionally, the use of a global view on dynamic IoT networks is problematic due to the high communication overhead involved. To tackle these challenges, this paper presents an adaptive management approach that jointly optimizes caching and communication in IoT networks using a novel bi-level control method called BC3. The approach employs two types of controllers: a global ILP-based optimal controller for long-term timeslots and local learning-based controllers for short-term timeslots. The long-term controller periodically establishes a global cache policy for the network and sends specific cache rules to each edge server. The local controller at each edge server solves the joint problem of bandwidth allocation and cache adaptation using deep reinforcement learning (DRL) technique. The main objective is to minimize energy consumption and system response time with utilizing the global and local observations. Experimental results demonstrate that the proposed approach increases cache hit rate by approximately 12% and uses 11% less energy compared to the other methods. Increasing the cache hit rate can lead to a reduction in about 17% in response time for user requests. Our bi-level control approach offers a promising solution for leveraging the network's global visibility while balancing communication overhead (as energy consumption) against system performance. Additionally, the proposed method has the lowest cache eviction, around 19% lower than the lowest eviction of the other comparison methods. The eviction metric is a metric to evaluate the effectiveness of adaptive caching approach designed for transient data.

MS-GD-P: priority-based service deployment for cloud-edge-end scenarios

In cloud-edge-end scenarios, how to achieve rational resource allocation, implement effective service deployment, and ensure high service quality has become a hot research topic in academic domains. Service providers usually deploy services by considering the characteristics of different geographical regions, which helps to meet the diverse needs of users in different regions and optimize resource allocation and utilization. However, due to the widespread distribution of users and limited server resources, providing all types of services to users in every geographical region is not feasible. In addition, edge servers are prone to operational failures caused by software anomalies, hardware malfunctions, and malicious attacks, which will decrease service reliability. To address the problems above, this paper proposes a metric for service priorities based on user demands and regional characteristics for different geographical regions. Building upon this foundation, a Multi-Service Geographic region Deployment based on Priority (MS-GD-P) is proposed. This method takes user coverage and service reliability into consideration, which facilitates users’ needs for multiple services in different geographical regions. Experimental results on real datasets demonstrate that MS-GD-P outperforms baseline methods in user coverage and service reliability.

BeHarmony: Blockchain-Enabled Trustworthy Communication and Legitimate Decision Making in Multi-Party Internet of Vehicles Systems

The rapid development of the Internet of Vehicles using centralized systems faces significant challenges, including reliability and security vulnerabilities and high latency. This paper introduces a blockchain-enabled authentication and communication network for scalable IoV to enhance security, reduce latency, and relieve the dependency on centralized infrastructures. The network applies blockchain-enabled domain name services and mutual authentication for fault tolerance consensus, such as PBFT and RAFT, featuring a primary layer of road side units and edge servers for inter-vehicle communication and a sub-layer within each vehicle for intra-vehicle communication. The study evaluates various scenarios and assesses roadside unit availability based on random distribution along vehicle routes. This paper also discusses the legal issues involved in the proposed model, highlighting that the IoV system should be governed by a contract-based decentralized IoV system comprising both smart contracts and traditional contracts. This model offers a novel approach to developing a decentralized, secure, efficient, and ethical IoV ecosystem, advancing autonomous and reliable vehicular networks.

Corun: Concurrent Inference and Continuous Training at the Edge for Cost-Efficient AI-Based Mobile Image Sensing.

Intelligent mobile image sensing powered by deep learning analyzes images captured by cameras from mobile devices, such as smartphones or smartwatches. It supports numerous mobile applications, such as image classification, face recognition, and camera scene detection. Unfortunately, mobile devices often lack the resources necessary for deep learning, leading to increased inference latency and rapid battery consumption. Moreover, the inference accuracy may decline over time due to potential data drift. To address these issues, we introduce a new cost-efficient framework, called Corun, designed to simultaneously handle multiple inference queries and continual model retraining/fine-tuning of a pre-trained model on a single commodity GPU in an edge server to significantly improve the inference throughput, upholding the inference accuracy. The scheduling method of Corun undertakes offline profiling to find the maximum number of concurrent inferences that can be executed along with a retraining job on a single GPU without incurring an out-of-memory error or significantly increasing the latency. Our evaluation verifies the cost-effectiveness of Corun. The inference throughput provided by Corun scales with the number of concurrent inference queries. However, the latency of inference queries and the length of a retraining epoch increase at substantially lower rates. By concurrently processing multiple inference and retraining tasks on one GPU instead of using a separate GPU for each task, Corun could reduce the number of GPUs and cost required to deploy mobile image sensing applications based on deep learning at the edge.

Task offloading scheme in Mobile Augmented Reality using hybrid Monte Carlo tree search (HMCTS)

Mobile Augmented Reality (MAR) applications enhance user experiences by providing realistic information about the current location through mobile devices. However, MAR applications are computationally intensive, leading to high energy consumption and latency issues. To address these challenges, this research presents a Hybrid Monte Carlo Tree Search (HMCTS) based task offloading scheme, combining a genetic algorithm with Monte Carlo tree search for efficient task management. The proposed method uses YoloV7 for object recognition and aims to reduce energy consumption, response time, and migration time. Experimental results demonstrate that the HMCTS approach significantly reduces energy consumption to 1290 kJ, response time to 24 ms, and migration time to 0.52 ms, outperforming existing techniques. These improvements highlight the potential of the HMCTS method for enhancing the performance of MAR applications. Proposed hybrid approach aims to improve the efficiency and effectiveness of task offloading in MAR applications. The HMCTS model dynamically offloads tasks to edge servers, optimizing scheduling time, response time, and energy consumption.

PODI: A Private Object Detection Inference framework for autonomous vehicles

Object detection is essential for autonomous vehicles to perceive and understand their environment. The restricted storage and processing capacities of vehicles necessitate the outsourcing of object detection services. However, this may raise concerns regarding the privacy of the uploaded images. Although there have been some studies on privacy-preserving object detection networks, they either lack location privacy protection or involve excessive computational and communication overheads. To address this issue, we propose a private object detection inference framework (PODI), which is based on a Faster R-CNN and aims to protect both classification and location privacy. PODI employs additive secret sharing protocols to support collaborative computation between two edge servers. By using efficient protocols such as secure Maxpool, secure array access, and secure exponent, PODI significantly reduces computational and communication overheads. A theoretical analysis has confirmed the security, correctness, and efficiency of PODI. Extensive experiments were used to demonstrate its security, inference accuracy comparable to plaintext approaches, and lower cost of secure inference.

Cloud-edge collaborative high-frequency acquisition data processing for distribution network resilience improvement

To realize transparent monitoring and resilience improvement of low-voltage distribution network, both the data acquisition scope and frequency have been greatly expanded. Cloud-edge collaboration leverages the edge server’s real-time response capabilities and the cloud server’s robust data processing power to enhance the performance of high-frequency data acquisition processing. Nonetheless, it continues to confront challenges such as the entanglement of optimization variables, the presence of uncertain information, and a lack of awareness regarding acquisition frequencies. In this paper, we propose a machine learning-based cloud-edge collaborative data processing optimization algorithm to minimize the weighted sum of data processing delay and device energy consumption for distribution network resilience improvement. The joint optimization problem is decoupled into device-edge data offloading subproblem and edge-cloud data splitting subproblem, which are solved by the proposed upper confidence bound (UCB) based frequency-aware device-edge data offloading optimization algorithm and the exponential-weight algorithm for exploration and exploitation (EXP3) based edge-cloud data splitting optimization algorithm, respectively. Simulation results show that the proposed algorithm is superior to existing algorithms in performances of energy consumption and total processing delay.

Leveraging Edge Computing for Video Data Streaming in UAV-Based Emergency Response Systems.

The rapid advancement of technology has greatly expanded the capabilities of unmanned aerial vehicles (UAVs) in wireless communication and edge computing domains. The primary objective of UAVs is the seamless transfer of video data streams to emergency responders. However, live video data streaming is inherently latency dependent, wherein the value of the video frames diminishes with any delay in the stream. This becomes particularly critical during emergencies, where live video streaming provides vital information about the current conditions. Edge computing seeks to address this latency issue in live video streaming by bringing computing resources closer to users. Nonetheless, the mobile nature of UAVs necessitates additional trajectory supervision alongside the management of computation and networking resources. Consequently, efficient system optimization is required to maximize the overall effectiveness of the collaborative system with limited UAV resources. This study explores a scenario where multiple UAVs collaborate with end users and edge servers to establish an emergency response system. The proposed idea takes a comprehensive approach by considering the entire emergency response system from the incident site to video distribution at the user level. It includes an adaptive resource management strategy, leveraging deep reinforcement learning by simultaneously addressing video streaming latency, UAV and user mobility factors, and varied bandwidth resources.

TRUST-ME: Trust-Based Resource Allocation and Server Selection in Multi-Access Edge Computing

Multi-access edge computing (MEC) has attracted the interest of the research and industrial community to support Internet of things (IoT) applications by enabling efficient data processing and minimizing latency. This paper presents significant contributions toward optimizing the resource allocation and enhancing the decision-making process in edge computing environments. Specifically, the TRUST-ME model is introduced, which consists of multiple edge servers and IoT devices, i.e., users, with varied computing tasks offloaded to the MEC servers. A utility function was designed to quantify the benefits in terms of latency and cost for the IoT device while utilizing the MEC servers’ computing capacities. The core innovation of our work is a novel trust model that was designed to evaluate the IoT devices’ confidence in MEC servers. This model integrates both direct and indirect trust and reflects the trustworthiness of the servers based on the direct interactions and social feedback from other devices using the same servers. This dual trust approach helps with accurately gauging the reliability of MEC services and ensuring more informed decision making. A reinforcement learning framework based on the optimistic Q-learning with an upper confidence bounds action selection algorithm enables the IoT devices to autonomously select a MEC server to process their computing tasks. Also, a multilateral bargaining model is proposed for fair resource allocation of the MEC servers’ computing resources to the users while accounting for their computing demands. Numerical simulations demonstrated the operational effectiveness, convergence, and scalability of the TRUST-ME model, which was validated through real-world scenarios and comprehensive comparative evaluations against existing approaches.

Keeping Verticals’ Sovereignty During Application Migration in Continuum

Competing service providers in the cloud environment ensure services are delivered under the promised security requirements. It is crucial for mobile services where user’s movement results in the service’s migration between edge servers or clouds in the Continuum. Maintaining service sovereignty before, during, and after the migration is a real challenge, especially when the service provider has committed to ensuring its quality following the Service Level Agreement. In this paper, we present the main challenges mobile service providers face in a cloud environment to guarantee the required level of security and digital sovereignty as described in the Security Service Level Agreement, with emphasis on challenges resulting from the service migration between the old and new locations. We present the security and sovereignty context intended for migration and the steps of the migration algorithm. We also analyze three specific service migration cases for three vertical industries with different service quality requirements.

VESBELT: An energy-efficient and low-latency aware task offloading in Maritime Internet-of-Things networks using ensemble neural networks

Due to increasing maritime activities, the number of Maritime Internet-of-things (MIoT) devices requiring real-time marine data processing is growing exponentially. To offload maritime tasks and address the limited computational capabilities of heterogeneous MIoT devices, edge and cloud computing networks are employed. However, these networks introduce several challenges, including increased energy consumption and service latency within the complex marine network environment. Current state-of-the-art solutions address these issues by focusing exclusively on real-time offloading data, neglecting the relationship with past offloading tasks. In this work, we develop an optimization framework, named VESBELT, for offloading tasks from Vessel users to nearby Edge Servers or the cloud server, aiming to reduce Energy consumption and service Latency Trade-off through a multi-objective linear programming problem. However, finding optimal solutions from this formulation is considered an NP-hard problem. To address this, we introduce VESBELT-ECNN, VESBELT-EANN, and VESBELT-ELSTM systems that leverage ensemble convolutional, artificial neural networks and Long-short-term memory, respectively, to achieve solutions in polynomial time. The developed ensemble models integrate multiple combinations of deep learning models and exploit the pre-trained models to provide real-time solutions with better prediction accuracy. The experimental findings, obtained using Python programming version 3.10.2, indicate that the proposed VESBELT-ECNN, VESBELT-EANN, and VESBELT-ELSTM systems outperform existing approaches in terms of user Quality of Experience (QoE) in the timeliness domain and energy savings.

Energy-efficiency optimization for heterogeneous computing-assisted NOMA-MEC edge AI tasks

Edge artificial intelligence (AI) is an emerging paradigm that leverages edge computing to pave the last-mile delivery of AI. To satisfy the increasing demand for high-performance computing and low latency of edge service, heterogeneous computing accelerators, especially Neural Processor Units (NPUs), are widely deployed on edge nodes. However, the edge AI heterogeneous computing system encounters the challenge of energy constraints. In this paper, we investigate the energy efficiency (EE) optimization problem in heterogeneous computing-assisted non-orthogonal multiple access mobile edge computing (NOMA-MEC) network model. Edge devices are configured with CPU-NPU heterogeneous computing processors to improve the AI task processing, and NOMA is applied to edge task offloading to enable massive connectivity. The system-centric energy efficiency maximization problem is studied. We formulate a system-centric energy efficiency maximization problem. To solve this problem, we decouple the original problem into two subproblems, i.e., the optimization problems of heterogeneous computing workload splitting and task offloading. A heuristic algorithm and binary search algorithm are proposed to optimize NOMA user pairing and task offloading delay, respectively. Furthermore, we propose a multi-objective alternative iterative algorithm to optimize system energy efficiency. Numerical results show that the proposed scheme can significantly improve the energy efficiency of heterogeneous computing-assisted NOMA-MEC networks compared to the existing baselines.

Multi-agent DRL for edge computing: A real-time proportional compute offloading

In the Industrial Internet of Things, devices with limited computing power and energy storage often rely on offloading tasks to edge servers for processing. However, existing methods are plagued by the high cost of device communication and unstable training processes. Consequently, Deep reinforcement learning (DRL) has emerged as a promising solution to tackle the computation offloading problem. In this paper, we propose a framework called multi-agent twin delayed shared deep deterministic policy gradient algorithm (MASTD3) based on DRL. Firstly, we formulate the task offloading conundrum as a long-term optimization problem, which aids in mitigating the challenge of deciding between local or remote task execution by a device, leading to more effective task offloading management. Secondly, we enhance MASTD3 by introducing a priority experience replay buffer mechanism and a model sample replay buffer mechanism, thus improving sample utilization and overcoming the cold-start problem associated with long-term optimization. Moreover, we refine the actor-critic structure, enabling all agents to share the same critic network. This modification accelerates convergence speed during the training process and reduces computational costs during runtime. Finally, experimental results demonstrate that MASTD3 effectively addresses the proportional offloading problem, which is optimized by 44.32%, 29.26%, and 17.47% compared to DDPQN, MADDPG, and FLoadNet.

Vehicle edge server deployment based on reinforcement learning in cloud-edge collaborative environment

Vehicle edge server deployment based on reinforcement learning in cloud-edge collaborative environment

Learning optimal edge processing with offloading and energy harvesting

Modern portable devices can execute increasingly sophisticated AI models on sensed data. The complexity of such processing tasks is data-dependent and has relevant energy cost. This work develops an Age of Information Markovian model for a system where multiple battery-operated devices perform data processing and energy harvesting in parallel. Part of their computational burden is offloaded to an edge server which polls devices at given rate. The structural properties of an optimal policy for a single device-server system are derived. They permit to define a new model-free reinforcement learning method specialized for monotone policies, namely Ordered Q-Learning, providing a fast procedure to learn the optimal policy. The method is oblivious to the devices’ battery capacities, the cost and the value of data batch processing and to the dynamics of the energy harvesting process. Finally, the polling strategy of the server is optimized by combining this policy improvement technique with stochastic approximation methods. Extensive numerical results provide insight into the system properties and demonstrate that the proposed learning algorithms outperform existing baselines.

Microservice-Based Vehicular Network for Seamless and Ultra-Reliable Communications of Connected Vehicles

The fifth-generation (5G) cellular infrastructure is expected to bring about the widespread use of connected vehicles. This technological progress marks the beginning of a new era in vehicular networks, which includes a range of different types and services of self-driving cars and the smooth sharing of information between vehicles. Connected vehicles have also been announced as a main use case of the sixth-generation (6G) cellular, with ultimate requirements beyond the 5G (B5G) and 6G eras. These networks require full coverage, extremely high reliability and availability, very low latency, and significant system adaptability. The significant specifications set for vehicular networks pose considerable design and development challenges. The goals of establishing a latency of 1 millisecond, effectively handling large amounts of data traffic, and facilitating high-speed mobility are of utmost importance. To address these difficulties and meet the demands of upcoming networks, e.g., 6G, it is necessary to improve the performance of vehicle networks by incorporating innovative technology into existing network structures. This work presents significant enhancements to vehicular networks to fulfill the demanding specifications by utilizing state-of-the-art technologies, including distributed edge computing, e.g., mobile edge computing (MEC) and fog computing, software-defined networking (SDN), and microservice. The work provides a novel vehicular network structure based on micro-services architecture that meets the requirements of 6G networks. The required offloading scheme is introduced, and a handover algorithm is presented to provide seamless communication over the network. Moreover, a migration scheme for migrating data between edge servers was developed. The work was evaluated in terms of latency, availability, and reliability. The results outperformed existing traditional approaches, demonstrating the potential of our approach to meet the demanding requirements of next-generation vehicular networks.