|
Reinforcement Learning for Energy-Reducing Start-Up Schemes Authors: K. Marguerite Van Moffaert, Y. De Hauwere, P. Vrancx and A. Nowé Publication Date: Oct. 2012 Pages: 178-185
Abstract: In this paper, we present a learning technique for determining energy-reducing schedules for general devices and equipment. The proposed learning algorithm is based on Fitted-Q Iteration (FQI) and analyzes the usage and the users of a particular device to decide upon the appropriate profile of start-up and shut- down times. We experimentally evaluated our algorithm on a mixture of real-life and simulated data to discover that close-to-optimal control policies can be learned on a short timespan of a only few iterations. Our results show that the algorithm is capable of proposing intelligent schedules that minimize energy consumption and at the same time maximize user satisfaction.
|
