TY - EJOUR
AU - Panda, Saroj
AU - Ray, Papia
AU - Salkuti, Surender
PY - 2024
DA - February
TI - Hybrid Techniques for Short Term Load Forecasting
T2 - Majlesi Journal of Electrical Engineering
VL - 17
L1 - https://oiccpress.com/Majlesi-Journal-of-Electrical-Engineering/article/hybrid-techniques-for-short-term-load-forecasting/
DO - 10.30486/mjee.2023.1970200.0
N2 - Short Term Load Forecasting (STLF) is the projection of system load demands for the next day or week. Because of its openness in modeling, simplicity of implementation, and improved performance, the ANN-based STLF model has gained traction. The neural model consists of weights whose optimal values are determined using various optimization approaches. This paper uses an Artificial Neural Network (ANN) trained using multiple hybrid techniques (HT) such as Back Propagation (BP), Cuckoo Search  (CS) model, and Bat algorithm (BA) for load forecasting. Here, a thorough examination of the various strategies is taken to determine their scope and ability to produce results using different models in different settings. The simulation results show that the BA-BP model has less predicting error than other techniques. However, the Back Propagation model based on the Cuckoo Search method produces less inaccuracy, which is acceptable.
IS - 1
PB - OICC Press
KW - Back Propagation, Cuckoo Search. Bat algorithm, Artificial Neural Network, Short Term Load Forecasting, Hybrid Techniques 
EN -