An Intelligent Mechanism for Utility and Active Customers in Demand Response Using Single and Double Q Learning Approach

Abstract

The energy profiles of users in the traditional grid are non-compliant and intractable. However, with the evolution of smart grid, this need is fulfilled by customer-oriented programs known as demand side management (DSM) and demand response (DR). Q learning algorithm employed here so that enhanced benefits of DR made available to customers and retailers or utility. In this paper, various price versus demand functions along with their combinations have been used to tackle varying load profiles and comfort levels of different categories of customers. To represent customer response to incentive-based and price-based DR programs, composite demand functions (CDF) and dynamic price elasticity are put forward to examine user susceptibility to changing hourly price. This will help a retailer or any utility that will work as an agent to learn the customer environment and offer the most suitable price. Their learning capability is determined by principles of single and double q learning to demonstrate the comprehensive demand response (CDR) model that will yield best-suited benefit to users and utility. A study has been conducted by analyzing previous hourly demand and market prices of an area for the day.