001 Cooperative Dynamic Voltage Scaling and Radio Resource Allocation for Energy-Efficient Multiuser Mobile Edge Computing
This article investigates cooperative dynamic voltage regulation and wireless resource allocation in multi-user mobile edge computing for energy efficient computation offloading. The article proposes a suboptimal algorithm based on Lagrangian pairwise decomposition to minimize the weighted sum of mobile energy consumption by jointly optimizing the computational speed of smart mobile devices, subcarrier allocation, transmit power of each subcarrier, data size sent per subcarrier, and offloading ratio. Simulation results show that the algorithm converges quickly and can significantly reduce energy consumption. In addition, the paper finds that the total mobile energy consumption remains stable or increases with the variance of the delay requirement for a given delay mean, which can guide the access control in practice.
002 Energy-Efficient Resource Allocation for Mobile-Edge Computation Offloading
The article investigates the resource allocation of multi-user mobile edge computing offload (MECO) systems based on time division multiple access (TDMA) and orthogonal frequency division multiple access (OFDMA). The article first investigates TDMA MECO systems with infinite or finite cloud computing capabilities and formulates the optimal resource allocation problem as a convex optimization problem. Then, the authors consider OFDMA MECO systems and formulate the optimal resource allocation problem as a mixed integer problem. By converting the OFDMA problem into its TDMA counterpart, the authors propose a low-complexity suboptimal algorithm and show near-optimal performance in simulations. In summary, this paper investigates the energy efficient resource allocation problem for mobile edge computing offload and proposes corresponding optimal and suboptimal algorithms.
003 Game and Contract Theory-Based Energy Transaction Management for Internet of Electric Vehicle
This is a research paper on game and contract theory based power transaction management in smart grid systems. The article proposes a three-tier bi-directional electric energy trading management strategy, including an energy grid as an energy supplier, an energy aggregator as an energy distributor, and an electric vehicle as an energy provider. The article uses a Stackelberg game to solve the optimal pricing and electric vehicle discharging problems, and proposes an incentive mechanism based on contract theory to motivate electric vehicles to participate in energy trading and optimize the utility of energy aggregators. Simulation results show that the proposed scheme performs significantly better than other existing schemes in various scenarios.
004 Joint Offloading and Computing Optimization in Wireless Powered Mobile-Edge Computing Systems
In this paper, the study the problem of joint offloading and computational optimization in wireless mobile edge computing systems. The paper considers a wirelessly powered multi-user MEC system consisting of multiple antenna access points (APs) and multiple users, where the APs (integrated MEC servers) transmit energy via radio waves to charge multiple users, and each user node relies on the collected energy to perform latency-sensitive computational tasks. Through the MEC, these users can perform their respective tasks locally by themselves or offload all or part of them to the AP according to the time division multiple access (TDMA) protocol.In this case, this study optimizes the MEC-WPT system by jointly optimizing the transmitted energy beamformer of the AP, the central processing unit (CPU) frequency and offload bits of each user, and the time allocation between different users design to pursue energy efficiency. Specifically, this study minimizes the energy consumption of the access point in a given time block under the computational delay and energy harvesting constraints for each user. By transforming this problem into a convex framework and using the Lagrangian dual method, an optimal solution in semi-closed form is obtained in this paper. Numerical results show that the proposed joint design outperforms other benchmark solutions in terms of achieving energy efficiency.
005 Learning Based Energy Efficient Task Offloading for Vehicular Collaborative Edge Computing
This paper is a paper on Vehicular Collaborative Edge Computing (VCEC). The article proposes an energy efficient task offloading approach based on learning, which aims to reduce energy consumption within the VCEC system by maximizing the use of idle and redundant resources of vehicles. The authors apply Lyapunov optimization to decompose the original problem into three subproblems and solve them one by one by addressing the challenges of short-term decision and long-term queueing delay constraints, information uncertainty, and task offloading conflicts. These three subproblems are 1) short-term task unloading decision, 2) long-term queueing delay constraint, and 3) information uncertainty and task unloading conflict. The results of extensive numerical simulations show that the method outperforms the benchmark method in terms of energy consumption, learning regret, task backlog and end-to-end delay.
006 Mobile Edge Computing-Enabled Internet of Vehicles: Toward Energy-Efficient Scheduling
This article discusses the construction of green cities in modern transportation systems. The article points out that although modern transportation systems facilitate the daily life of citizens, increasing energy consumption and air pollution pose challenges to the construction of green cities. Currently, research on green IoVs has focused on battery-backed RSUs or energy management of electric vehicles. However, the computational tasks and load balancing among RSUs have not been fully studied. To meet the heterogeneous requirements of communication, computation and storage in IoV, this paper constructs an energy-efficient scheduling framework for minimizing the energy consumption of RSUs in MEC-supported IoV. Specifically, the paper proposes a heuristic algorithm to achieve this by jointly considering task scheduling among MEC servers and the downlink energy consumption of RSUs. To the best of our knowledge, this is the first work to focus on the problem of energy consumption control of MEC-enabled RSUs. The performance evaluation shows that the framework is effective in terms of energy consumption, latency and task blocking possibilities. Finally, the paper details some of the main challenges and open issues and identifies future research directions including renewable energy recharge, sustainable and reliable MEC, incentive and trusted offloading, and deep learning-based scheduling.
007 Multi-User Multi-Task Computation Offloading in Green Mobile Edge Cloud Computing
This article discusses multi-user multi-task computation offloading in green mobile edge cloud computing. The article proposes a multi-user multi-task computation offloading framework that takes into account the dynamics of energy in the mobile edge cloud and the dynamics of tasks in different mobile devices. The article also proposes a centralized and distributed greedy maximum scheduling algorithm and discusses the performance bounds of the proposed scheme. Simulation results show that the proposed scheduling algorithm provides an average system utility improvement of 18.8% to 31.9% over the random scheduling scheme.
008 Weighted Energy-Efficiency Maximization for a UAV-Assisted Multiplatoon Mobile-Edge Computing System
This article investigates a UAV-assisted multi-fleet mobile edge computing system that aims to maximize the weighted global energy efficiency of the system. The article designs a fleet controller based on a 2-D path-tracking model and the Frenet framework, and simulates the coupling characteristics of air-to-ground communication and on-board computing. Due to the non-convexity of the objective function and constraints of the optimization problem, the article proposes an optimization algorithm based on sequential quadratic programming (SQP) method. Simulation results show that the proposed method significantly outperforms the conventional scheme. This paper provides new ideas and methods to improve the energy efficiency of the system by studying the UAV-assisted multi-fleet mobile edge computing system.
009 Fast Adaptive Task Offloading in Edge Computing Based on Meta Reinforcement Learning
This article presents a fast adaptive task offloading method based on meta-reinforcement learning for solving the task offloading problem in multi-access edge computing (MEC). The article first introduces the background of MEC and the challenges of the task offloading problem. Then, the article proposes a meta-reinforcement learning-based task offloading method that can quickly adapt to new environments with a small number of gradient updates and samples. The article models the mobile application as a directed acyclic graph (DAG) and uses a custom sequence-to-sequence (seq2seq) neural network to model the offloading strategy. To effectively train the seq2seq network, the article proposes a method that combines first-order approximations and truncated alternative targets. Experimental results show that the method is able to reduce the latency by up to 25% compared to three benchmark algorithms, while being able to quickly adapt to new environments. In conclusion, this article proposes a fast adaptive task offloading method based on meta-reinforcement learning that can effectively solve the task offloading problem in MEC.
010 Meta Reinforcement Learning for Multi-task Offloading in Vehicular Edge Computing
This paper investigates the problem of multitask offloading in vehicular edge computing. Due to the highly dynamic nature of the vehicle environment and the heterogeneous characteristics of vehicle services, traditional expert-based or learning-based strategies require updating manual parameters or retraining learning models, which leads to intolerable overhead. Therefore, in this paper, a Seq2seq-based meta-reinforcement learning algorithm is proposed for solving the multitask offloading problem. Specifically, a bidirectional gated cyclic unit integrated attention mechanism is designed to determine unloading actions by encoding sequential unloading actions and displaying different preferences for input sequences. In particular, a meta-reinforcement learning framework is designed based on a model agnostic meta-learning framework that trains meta-strategies offline and quickly adapts to new multitask offloading scenarios within a few training steps. Finally, this paper evaluates the performance based on the task generator DAGGEN and real vehicle trajectories, and the results show that SMRL-MTO reduces the task execution time by 11.36% on average compared to the greedy algorithm.