ELECTRONICS & ELECTRICAL DOMAIN
Published April 28, 2026 | Version v1
Journal article Open

Intelligent Load Forecasting and Enhanced Reliability and Sustainability in Smart Grid Systems Using Smart Meter

Authors/Creators

Description

As global energy demand escalates due to the proliferation of electric vehicles and smart infrastructure, the necessity for optimal grid scheduling becomes paramount. The stochastic nature of electricity consumption complicates the synchronization of generation and demand. This paper proposes a four-step predictive framework comprising data collection, feature extraction, characteristic analysis, and final application to improve power generation utilization. Accurate load forecasting is established as the primary mechanism for ensuring safe, reliable, and cost-effective grid operations.

Files

Intelligent Load Forecasting and Enhanced Reliability -HBRP Publication.pdf

Files (164.2 kB)

Additional details

References

  • 1. Zhao, B., et al. (2020). Collaborative control of thermostatically controlled appliances for balancing renewable generation in smart grid. IEEJ Transactions on Electrical and Electronic Engineering.
  • 2. Berk, K., et al. (2018). Probabilistic forecasting of industrial electricity load with regime switching behaviour. International Journal of Forecasting.
  • 3. Cancelo, J. R., et al. (2008). Forecasting the electricity load from one day to one week ahead. International Journal of Forecasting.
  • 4. Djukanovic, M., et al. (1995). A neural network-based short-term load forecasting using moving window procedure. International Journal of Electrical Power & Energy Systems.
  • 5. Soares, L. J., & Medeiros, M. C. (2008). Modelling and forecasting short-term electricity load. International Journal of Forecasting.
  • 6. Hu, R., et al. (2017). A short-term power load forecasting model based on the GRNN. Neurocomputing.
  • 7. Kavousi-Fard, A., et al. (2014). A new hybrid modified firefly algorithm and SVR model. Expert Systems with Applications.
  • 8. Osman, Z. H., et al. (2009). Neural network-based approach for short-term load forecasting. In Proceedings of IEEE/PES.
  • 9. Zeng, N., et al. (2017). A switching delayed PSO optimized extreme learning machine. Neurocomputing.