Effective and reliable load forecasting is an important basis for power system planning and operation decisions. Its forecasting accuracy directly affects the safety and economy of the operation of the power system. However, attaining the desired point forecasting accuracy has been regarded as a challenge because of the intrinsic complexity and instability of the power load. Considering the difficulties of accurate point forecasting, interval prediction is able to tolerate increased uncertainty and provide more information for practical operation decisions. In this study, a novel hybrid system for short-term load forecasting (STLF) is proposed by integrating a data preprocessing module, a multi-objective optimization module, and an interval prediction module. In this system, the training process is performed by maximizing the coverage probability and by minimizing the forecasting interval width at the same time. To verify the performance of the proposed hybrid system, half-hourly load data are set as illustrative cases and two experiments are carried out in four states with four quarters in Australia. The simulation results verified the superiority of the proposed technique and the effects of the submodules were analyzed by comparing the outcomes with those of benchmark models. Furthermore, it is proved that the proposed hybrid system is valuable in improving power grid management.Energies 2018, 11, 1561 2 of 30 time. Among these categories, short-term load forecasting (STLF) is an essential tool for the planning and operation [1,2] of energy systems and it has thus been a major area of research during the past few decades.According to existing research, concern mostly focuses on the point forecasting of STLF. Additionally, the relative algorithms can be mainly classified into three major categories: traditional statistical techniques, computational intelligent methods, and multimodule hybrid models [3].In the early stages of research, traditional statistical techniques were extensively employed for point forecasting of STLF, such as linear regression methods [4,5], exponential smoothing [6], Kalman filters [7], and other linear time-series models. In general, most of the traditional statistical approaches have been involved in linear analysis and have mainly considered linear factors in time series. However, the short-term load series are a mixture of multiple components which include linear and non-linear factors. Therefore, the traditional statistical approaches encounter difficulties when dealing with the STLF, and the forecasting accuracy is often unsatisfactory. With the development of machine learning and artificial intelligence, an increased number of non-linear computational intelligent methods have been applied to STLF, such as neural network models (NN) [8,9], expert systems [10] and support vector machines (SVM) [11,12]. These approaches have been proved to have advantages in dealing with the non-linear problems of STLF compared to traditional statistical methods, thereby eliciting improved performanc...