Analysis of Consumer Baseline for Demand Response Implementation: A Case Study

Abstract

Demand response (DR) refers to short term modification in electricity consumption pattern by consumers in terms of time and volume as per utility requirement. Implementation of DR helps utility for effective load management and consumers to avail of monetary and service benefits. The important component in evaluating the success of a DR implementation program is related to the accurate estimation of the consumer baseline load (CBL). A decision about load curtailment volume and incentives offering to the consumers is decided based on the estimation of CBL. A case study is performed for a domestic feeder of 33/11 kV substation of Goa state utility based upon the load and weather data. Different methods of CBL estimation computed based on the historical data and forecasting techniques are analyzed. In this paper, the Artificial Neural Network (ANN) based model is adopted for CBL estimation. From the computation of performance metrics, it is found that the proposed ANN method gives better performance in terms of higher accuracy, improved bias and variability over other estimation methods. The results obtained from ANN-based CBL estimation is used to analyze the impact of the implementation of price and incentive-based DR program on the consumer and state utility.