Direct Load Control of Thermostatically Controlled Loads Based on Sparse Observations Using Deep Reinforcement Learning

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

作者机构：Department of Electrical EngineeringKU Leuven/EnergyVille3001 LeuvenBelgium REstoreCentrica2600 AntwerpBelgium AI-labVrije Universiteit Brussel1050 BrusselsBelgium Vito/EnergyVille2600 MolBelgium 

出 版 物：《CSEE Journal of Power and Energy Systems》 (中国电机工程学会电力与能源系统学报（英文）)

年 卷 期：2019年第5卷第4期

页      面：423-432页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Convolutional networks deep reinforcement learning long short-term memory residential demand response 

摘      要：This paper considers a demand response agent that must find a near-optimal sequence of decisions based on sparse observations of its *** a relevant set of features from these observations is a challenging task and may require substantial domain *** 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 *** 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 *** 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.