Application of Neural Networks to Power Systems for Electrical Load Forecasting


  • Dr. Mithilesh Singh Department of Electrical and Electronics Engineering, Kruti Institute of Technology and Engineering, (C.S.V.T.U.) Raipur, C.G.India 492001
  • Dr. Shubhrata Gupta National Institute of Technology Raipur, India, 492010


Artificial neural network (ANN),, load forecasting, power system,, power quality.


The artificial neural network system referred as parallel distributed processors conserve the information previously learnt but same time accessible to learning new information. This paper gives a brief indication of artificial neural network and its application in power system for electrical load forecasting which can further be used for enhancement of power quality. The accuracy of load forecasts has a significant effect on economy and control of power system operations for reliable and secure operation of power system. In this paper the accurate and real time data are collected from Chhattisgarh load dispatch centre of western grid of India of year 2018. This data of power flow is simulated using artificial neural network. The purpose of short term forecasting is to satisfy as much as possible, to improve prediction accuracy.


[1] Quan, H. Srinivasan D. ; Khosravi A.” Short-Term Load and Wind Power Forecasting Using Neural Network-Based Prediction Intervals” Volume:25 Issue:2, Page(s):303 – 315, ISSN :2162-237X, Feb. 2014.
[2] Chaouch, M, “Clustering-Based Improvement of Nonparametric Functional Time Series Forecasting: Application to Intra-Day Household-Level Load Curves” Smart Grid, IEEE Transactions , Volume:5 Issue:1, Page(s): 411 – 419, ISSN : 1949-3053, Jan. 2014.
[3] Licciardi G. A. St. Martind 'Hères Dambreville, R. Chanussot, J. Dubost, S., 2015. Spatiotemporal Pattern Recognition and Nonlinear PCA for Global Horizontal Irradiance Forecasting” Geoscience and Remote Sensing Letters ,IEEE 12(2)284 – 288.
[4] Galvan E. ; Gutierrez Alcaraz, G. ; Gonzalez Cabrera, N., 2015 “Two-phase Short-term Scheduling Approach with Intermittent Renewable Energy Resources and Demand Response” Revista IEEE AmericaLatina, 13(1),181 – 187, ISSN :1548-0992.
[5] Quilumba, F. L. Wei-Jen Lee Wang, D.Y., 2014 “Using Smart Meter Data to Improve the Accuracy of Intraday Load Forecasting Considering Customer Behavior Similarities” Smart Grid, IEEE Transactions on 6(2 ), 911 – 918, ISSN: 1949-3053.
[6] Black, J. D. Henson, W.L.W. 2014 Hierarchical Load Hindcasting Using Reanalysis Weather” Smart Grid, IEEE Transactions on 5(1),:447 – 455, ISSN :1949-3053.
[7] Gu C. Dazhi Y. Jirutitijaroen, P. ; Walsh, W.M. 2014. Spatial Load Forecasting With Communication Failure Using Time-Forward Kriging” Power Systems, IEEE Transactions 29(6,) 2875 – 2882..
[8] Lee, K.Y. Park, J. H. 1992. “Short term Load forecasting using an ANN” IEEE Transaction on power system 7(1), 124-132, ISSN 0885-8950.
[9] Chaturvedi, D. K. Mohan,M. Singh, R. K. and Kalra, P. K. 2004. “Improved generalized neuron model for short term load forecasting,” International Journal on Soft Computing–A FFMA, Springer, 8(1)10–18.
[10] Natessan, R., Radman G. 2004. Effects of STATCOM, SSSC and UPFC on voltage stability", IEEE Transaction on Power Systems, 4,546-550.
[11] Dipen A. Mistry, Bhupelly Dheeraj, Ravit Gautam, Manmohan Singh Meena, Suresh Mikkili, “Power Quality Improvement Using PI and Fuzzy Logic Controllers Based Shunt Active Filter “ WASET, International Journal of Electrical, Robotics, Electronics and Communications Engineering Vol:8,pp4-10, 2014.
[12] Jain, A., Choi, J., & Min, J. (2002, October). Power system network observability determination using feedforward neural networks. In Proceedings. International Conference on Power System Technology (Vol. 4, pp. 2086-2090). IEEE.
[13] Islam, B. U. (2011). Comparison of conventional and modern load forecasting techniques based on artificial intelligence and expert systems. International Journal of Computer Science Issues (IJCSI), 8(5), 504-513.
[14] Dopazo, J. F., Dwarakanath, M. H., Li, J. J., & Sasson, A. M. (1977). An external system equivalent model using real-time measurements for system security evaluation. IEEE Transactions on Power Apparatus and Systems, 96(2), 431-446.
[15] Dillon, T. S. (1993). "Artificial neural network applications to power systems and their relationship to symbolic methods", International Journal of Electric Power and energy system, Vol. 2, 1533-1536.
[16] Chaturvedi, D. K., Satsangi, P. S., & Kalra, P. K. (2001). Fuzzified neural network approach for load forecasting. Engineering Intelligent Systems, 9(1), 3-9.
[17] El Desouky, A. A., & El Kateb, M. M. (2000). Hybrid adaptive techniques for electric-load forecast using ANN and ARIMA. IEE Proceedings-Generation, Transmission and Distribution, 147(4), 213-217.
[18] Manchanda, P., Kumar, J., & Siddiqi, A. H. (2007). Mathematical methods for modelling price fluctuations of financial times series. Journal of the Franklin Institute, 344(5), 613-636.
[19] Kumar, P. and Mahajan, A. 2009. Soft Computing Technics for the control of an Active Power Filter, IEEE Transaction on Power Delivery, 24 (1-5).
[20] Mishra, D. K. Dwivedi AK D. 2012. Efficient journal of latest algorithm for load forecasting in electrical power system” International journal of latest research in science & technology, 3, 6-11, ISSN 2278-5299.
[21] Hingorani, N.G. and Gyugyi, Understandind L. FACTS, concepts and technology of flexible AC Transmission, IEEE Press 2000, New York.




How to Cite

Singh, D. M., & Gupta, D. S. (2020). Application of Neural Networks to Power Systems for Electrical Load Forecasting. CSVTU Research Journal, 8(2), 152–159. Retrieved from