Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control

TL;DR

This paper introduces a reinforcement learning controller with surprise minimization to enhance energy demand response management by leveraging predictability in user behavior, resulting in improved learning speed and efficiency.

Contribution

It presents a novel reinforcement learning architecture incorporating surprise minimization specifically designed for energy demand response applications.

Findings

The architecture improves learning speed in simulations.

Surprise minimization enhances predictability in energy usage control.

The method shows potential for large-scale energy management.

Abstract

Optimizing prices for energy demand response requires a flexible controller with ability to navigate complex environments. We propose a reinforcement learning controller with surprise minimizing modifications in its architecture. We suggest that surprise minimization can be used to improve learning speed, taking advantage of predictability in peoples' energy usage. Our architecture performs well in a simulation of energy demand response. We propose this modification to improve functionality and save in a large scale experiment.