The augmented reality (AR) applications have been widely used in the field of Internet of Things (IoT) because of good immersion experience for users, but their ultralow delay demand and high energy consumption bring a huge challenge to the current communication system and terminal power. The emergence of mobile-edge computing (MEC) provides a good thinking to solve this challenge. In this article, we study an energy-efficient task offloading and resource allocation scheme for AR in both the single-MEC and multi-MEC systems. First, a more specific and detailed AR application model is established as a directed acyclic graph according to its internal functionality. Second, based on this AR model, a joint optimization problem of task offloading and resource allocation is formulated to minimize the energy consumption of each user subject to the latency requirement and the limited resources. The problem is a mixed multiuser competition and cooperation problem, which involves the task offloading decision, uplink/downlink transmission resources allocation, and computing resources allocation of users and MEC server. Since it is an NP-hard problem and the communication environment is dynamic, it is difficult for genetic algorithms or heuristic algorithms to solve. Therefore, we propose an intelligent and efficient resource allocation and task offloading algorithm based on the deep reinforcement learning framework of multiagent deep deterministic policy gradient (MADDPG) in a dynamic communication environment. Finally, simulation results show that the proposed algorithm can greatly reduce the energy consumption of each user terminal.

Energy-Efficient Task Offloading and Resource Allocation via Deep Reinforcement Learning for Augmented Reality in Mobile Edge Networks

With the development of computer technology, computational-intensive and delay-sensitive applications are emerging endlessly, and they are limited by the computing power and battery life of Smart Mobile Devices (SMDs). Mobile edge computing (MEC) is a computation model with great potential to meet application requirements and alleviate burdens on SMDs through computation offloading. However, device mobility and server status variability in the multi-server and multi-task scenario bring challenges to the computation offloading. To cope with these challenges, we first propose a parallel task offloading model and a small area-based edge offloading scheme in MEC. Then, we formulate the optimization problem to minimize the completion time of all tasks, and transform the problem into a deep reinforcement learning-based offloading scheme by Markov decision approach. Furthermore, we present a deep deterministic policy gradient (DDPG) approach for obtaining the offloading strategy. Experimental results demonstrate that the DDPG- based offloading approach improves long-term performance by at least 19% in ultra-low latency, efficient usage of servers, and frequent mobility of SMDs over traditional strategies.

/pdf/ultra-low-latency-multi-task-offloading-in-mobile-edge-3og227fa98.pdf

Ultra-Low Latency Multi-Task Offloading in Mobile Edge Computing

Virtual power plant containing electric vehicles scheduling strategies based on deep reinforcement learning

/pdf/incentive-techniques-for-the-internet-of-things-a-survey-1pku9vrj.pdf

Incentive techniques for the Internet of Things: A survey

With the rapid advancement of the Internet of Vehicles and artificial intelligence (AI) technologies, the cooperative intelligent transportation system (C-ITS) has drawn great attention in recent years. To provide an ultra-reliable, low-latency computation experience of C-ITS, computation offloading is deemed indispensable by working with edge-cloud servers. In this paper, we first investigate a distributed dynamic computation offloading model for multi-access edge computing (MEC) enabled C-ITS under a heterogeneous road network, in which the multiple and heterogeneous computing power sources cooperatively provide computation offloading services for vehicles. Considering the autonomous offloading manner of the vehicles, we formulate the task offloading and computing power allocation as a distributed Stackelberg game, where the MEC servers as the leader to allocate computing resources and manage local energy, and the vehicles as the followers to offload local computation task. Since the observable states in the game is incomplete, the problem of resolving the optimal strategies for each game player is modeled as a partially observable Markov decision process (POMDP) to maximize the long-term cumulative reward. Then we develop a computation offloading algorithm using Stackelberg game-based multi-agent deep deterministic policy gradient (SG-MADDPG), which uses a centralized training and decentralized execution method to learn the optimal computing power allocation and computation offloading policies. Finally, extensive simulations are carried out and show the rationality and effectiveness of the proposed algorithm. 

Distributed Offloading for Cooperative Intelligent Transportation Under Heterogeneous Networks

Mobile crowdsensing (MCS) is an appealing sensing paradigm that leverages the sensing capabilities of smart devices and the inherent mobility of device owners to accomplish sensing tasks with the aim of constructing powerful industrial systems. Incentivizing mobile users (MUs) to participate in sensing activities and contribute high-quality data is of paramount importance to the success of MCS services. In this article, we formulate the competitive interactions between a sensing platform (SP) and MUs as a multistage Stackelberg game with the SP as the leader player and the MUs as the followers. Given the unit prices announced by MUs, the SP calculates the quantity of sensing time to purchase from each MU by solving a convex optimization problem. Then, each follower observes the trading records and iteratively adjusts their pricing strategy in a trial-and-error manner based on a multiagent deep reinforcement learning algorithm. Simulation results demonstrate the efficiency of the proposed method.

Multiagent Actor-Critic Network-Based Incentive Mechanism for Mobile Crowdsensing in Industrial Systems

Vehicular crowdsensing (VCS) is a promising paradigm that utilizes the mobility of vehicles to collect city-scale environmental data for monitoring and management purpose. However, the dramatic growth of traffic load, lack of incentive mechanism, and sensing cost heterogeneity bring considerable challenges in achieving a successful VCS system in the real world. To address these issues, we present an edge-assisted hierarchical VCS framework to achieve efficient vehicle recruitment and data collection. In particular, a Stackelberg game is for-mulated to analyze the interactions between edge servers and vehicles. Then, a deep reinforcement learning-based incentive mechanism is detailed for motivating vehicles to participate in sensing activities and contribute high-quality data. Intensive simulations are conducted to verify the efficiency of the proposed mechanism. Finally, we present several open issues and directions for future research.

Xinxin Yang

Papers

Multiagent Actor-Critic Network-Based Incentive Mechanism for Mobile Crowdsensing in Industrial Systems

Toward Incentive-Compatible Vehicular Crowdsensing: An Edge-Assisted Hierarchical Framework