Load forecasting and price forecasting using Teaching Learning based Optimization and learning and adaptive fuzzy neural network

Today, the electricity market in the world is known scientifically that the competition in it is more every day than the previous day. Since the ability to store electrical energy is very small, therefore, forecasting the consumption load and the price of electricity helps the market participants to get more profit. The impact of the load pattern on various factors and the non-linearity of the electricity price signal make it difficult to accurately forecast the load and price; Therefore, the use of intelligent algorithms has found more use in forecasting problems compared to numerical and statistical methods. Therefore, in this thesis, the issues related to forecasting the load and electricity price are stated. Also, the electric load and electricity price have been predicted using the Adaptive neuro fuzzy inference system (ANFIS) combined with the Teaching Learning based Optimization (TLBO) and the effect of various factors on it has been investigated and simulated. In fact, by combining the evolutionary algorithms with the fuzzy neural system, the adjustment of the optimal values of the parameters of the adaptive fuzzy neural network should be assigned to the intelligent optimization algorithm of teaching and learning. The purpose of using this approach is to improve network performance and reduce computational complexity compared to gradient descent and least squares methods. The results of the implementation of the proposed algorithm show the better efficiency of this algorithm compared to previous algorithms for predicting load and electricity price.