Domain Randomization for Demand Response of an Electric Water Heater
Open Access
- 21 September 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 12 (2) , 1370-1379
Abstract
Thermostatically Controlled Loads (TCLs) provide a source of demand flexibility, and are often considered a good source for Demand Response (DR) applications. Due to their heterogeneity, and as such a lack of dynamics models, Reinforcement Learning (RL) is often used to exploit this flexibility. Unfortunately, RL requires exploratory interaction with the TCL, resulting in a period of potential discomfort for the users. We present an approach to reduce this exploratory time by pretraining the RL-agent. Domain randomization is used to facilitate knowledge transfer. We evaluate the pre-training potential in a DR energy arbitrage scenario with an Electric Water Heater (EWH). Our experiments show that a priori knowledge about EWH dynamics can be used to initialize and improve the control policy. In our experiments, pre-training attributes to 8.8 % additional cost savings, compared to starting from scratch.Keywords
Funding Information
- Flemish Institute for Technological Research (TSG-00362-2020)
This publication has 19 references indexed in Scilit:
- Gigawatt-hour scale savings on a budget of zero: Deep reinforcement learning based optimal control of hot water systemsEnergy, 2018
- Domain randomization for transferring deep neural networks from simulation to the real world2017
- Reinforcement Learning Applied to an Electric Water Heater: From Theory to PracticeIEEE Transactions on Smart Grid, 2016
- Experimental analysis of data-driven control for a building heating systemSustainable Energy, Grids and Networks, 2016
- Residential Demand Response of Thermostatically Controlled Loads Using Batch Reinforcement LearningIEEE Transactions on Smart Grid, 2016
- Grey-box modeling of a low pressure electric boiler for domestic hot water systemApplied Thermal Engineering, 2015
- Representative hot water draw profiles at high temporal resolution for simulating the performance of solar thermal systemsSolar Energy, 2015
- Approximate model-assisted Neural Fitted Q-Iteration2014
- A Smart Domestic Hot Water BufferIEEE Transactions on Smart Grid, 2012
- Random ForestsMachine Learning, 2001