Abstract
Accurate and stable load forecasting has great significance to ensure the safe operation of distributed energy system. For the purpose of improving the accuracy and stability of distributed energy system load forecasting, a forecasting model in view of kernel principal component analysis (KPCA), kernel extreme learning machine (KELM) and fireworks algorithm (FWA) is proposed. First, KPCA modal is used to reduce the dimension of the feature, thus redundant input samples are merged. Next, FWA is employed to optimize the parameters C and σ of KELM. Lastly, the load forecasting modal of KPCA-FWA-KELM is established. The relevant data of a distributed energy system in Beijing, China, is selected for training test to verify the effectiveness of the proposed method. The results show that the new hybrid KPCA-FWA-KELM method has superior performance, robustness and versatility in load prediction of distributed energy systems.
Highlights
The concept of energy internet will effectively promote world energy production, consumption and system reform, and drive energy transformation in all countries so as to achieve energy cleanliness, efficiency, safety, convenience, and sustainable use [1]
The influence factors of the tributed energy system load are determined by the literature data analysis, and the distributed energy system load are determined by the literature data analysis, and candidate input variables C = {Ci, i = 1, 2, ..., n} are formed, and quantify and normal‐
The results show that the prediction curve of kernel extreme learning machine (KELM) method is more accurate than that of single prediction curve, indicating that the introduction of kernel function increases the accuracy of the model to a certain extent
Summary
The concept of energy internet will effectively promote world energy production, consumption and system reform, and drive energy transformation in all countries so as to achieve energy cleanliness, efficiency, safety, convenience, and sustainable use [1]. Since intelligent algorithms can simulate the human brain mechanism, simulation forecast the change of objects through the function of self-learning and self-optimization, establish suitable models, the prediction accuracy of intelligent algorithms such as artificial neural network (ANN) has been improved [9]. Due to these elements, scholars began to focus on continuous optimization of ANN and support vector machine (SVM), so as to enhance the convergence speed and the accuracy of the prediction results.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
