Short-term cooling, heating and electrical load forecasting in business parks based on improved entropy method

Short-term cooling, heating and electrical load forecasting in business parks is the basis of safe and economical operation of the scheduling system, and its accuracy is largely influenced by the selection of similar days. In order to improve the accuracy of load forecasting, a short-term load forecasting method based on improved entropy method is proposed. This method is used in the similar day selection and the similar day weight determination separately. It overcomes the drawback of traditional entropy weight method that the information transferred by entropy weight and entropy value is inconsistent when all entropy values are close to one. The verification example shows that this method can not only select the most suitable similar day from the historical day, but also has a faster computing speed than the conventional intelligent algorithm.