Short-term power load forecasting based on support vector machine and particle swarm optimization

Abstract

In this work, we summarized the characteristics and influencing factors of load forecasting based on its application status. The common methods of the short-term load forecasting were analyzed to derive their advantages and disadvantages. According to the historical load and meteorological data in a certain region of Taizhou, Zhejiang Province, a least squares support vector machine model was used to discuss the influencing factors of forecasting. The regularity of the load change was concluded to correct the "abnormal data" in the historical load data, thus normalizing the relevant factors in load forecasting. The two parameters are as follows Gauss kernel function and Eigen parameter C in LSSVM had a significant impact on the model, which was still solved by empirical methods. Therefore, the particle swarm optimization was used to optimize the model parameters. Taking the error of test set as the basis of judgment, the optimization of model parameters was achieved to improve forecast accuracy. The practical examples showed that the method in the work had good convergence, forecast accuracy, and training speed.

Methods and Models for Electric Load Forecasting: A Comprehensive Review

“…Hu and his colleagues [83] have demonstrated that the SVM forecasting model, whose parameters were adjusted by a firefly based memetic algorithm, can significantly outperform the other evolutionary-based SVR models, besides some of the classical forecasting models. Furthermore, Qiang and Pu [84] have deployed the SVMs based on the particle swarm optimization to apply a short-term load forecasting. There have also been detected many other papers in the literature that are dealing with the ELF forecasting.…”

“…The details of the derivation of the SVM (and SVR) models can be found in the literature (e.g., see [81][82][83][84][85][86][87][88][89]). When addressing the SVM models, the structured risk minimization risk principle is considered instead of finding the minimum empirical errors [81,83].…”

Applying statistical analysis for assessing the reliability of input data to improve the quality of short-term load forecasting for a Ho Chi Minh City distribution network

“…Dự báo phụ tải ngắn hạn (Short-time Load Forecasting -STLF) trong lưới phân phối có thể được thực hiện bằng các thuật toán học máy thông thường hoặc phức tạp. Đã có rất nhiều công trình nghiên cứu về các phương pháp dự báo phụ tải ngắn hạn, nhưng chỉ một số ít nghiên cứu có đề cập hoặc tập trung vào việc phát triển giải thuật/thuật toán lọc dữ liệu trước khi áp dụng mô hình dự báo phụ tải [1][2][3][4][5][6] . Nguyên nhân xuất phát từ việc một số tác giả cho rằng dữ liệu đầu vào là hoàn hảo hoặc đã được lọc trước khi được khai thác trong mô hình dự báo phụ tải.…”

Detecting load redistribution attacks via support vector models

“…SVR has been widely used for load prediction in electric power systems. In [19], a short‐term load forecasting algorithm is proposed combining SVR and particle swarm optimisation. Capuno et al .…”