Shivani Rao
Independent Researcher
India
Abstract
Efficient load balancing is critical for the reliability and stability of modern smart grids, which integrate renewable energy sources and distributed generation. This paper explores the application of neural network-based forecasting models to predict electrical load demand for load balancing in smart grids. A feedforward neural network (FNN) approach is developed and trained using historical load data, weather conditions, and temporal features. The model forecasts short-term load demand to optimize grid resource allocation, minimize power losses, and enhance grid stability. The study evaluates the performance of the neural network model using real-world data and compares it with traditional forecasting methods. Results demonstrate that the neural network model significantly improves forecasting accuracy, leading to better load balancing and operational efficiency. This research highlights the potential of neural network-based forecasting as a pivotal tool in smart grid management.
Keywords
Smart grid, load balancing, neural networks, load forecasting, energy management, power system stability
References
- Taylor, J.W., “Short-term electricity demand forecasting using double seasonal exponential smoothing,” Journal of the Operational Research Society, vol. 54, no. 8, pp. 799–805, 2003.
- Hippert, H.S., Pedreira, C.E., Souza, R.C., “Neural networks for short-term load forecasting: A review and evaluation,” IEEE Transactions on Power Systems, vol. 16, no. 1, pp. 44–55, 2001.
- Zhang, G., Patuwo, B.E., Hu, M.Y., “Forecasting with artificial neural networks: The state of the art,” International Journal of Forecasting, vol. 14, no. 1, pp. 35–62, 1998.
- Khotanzad, A., Bijari, M., “Load forecasting using artificial neural networks,” IEEE Transactions on Power Systems, vol. 8, no. 4, pp. 1392–1398, 1993.
- Hong, T., Fan, S., “Probabilistic electric load forecasting: A tutorial review,” International Journal of Forecasting, vol. 32, no. 3, pp. 914–938, 2016.
