Multi-Agent Deep Reinforcement Learning for content caching within the Internet of Vehicles

Review Computer Science, Hardware & Architecture

A comprehensive survey on reinforcement-learning-based computation offloading techniques in Edge Computing Systems

Diego Hortelano et al.

Summary: In recent years, the number of embedded computing devices connected to the Internet has increased exponentially. The concepts of computation offloading and edge computing have emerged to address the increasing complexity and computational demands of applications. The use of Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) techniques has gained momentum in solving the computation offloading problem in edge computing systems.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A survey on computation resource allocation in IoT enabled vehicular edge computing

Naren et al.

Summary: The global vehicle population is rapidly increasing, with a significant portion expected to be electrically driven and connected to vehicular networks in the future. Vehicular edge computing has emerged as a result of rapid advancements in vehicle technology and communications. Existing computation resource allocation schemes involve technologies such as cloud computing, artificial intelligence, blockchain, and require specific network performance characteristics for maximum efficiency.

COMPLEX & INTELLIGENT SYSTEMS (2022)

添加到收藏夹

Review Chemistry, Analytical

Study and Investigation on 5G Technology: A Systematic Review

Ramraj Dangi et al.

Summary: This paper presents the characteristics and advantages of 5G technology as the latest generation of mobile networks, highlighting how businesses can utilize the opportunities brought by 5G.

SENSORS (2022)

添加到收藏夹

Article Telecommunications

Multi-agent reinforcement learning for edge information sharing in vehicular networks

Ruyan Wang et al.

Summary: This paper investigates the design of a comprehensive cooperative policy to guarantee the heterogeneous delay requirements of both Vehicle to Infrastructure (V2I) and Vehicle to Vehicle (V2V) links. It formulates mean delay minimization and maximum individual delay minimization problems to improve the global network performance and ensure fairness for individual users. A multi-agent reinforcement learning framework is used to solve these problems, and a proximal policy optimization approach is proposed. Simulation experiments validate the effectiveness of the proposed approach.

DIGITAL COMMUNICATIONS AND NETWORKS (2022)

添加到收藏夹

Article Computer Science, Information Systems

Resources Sharing in 5G Networks: Learning-Enabled Incentives and Coalitional Games

Li Yu et al.

Summary: This article introduces a method to control high delay in smart systems under battery constraints and cloud resource competition by collaboratively sharing resources among neighboring neighbors. By delving into the learning incentive mechanism between cooperation and competition, a distributed intelligent algorithm is provided for coordinating the overall goal of the cellular system with the individual goals of IoT devices.

IEEE SYSTEMS JOURNAL (2021)

添加到收藏夹

Article Engineering, Civil

Deep Learning Based Caching for Self-Driving Cars in Multi-Access Edge Computing

Anselme Ndikumana et al.

Summary: Self-driving cars will have new interior outlook and spaces for enhanced infotainment services. The choice of infotainment contents depends on passengers' features, and infotainment caching based on deep learning can minimize the delay in retrieving content.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Applying machine learning techniques for caching in next-generation edge networks: A comprehensive survey

Junaid Shuja et al.

Summary: Edge networking is a computing paradigm that aims to bring cloud resources closer to end users to improve responsiveness, with user mobility, preferences, and content popularity being key features. In next generation edge networks, machine learning techniques can be applied to predict content popularity and optimize cache strategies.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Incentive-Driven Deep Reinforcement Learning for Content Caching and D2D Offloading

Huan Zhou et al.

Summary: An Incentive-driven and Deep Q Network (DQN) based Method, named IDQNM, utilizes a reverse auction as an incentive mechanism to motivate nodes to participate in D2D offloading and content caching in order to maximize the CSP's saving cost.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Smart Resource Allocation for Mobile Edge Computing: A Deep Reinforcement Learning Approach

Jiadai Wang et al.

Summary: The development of mobile devices has led to an increase in complex and computation-intensive mobile applications. Mobile Edge Computing (MEC) is a promising solution to the capacity constraints of mobile devices, but it also faces challenges such as high infrastructure costs and pressure on MEC servers. The proposed Deep Reinforcement Learning based Resource Allocation (DRLRA) scheme aims to adaptively allocate resources to improve service times and balance resource usage in changing MEC environments.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING (2021)

添加到收藏夹

Article Computer Science, Information Systems