Electric load forecasting becomes one of the most critical factors for the economic operation of power systems due to the rapid increment of daily energy demand in the world. The energy usage of the electricity demand is higher than the other energy sources in Sri Lanka according to the record of Generation Expansion Plan—2016, Ceylon Electricity Board, Sri Lanka. Moreover, forecasting is a hard challenge due to its complex nature of consumption. In this research, the long-term electric load forecasting based on optimized artificial neural networks (OANNs) is implemented using particle swarm optimization (PSO) and results are compared with a regression model. Results are validated using the data collected from Central Bank annual reports for thirteen years from the year 2004–2016. The choice of the inputs for ANN, OANNs, and regression models are given depends on the values obtained through the correlation matrix. The training data sets used in the proposed work are scaled between 0 and 1, and it is obtained by dividing the entire data set by its large value. The experimental results show that OANN has better accuracy in forecasting compared to ANN and regression model. The forecasting accuracy of each model is performed by the mean absolute percentage error (MAPE).
CITATION STYLE
Shyamali Dilhani, M. H. M. R., Wagarachchi, N. M., & Kumara, K. J. C. (2021). Electricity Load Forecasting Using Optimized Artificial Neural Network. In Lecture Notes in Networks and Systems (Vol. 173 LNNS, pp. 665–676). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-33-4305-4_48
Mendeley helps you to discover research relevant for your work.