IJIREM

Abstract

This Paper proposes a data-driven approach for grid loss prediction in power systems. It utilizes a comprehensive dataset with relevant features such as grid load, temperature forecasts, and calendar data. The dataset is pre-processed by handling missing values, normalizing features, and encoding cyclic calendar features. A Long Short-Term Memory (LSTM) recurrent neural network is employed for the prediction model, capturing temporal dependencies and generating forecasts of grid loss two hours ahead. The model is trained using mean absolute error (MAE) as the loss function and optimized through hyperparameter tuning. Evaluation metrics like MAE and root mean squared error (RMSE) assess the model's accuracy. Visualization techniques compare predicted and actual grid loss values. The Paper concludes with analysis, future research suggestions, and highlights the potential of the Prophet data-driven approach for efficient and reliable power distribution.

Keywords

Loss prediction, power loss, LSTM, prophet model

Reference

Electric power transmission and distribution losses, 2018, Accessed: 2020-03-05. Available at https://data.worldbank.org/.
J. Sahlin, R. Eriksson, T. Ali, M. Ghandhari, Transmission line loss prediction based on linear regression and exchange flow modelling, 2017 IEEE Manchester PowerTech, (2017), pp. 1–6.
L. Tian, Q. Wang, A. Cao, Research on SVM line loss rate prediction based on heuristic algorithm, Appl. Mech. Mat. 291–294 (2013) 2164–2168.
P. Nallagownden, T. Hong, Development of a new loss prediction method in a deregulated power market using proportional sharing, 2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Program and Abstracts, (2011).
W. Liu, T. Zeng, T. Jun, L. Guan, B. Li, Research on electric power with development and application of line loss rate forecasting software based on MLRM-GM, Adv. Mat. Res. 977 (2014) 182–185.
S. Appalasamy, H.-S. Gan, O. Jones, N. Moin, C.S. Tan, Transmission loss modelling and analysis with multiple linear regression, in Proceedings of the 20th International Congress on Modelling and Simulation. Adelaide, Australia: MODSIM2013, December 2013.
Y. Ren, X. Zhang, X. Huang, Study on the prediction of line loss rate based on the improved RBF neural network, Adv. Mat. Res. 915–916 (2014) 1292–1295.
F. Xie, B. Zhou, Q. Zhang, L. Jiang, Line loss rate forecasting based on grey model and combination of neural network, Adv. Mat. Res. 621 (2012) 340–343.
S. Bouktif, A. Fiaz, A. Ouni, M. Serhani, Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: comparison with machine learning approaches, Energies 11 (2018) 1636.
R. Agrawal, F. Muchahary, M. Tripathi, Long term load forecasting with hourly predictions based on long-short-term-memory networks, 2018 IEEE Texas Power and Energy Conference (TPEC), 2018, pp. 1–6.
Q. Xiaoyun, K. Xiaoning, Z. Chao, J. Shuai, M. Xiuda, Short-term prediction of wind power based on deep long short-term memory, 2016 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), (2016), pp. 1148–1152.

Cites this article as

[Vasu Sharma, Dr. Satish Saini (2023), Prediction of Power Loss in Grid Using Neural Network, International Journal of Innovative Research in Engineering & Management (IJIREM), Vol-10, Issue-4, Page No-77-85], (ISSN 2347 - 5552). www.ijirem.org