Development Of Online Demand Response Framework For Smart Grid Infrastructure Toward Social Welfare

Due to continuous growth in the demand for electricity with unmatched generation and transmission capacity expansion, the resource management and rescheduling of load without affecting the welfare of the market participants are the major concerns of the power market. As the demand changes continuously, the peak load consumers are unaware of the bidding cost and penalty. The Artificial Neural Network (ANN) based online Demand Response (DR) connectivity scheme is proposed for the smart power networks to obtain the equilibrium demand. The optimally rescheduled load, percentage increase of peak load, and time are considered the ANN input. Bidding cost and penalty of the peak load consumer are considered as the output. The data required to develop the ANN are generated using the Genetic Algorithm (GA) to maximize social welfare as the objective. The optimum load curtailment is taken as the decision variable. In this proposed method, the Curtailment Index (CI) is calculated and incorporated to utilize DR connectivity properly. This adopted method is tested with IEEE 30 bus system, and the GA results for CI and bidding cost have been compared with Particle Swarm Optimization (PSO) methodology. The ANN predicted bidding cost results are compared with GA optimized bidding cost. The result shows the accuracy of ANN for online DR techniques with minimum testing Mean Square Error (MSE) value of 1.72 x 10(-3) and the training period of 45.98 seconds.