关键词： Mobile edge computing   Wireless power transfer   Green energy   Resource management   Deep reinforcement learning  

摘要： Recently, the integration of mobile edge computing (MEC) and wireless power transfer (WPT) technologies presents a transformative approach to overcoming the energy limitations of wireless devices (WDs), thereby enhancing both the sustainability and operational efficiency of mobile networks. This paper introduces a novel green-prioritized hybrid energy supply system that harnesses both renewable and grid energy, which aims at optimizing energy use and computational power in mobile networks under dynamic conditions. Specifically, we formulate a long-term average grid energy minimization problem (LAGEMP) to reduce grid energy consumption while maintaining robust and efficient network operations. To solve the complex and dynamic LAGEMP, we propose an action space reduction scheme and an enhanced deep deterministic policy gradient (EDDPG) algorithm, which incorporates the cross-entropy method (CEM). These introduced enhanced approaches not only reduce the computational load but also expedite the convergence of network training, thereby optimizing both energy usage and task offloading strategies. Simulation results reveal that the EDDPG algorithm significantly outperforms existing strategies and algorithms, and achieves near-optimal task offloading efficiency with reduced grid energy.

关键词： Mobile Edge Computing   Task offloading   Task size prediction   Deep reinforcement learning  

摘要： Mobile Edge Computing (MEC) has been identified as an innovative paradigm to improve the performance and efficiency of mobile applications by offloading computation-intensive tasks to nearby edge servers. However, the effective implementation of task offloading in MEC systems faces challenges due to uncertainty, heterogeneity, and dynamicity. Deep Reinforcement Learning (DRL) provides a powerful approach for devising optimal task offloading policies in complex and uncertain environments. This paper presents a DRL-based task offloading approach using Deep Deterministic Policy Gradient (DDPG) and Distributed Distributional Deep Deterministic Policy Gradient (D4PG) algorithms. The proposed solution establishes a distributed system, where multiple mobile devices act as Reinforcement Learning (RL) agents to optimize their individual performance. To reduce the computational complexity of the neural networks, Gated Recurrent Units (GRU) are used instead of Long Short-Term Memory (LSTM) units to predict the load of edge nodes within the observed state. In addition, a GRU-based sequencing model is introduced to estimate task sizes in specific scenarios where these sizes are unknown. Finally, a novel scheduling algorithm is proposed that outperforms commonly used approaches by leveraging the estimated task sizes to achieve superior performance. Comprehensive simulations were conducted to evaluate the efficacy of the proposed approach, benchmarking it against multiple baseline and state-of-the-art algorithms. Results show significant improvements in terms of average processing delay and task drop rates, thereby confirming the success of the proposed approach.

关键词： Mobile edge computing   Resource pricing   Stackelberg game   Task offloading  

摘要： With the rapid advancement of fifth-generation communication technologies, the data produced by the Internet of Everything is growing exponentially. As mobile cloud computing struggles to keep up with the demands for massive data processing and low latency, mobile edge computing (MEC) has emerged as a solution. By shifting services from centralized cloud platforms to edge servers located closer to data sources, MEC achieves reduced latency, enhanced computing efficiency, and an improved user experience. This paper introduces a task offloading algorithm designed for a multi-base station cooperative mobile edge environment, addressing the challenges of task offloading and resource pricing. The system architecture includes a macro base station and several micro base stations, strategically deployed in a densely populated mobile device area. Each mobile device serves as an autonomous decision-making unit, offloading tasks to an optimal base station. We model the interactions between base stations and end-users using a Stackelberg game approach, with strategy optimization achieved through a multi-agent deep deterministic policy gradient algorithm. The proposed TO-SG-MADDPG algorithm intelligently coordinates the policies of multiple base stations and end-users by centralized training and distributed execution, resulting in globally optimal task offloading and resource pricing. The results demonstrate that the proposed algorithm not only reduces the task loss rate but also safeguards the interests of all stakeholders.

关键词： blockchain technology   clouded leopard optimization   conditional self-attention generative adversarial network   fair proof-of-reputation   Internet of Vehicles   mobile edge computing  

摘要： The Internet of Vehicles (IoV) heralds a paradigm shift in vehicular communication by enhancing traffic efficiency, safety, and overall driving experiences through interconnectivity. However, real-world IoV systems often face significant challenges. High computational demands for processing real-time data in autonomous vehicles lead to rapid energy depletion, whereas vulnerabilities in communication networks can expose systems to cyberattacks. Although mobile edge computing (MEC) alleviates some of the issues by relocating computational resources closer to vehicles, it introduces critical hurdles. Frequent handovers due to high vehicle mobility result in service discontinuity and dynamic environments with dense vehicular networks complicate resource management and scalability. To tackle this, a blockchain-based multiobjective secure task offloading strategy utilizing an optimized conditional self-attention generative adversarial network (CSAGAN) enhanced by clouded leopard optimization (CLOA) is proposed (BMOSTO-CSAGAN-MEC-IoV). The self-attention mechanism of CSAGAN and the exploration-exploitation balance of CLOA prevent premature convergence by maintaining diverse search space, leading to optimized task scheduling. The model leverages fair proof of reputation (FPoR) for secure, decentralized task offloading ensuring data integrity and reliability. The proposed method attains 24.8% lower energy consumption, 26.2% lower latency, and 22.5% lower cost compared to existing methods when evaluated using IoV-synthetic dataset. These results demonstrate the model's effectiveness in enhancing IoV-MEC system performance.

关键词： 5G edge-cloud continuum   mobile edge computing   probabilistic spiking neural network   tactical unit algorithm   task offloading  

摘要： In order to maximize resource usage, minimize latency, and enhance energy efficiency in Mobile Edge Computing (MEC), task offloading is crucial in the 5G Edge-Cloud Continuum. Traditional methods suffer from high computational complexity and static decision-making, leading to inefficiencies. This work proposes a Probabilistic Spiking Neural Network with Tactical Unit Algorithm (PSNN-TUA) for adaptive, low-power task offloading. The system operates across three tiers: Device Layer, MEC Layer, and Cloud Layer, categorizing tasks as delay-sensitive, energy-sensitive, or latency-insensitive. Execution is modeled using Alpha-Beta-Gamma (ABG) path loss and OFDMA-based transmission. The PSNN-based decision model represents UEs, MEC servers, and cloud servers as spiking neurons, using spike probabilities to allocate offloading tasks according to network conditions and resource availability. The decision-making process based on membrane potentials facilitates appropriate work allocation and enhances computing efficiency. The TUA executes three operational stages namely Searchers Action followed by Executors Action then finishes with Assessors Combat Assessment to find optimal PSNN hyperparameters. The experimental data shows PSNN-TUA delivers superior performance compared to other methods by reaching 98.5% MEC availability with 12.3 ms latency and 0.75 J/task energy efficiency alongside 97.2% task completion and 0.9% packet loss and 1.3% failure rate which demonstrates its effectiveness for 5G MEC environments.

关键词： Internet of things   Mobile edge computing   Neural networks   Reinforcement learning   Resource allocation  

摘要： In the era of rapid technological advancement, Mobile Edge Computing (MEC) has become essential for supporting latency-sensitive applications such as internet of things, autonomous driving, and smart cities. However, efficient resource allocation remains a challenge due to the dynamic nature of MEC environments. The primary difficulties stem from fluctuating workloads, varying network conditions, and heterogeneous computational capabilities, which make real-time task offloading and resource management complex. Traditional centralized approaches suffer from high computational overhead and poor scalability, while conventional machine learning-based methods often require extensive labeled data and fail to adapt quickly in dynamic settings. To address these issues, this study proposes an advanced Multi-Agent Reinforcement Learning (MARL) framework combined with a lightweight neural network, LtNet, to optimize task offloading and resource management in MEC. MARL enables decentralized decision-making, allowing each device to learn optimal offloading strategies and adapt dynamically. Compared to prior single-agent or heuristic methods, our approach improves scalability and efficiency while reducing computational complexity. LtNet further enhances performance using H-Swish activation and selective Squeeze-and-Excitation modules, ensuring lower computational overhead. Experimental results demonstrate that the proposed methods achieve a 12-22% reduction in task completion time, a 5-8% decrease in energy consumption, and consistently high resource utilization, making them highly effective in managing dynamic MEC environments.

关键词： Time complexity   Streaming media   Heuristic algorithms   Data models   Training   Servers   Robustness   Prediction algorithms   Data mining   Capacity planning   Mobile edge computing   replacement algorithm   analytical model   performance evaluation  

摘要： This paper proposes a replacement algorithm for file caching in mobile edge computing (MEC) networks. While there are numerous schemes for file replacement, it remains a challenge to achieve good, robust, and predictable performance simultaneously. To address this challenge, we introduce a general scheme called Incremental Least-Recently-Used (iLRU), which builds on the classic Least-Recently-Used (LRU) algorithm. iLRU initially caches only a "portion" of the file upon the first request and incrementally caches more when there are more requests for the file. In this regard, the request frequency can be inferred from the cached size without incurring additional overhead, where a larger cached size represents a higher request frequency. We derive the theoretical hit ratio of iLRU based on the Time-to-Live (TTL) analysis. With the Time-to-Live (TTL) analysis, we can theoretically derive the hit ratio and properties of iLRU and notably show that iLRU allocates more cache space to popular files, resulting in a higher hit ratio than LRU. Simulation results demonstrate the superior performance of iLRU and validate the accuracy of the theoretical hit ratio. Furthermore, we conduct simulations over various real-world traces to show that iLRU outperforms existing schemes across various real-world traces, defenestrating the robustness of iLRU.

关键词： Mobile edge computing   Location prediction   5G   Computation offloading   Transformer   Dueling DQN   Double DQN   TOPSIS  

摘要： Mobile edge computing (MEC) brings the power of cloud computing closer to where users are, enhancing network performance and improving user experience. However, as users move around and individual edge servers cover only limited areas, there is a need for intelligent service assignment to keep up with user demands and low turn around time (TAT) requirements. This paper introduces TMLpSA, a synergistic framework that combines advanced user mobility prediction and decision-making techniques to optimize service assignments in a periodic fashion. By leveraging a Transformer model to anticipate where users will go next, and integrating a DRL-based TOPSIS technique, TMLpSA predicts user trajectories and proactively identifies the most suitable edge servers to assign services along their anticipated paths. Simulation results highlight how TMLpSA minimizes average application TAT significantly by 23.32%, while not only reducing offload energy consumption but also improving task completion rate and resource utilization with reasonable service migration frequency relative to the second best benchmark approach.

关键词： Mobile edge computing   Task offloading   Improved Particle swarm algorithm   Chemical reaction optimization algorithm  

摘要： The advent of mobile edge computing has given rise to a pressing concern: the optimal methodology for offloading edge computing tasks. Edge computing provides computing and storage capabilities at the edge of the network, in close proximity to the user. Through process of computation offloading, tasks that would otherwise be performed by the terminal are migrated to edge servers for execution, this has potential to significantly reduce application latency and conserve terminal energy consumption. Nevertheless, the majority of current significant research on task offloading for mobile edge environments focuses on the latency or energy consumption of a single mobile terminal. Accordingly, a hybrid heuristic task offloading algorithm based on integer coding is put forth for edge computing environments comprising multiple edge servers and multiple mobile terminals. The completion time of the task and the weighted calculation of energy consumption of the terminal were used as evaluation indexes. Based on the concepts of individual historical optimization and global optimization of the Improved Particle Swarm Optimization(IPSO) algorithm, four chemical molecular operations simulated by chemical reaction optimization (CRO) algorithm were introduced, so that molecules could be continuously optimized in the process of chemical reaction. The results of comparative simulation experiments demonstrate that compared with classical algorithms such as the IPSO algorithm, CRO algorithm and newer algorithms, IPSO_CRO algorithm can obtain better unloading decisions, and the optimization of objective function values, namely energy consumption and delay, is significantly better than other algorithms.

关键词： Servers   Collaboration   Vehicle dynamics   Dynamic scheduling   Optimization   Edge computing   Mobile computing   Resource management   Computational modeling   Real-time systems   Mobile edge computing   vehicle assisted   service caching   task offloading   multi-objective optimization  

摘要： The development of artificial intelligence (AI) enables vehicular edge computing (VEC) servers to be able to provide more intelligent services. However, the limited storage resources of VEC servers constrain the deployment of intelligent service contents, which greatly restricts the intelligence level of the VEC network. To resolve this problem, we first design a novel vehicle-assisted VEC network architecture and further propose VaCo, a Vehicle-assisted Collaborative caching system. VaCo allows VEC servers to download the cached service content from any vehicle in the VEC network to support task offloading. VaCo mainly considers the real-time scheduling problem of vehicle storage resources under the dynamic VEC network and the benefit problem caused by invoking vehicle resources under the highly dynamic load environment. VaCo models the vehicle storage resources as an independent resource pool and deploys a cross-VEC server content retrieval mechanism to achieve unified and efficient management of the storage resources of the vehicle cluster and the VEC server cluster. Then, we propose a multi-swarm collaborative optimization scheme to jointly optimize the service failure rate and cost, and further propose a Pareto-based optimization scheme to ensuring that VaCo can correctly evaluate the benefits of invoking vehicle resources in a dynamic VEC network. Finally, we implement VaCo and conduct extensive evaluations on real-world dataset. The experimental results on the real trajectory dataset show that VaCo can effectively utilize vehicle resources and ensure the benefits of both vehicles and VEC servers simultaneously.