Snake swarm optimization-based deep reinforcement learning for resource allocation in edge computing environment

S. Kaliraj, V. Sivakumar, N. Premkumar, S. Vatchala

Research output: Contribution to journalArticlepeer-review

Abstract

Mobile edge computing has become popular in the past few years as a means of creating computing resources close to end-user nodes at the network edge. Nodes—end users—demand work offloading to improve service utilization. Furthermore, when the number of users in mobile edge computing increases, the minimal resources deployed at the edge become a problem. Develop the idea of reinforcement learning using a metaheuristic technique intended to achieve effective resource allocation and resolve offloading issues to handle this issue. The ideal way to manage the implementation of mobile edge computing with a cognitive agent's help is to request compensation for all client necessities. To complete the infrastructure type for the Internet of Things (IoT), the operator information is combined with its distinctive methodology. Neural caching during task execution is provided by reinforcement learning based on snake swarm optimization (SSO). Neural caching during task execution is provided by reinforcement learning based on SSO. In the process of creating the cost mapping table and incentive factor-based optimal resource allocation, this suggested method is applied to a contract with effective resource allocation among the end manipulators. Using performance metrics like delivery ratio, energy consumption, throughput, and delay, the suggested approach is put into practice and examined. It is also contrasted with traditional methods like Gray Wolf Optimization (GWO) ant colony optimization (ACO) and genetic algorithms (GA).

Original languageEnglish
Article numbere8130
JournalConcurrency and Computation: Practice and Experience
Volume36
Issue number18
DOIs
Publication statusPublished - 15-08-2024

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Computer Science Applications
  • Computer Networks and Communications
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Snake swarm optimization-based deep reinforcement learning for resource allocation in edge computing environment'. Together they form a unique fingerprint.

Cite this