Smart grid short-term load estimation model based on BP neural network

As reasonable short-term load estimation system can provide reliable support for the operating, planning and designing of the smart grid, in this paper, we propose an effective smart grid short-term load estimation method. Different types of data are input to the BP neural network and then the output of BP neural network is represented as the load estimation results. Although BP neural network can approximate any nonlinear continuous function with the condition of a specific structure and suitable weights, it is very difficult to obtain the global minimum result. In order to obtain the global optimum solution in short-term load estimation, we exploit the genetic algorithm to optimise the weights and thresholds of the BP neural network, which is the main advantage of the proposed model. Finally, experimental results demonstrate that the proposed method can estimate short-term load of smart grid with higher accuracy and it can also clearly show the load requirement distribution in different time period.