CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 平行控制
Echo state network-based Q-learning method for optimal battery control of offices combined with renewable energy
Shi, Guang1; Liu, Derong2; Wei, Qinglai1
Source PublicationIET CONTROL THEORY AND APPLICATIONS
2017-04-25
Volume11Issue:7Pages:915-922
SubtypeArticle
AbstractAn echo state network (ESN)-based Q-learning method is developed for optimal energy management of an office, where the solar energy is introduced as the renewable source, and a battery is installed with a control unit. The energy consumption in the office, also considered as the energy demand, is separated into those from sockets, lights and air-conditioners. First, ESNs, well known for their excellent modelling performance for time series, are employed to model the time series of the real-time electricity rate, renewable energy and energy demand as periodic functions. Second, given the periodic models of the electricity rate, renewable energy and energy demand, an ESN-based Q-learning method with the Q-function approximated by an ESN is developed and implemented to determine the optimal charging/discharging/idle strategies for the battery in the office, so that the total cost of electricity from the grid can be reduced. Finally, numerical analysis is conducted to illustrate the performance of the developed method.
KeywordRecurrent Neural Nets Neurocontrollers Learning (Artificial Intelligence) Office Environment Optimal Control Solar Power Energy Consumption Time Series Secondary Cells Energy Management Systems Function Approximation Echo State Network-based Q-learning Method Optimal Battery Control Renewable Energy Optimal Energy Management Solar Energy Energy Consumption Energy Demand Time Series Real-time Electricity Rate Periodic Functions Q-function Optimal Charging Strategy Optimal Discharging Strategy Optimal Idle Strategy Numerical Analysis
WOS HeadingsScience & Technology ; Technology
DOI10.1049/iet-cta.2016.0653
WOS KeywordTIME NONLINEAR-SYSTEMS ; NEURAL-NETWORK ; SPEECH RECOGNITION ; MANAGEMENT-SYSTEM ; PREDICTION ; SCHEME ; SERIES ; MODEL
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61233001 ; 61273140 ; 61374105 ; 61533017 ; U1501251)
WOS Research AreaAutomation & Control Systems ; Engineering ; Instruments & Instrumentation
WOS SubjectAutomation & Control Systems ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS IDWOS:000399568800003
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/13635
Collection复杂系统管理与控制国家重点实验室_平行控制
Affiliation1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
Recommended Citation
GB/T 7714
Shi, Guang,Liu, Derong,Wei, Qinglai. Echo state network-based Q-learning method for optimal battery control of offices combined with renewable energy[J]. IET CONTROL THEORY AND APPLICATIONS,2017,11(7):915-922.
APA Shi, Guang,Liu, Derong,&Wei, Qinglai.(2017).Echo state network-based Q-learning method for optimal battery control of offices combined with renewable energy.IET CONTROL THEORY AND APPLICATIONS,11(7),915-922.
MLA Shi, Guang,et al."Echo state network-based Q-learning method for optimal battery control of offices combined with renewable energy".IET CONTROL THEORY AND APPLICATIONS 11.7(2017):915-922.
Files in This Item: Download All
File Name/Size DocType Version Access License
FinalPaper4_final.pd(3253KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shi, Guang]'s Articles
[Liu, Derong]'s Articles
[Wei, Qinglai]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shi, Guang]'s Articles
[Liu, Derong]'s Articles
[Wei, Qinglai]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shi, Guang]'s Articles
[Liu, Derong]'s Articles
[Wei, Qinglai]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: FinalPaper4_final.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.