Prediction of Transmission Losses Allocation using Artificial Neural Network and Z-Bus Tracing

• Published in: 2024 IEEE 4th International Conference in Power Engineering Applications: Powering the Future: Innovations for Sustainable Development, ICPEA 2024
• Main Author: Hamid Z.A.; James V.A.; Musirin I.; Salim N.A.
• Format: Conference paper
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2024
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85191724167&doi=10.1109%2fICPEA60617.2024.10498207&partnerID=40&md5=f2e21f690243a7d05a23cb6b45a66438

In a deregulated power market, it's essential to allocate transmission losses charges to consumers to cover the transmission system's operating costs. However, determining the allocated transmission losses in Megawatts precedes charge allocation. This paper proposes a method for predicting the allocation of real power losses in deregulated power systems using Artificial Neural Network (ANN) and the Z-Bus tracing technique. The ANN is employed to forecast the allocation of real power losses to consumers. Three distinct training algorithms - Levenberg-Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient backpropagation - are considered in developing the proposed ANN. The Z-Bus tracing technique is utilized to generate data samples for training the ANN. Simulation results demonstrate promising predictions on losses allocation through the integration of ANN and the Z-Bus tracing, albeit with varying performances across different training algorithms. © 2024 IEEE.