In the last few decades, electricity markets around the world have gradually transformed from highly regulated to deregulated and competitive markets. Prior knowledge of electricity demand and price is needed by the generation companies and market operators for getting best return of investment and for maintaining the real-time balance between demand and supply, respectively. Although, the nonlinear and black box structure of the forecasting models based on artificial intelligence techniques have made them popular among the researchers, their inherent limitations posed due to their structure can be overcome by using evolutionary optimization techniques along with them for achieving better forecasting accuracy. The proposed work presents artificial neural network-based short-term electricity price forecasting model. In the presented work, dynamic particle swarm optimization technique is used to adjust the weights of the neural network model to the optimal values. The electricity price of New South Wales electricity market is forecasted using the proposed model in order to verify the performance of the proposed model.
CITATION STYLE
Singh, N., Hussain, S., & Tiwari, S. (2018). A PSO-based ANN model for short-term electricity price forecasting. In Advances in Intelligent Systems and Computing (Vol. 696, pp. 553–563). Springer Verlag. https://doi.org/10.1007/978-981-10-7386-1_47
Mendeley helps you to discover research relevant for your work.