Learning-based Green Workload Placement for Energy Internet in Smart Cities

doi:10.35833/MPCE.2020.000271

Home > Archive>Volume 10, Issue 1, 2022 >91-99. DOI:10.35833/MPCE.2020.000271

PDF HTML Export

Learning-based Green Workload Placement for Energy Internet in Smart Cities

DOI:

10.35833/MPCE.2020.000271

Author:

Qihua Zhou ^¹
Qihua Zhou
School of Automation and School of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
Yanfei Sun ^¹
Yanfei Sun
School of Automation and School of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
Haodong Lu ^²
Haodong Lu
School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
Kun Wang ^³
Kun Wang
Department of Electrical and Computer Engineering, University of California, Los Angeles, USA
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

Affiliation:

1.School of Automation and School of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China;2.School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China;3.Department of Electrical and Computer Engineering, University of California, Los Angeles, USA

Fund Project:

This work was supported by the National Natural Science Foundation of China (No. 61772286), the Jiangsu Key Research and Development Program (No. BE2019742), and the Natural Science Foundation of Jiangsu Province of China (No. BK20191381).

Article

Figures

Metrics

Reference

Cited by

Materials

Abstract:

The Energy Internet is a fundamental infrastructure for deploying green city applications, where energy saving and job acceleration are two critical issues to address. In contrast to existing approaches that focus on static metrics with the assumption of complete prior knowledge of resource information, both application-level properties and energy-level requirements are realized in this paper by jointly considering energy saving and job acceleration during job runtime. Considering the online environment of smart city applications, the main objective is transferred as an optimization problem with a model partition and function assignment. To minimize the energy cost and job completion time together, a green workload placement approach is proposed by using the multi-action deep reinforcement learning method. Evaluations with real-world applications demonstrate the superiority of this method over state-of-the-art methods.

Key words:Energy saving ; workload scheduling ; Energy Internet ; green city

Get Citation

Copy

Article Metrics

Abstract:
PDF:
HTML:
Cited by:

History

Received:April 29,2020
Revised:August 10,2020
Adopted:
Online: January 28,2022
Published:

Home

Introduction

Editorial Board

For Author

Call For Papers

APC

Sponsor & Publisher

Get Citation

Share

Article Metrics

History