Optimal Demand Response Using Device-Based Reinforcement Learning

Residential Demand Response Applications Using Batch Reinforcement Learning

—Driven by recent advances in batch Reinforcement Learning (RL), this paper contributes to the application of batch RL to demand response. In contrast to conventional model-based approaches, batch RL techniques do not require a system identification step, which makes them more suitable for a large-scale implementation. This paper extends fitted Q-iteration, a standard batch RL technique, to the...

Optimal Scheduling of CHP-based Microgrid Under Real-Time Demand Response Program

Microgrid (MG) is considered as a feasible solution to integrate the distributed energy sources. In this paper, optimal scheduling of a grid-connected MG is investigated considering different power sources as combined heat and power (CHP) units, only power and heat generating units, and battery storage systems. Two different feasible operating regions are considered for the CHP units. In additi...

Demand Response Based Model for Optimal Decision Making for Distribution Networks

In this paper, a heuristic mathematical model for optimal decision-making of a Distribution Company (DisCo) is proposed that employs demand response (DR) programs in order to participate in a day-ahead market, taking into account elastic and inelastic load models. The proposed model is an extended responsive load modeling that is based on price elasticity and customers’ incentives in which they...

Demand Response by Decentralized Device Control Based on Voltage Level

This paper introduces a distributed, self-organizing approach to load control based on voltage measurement. A local voltage measurement defines a Level of Service (LoS), which is balanced with the neighboring households in order to avoid extreme restrictions of energy use in a single household. The approach distinguishes four criticality classes for devices which suspend themselves at specific ...

Approximately Optimal Approximate Reinforcement Learning