Comparative Analysis of Load Forecasting by Using ANN, FUZZY Logic and ANFIS

With the paradigm shift of power transmission and distribution system towards decentralized control, there has been a great upsurge in forecasting of load which would be effective for economic utilization of resources. In this paper, there is a comparative study about load forecasting using various Artificial Intelligence techniques which includes Neural Network, Fuzzy logic as well as adaptive neuro-fuzzy system to indicate an effective solution for optimum utilization of renewable sources which is incorporated in the existing grid conditions. The AI techniques have helped to utilize information like the data of historical load, weather conditions and temperature difference such that a decision can be taken when to integrate how much renewable energy source in the present system such that optimum results are obtained. The comparison reveals that the ANFIS system is more effective to pass decision on when to integrate renewable energy sources into the grid. Load Forecasting at various places is critical for efficiently utilizing energy potential. With this in mind, intelligent models based on fuzzy logic, ANN, and ANFIS are created and presented for Load prediction. The suggested Review can readily integrate climate variables’ uncertainty and nonlinearity. A comparison of the aforementioned models has also been performed. It is explored if the findings produced by the ANFIS model for load prediction are better and more accurate. As a result, the ANFIS model may be useful in anticipating load and optimizing resource consumption.