Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning

Frederik Ruelens; Bert J. Claessens; Peter Vrancx; Fred Spiessens; Geert Deconinck

doi:10.17775/CSEEJPES.2019.00590

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning

Regular Papers | 更新时间：2025-12-29

- Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning
- Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning
- 中国电机工程学会电力与能源系统学报(英文) 2019年5卷第4期页码：423-432
- 作者机构：
  
  1. Department of Electrical Engineering, KU Leuven, Leuven,Belgium
  2. REstore, Centrica, Antwerp,Belgium
  3. lab, Vrije Universiteit Brussel, Brussels,AI,Belgium
  4. Vito/EnergyVille, Mol,Belgium
- 作者简介：
- 基金信息：
- DOI：10.17775/CSEEJPES.2019.00590
  中图分类号：
- 纸质出版：2019
- 稿件说明：
移动端阅览
Frederik Ruelens, Bert J. Claessens, Peter Vrancx, 等. Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning[J]. 中国电机工程学会电力与能源系统学报(英文), 2019,5(4):423-432.

Frederik Ruelens, Bert J. Claessens, Peter Vrancx, et al. Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning[J]. CSEE Journal of Power and Energy Systems, 2019, 5(4): 423-432.
Frederik Ruelens, Bert J. Claessens, Peter Vrancx, 等. Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning[J]. 中国电机工程学会电力与能源系统学报(英文), 2019,5(4):423-432. DOI： 10.17775/CSEEJPES.2019.00590.

Frederik Ruelens, Bert J. Claessens, Peter Vrancx, et al. Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning[J]. CSEE Journal of Power and Energy Systems, 2019, 5(4): 423-432. DOI： 10.17775/CSEEJPES.2019.00590.

摘要

Abstract

This paper considers a demand response agent that must find a near-optimal sequence of decisions based on sparse observations of its environment. Extracting a relevant set of features from these observations is a challenging task and may require substantial domain knowledge. One way to tackle this problem is to store sequences of past observations and actions in the state vector

making it high dimensional

and apply techniques from deep learning. This paper investigates the capabilities of different deep learning techniques

such as convolutional neural networks and recurrent neural networks

to extract relevant features for finding near-optimal policies for a residential heating system and electric water heater that are hindered by sparse observations. Our simulation results indicate that in this specific scenario

feeding sequences of time-series to an Long Short-Term Memory (LSTM) network

which is a specific type of recurrent neural network

achieved a higher performance than stacking these time-series in the input of a convolutional neural network or deep neural network.

关键词

Keywords

references

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Neural Network Based Fea sible Region Approximation Model for Optimal Operation of Integrated Electricity and Heating System

Stochastic Accelerated Alternating Direction Method of Multipliers for Hedging Communication Noise in Combined Heat and Power Dispatch

State estimation approach for combined heat and electric networks

Review of learning-assisted power system optimization

Dispatch model for integrated heat and power systems considering internal composition of CHP plants