Power load forecasting in energy system based on improved extreme learning machine

Abstract

<jats:p> Through the accurate prediction of power load, the start and stop of generating units in the power grid can be arranged economically and reasonably. The safety and stability of power grid operation can be maintained. First, chicken swarm optimizer based on nonlinear dynamic convergence factor (NCSO) optimizer is proposed based on chicken swarm optimizer (CSO) optimizer. In NCSO optimizer, nonlinear dynamic inertia weight and levy mutation strategy are introduced. Compared with CSO optimizer, the convergence speed and effect of NCSO optimizer are obviously improved. Second, the random parameters of extreme learning machine (ELM) model are optimized by NCSO optimizer, and NCSOELM model is established to predict the power load. Finally, the NCSO optimization extreme learning machine (NCSOELM) model is used to predict the power load, and compared with back propagation (BP), support vector machine (SVM) and CSO optimization extreme learning machine (CSOELM) model. The experimental results show that the fitting accuracy of NCSOELM model is high, and the determination coefficient r<jats:sup>2</jats:sup> is above 90%. And the root mean square error value of the NCSOELM model is 0.87, 0.41, and 0.25 smaller than the root mean square error values of the support vector machine, BP, and CSOELM models, respectively. Experiments show that the model proposed in this study has high fitting effect and low prediction error, which is of positive significance for the realization of economic and safe operation of energy system. </jats:p>

Evaluation and Analysis of Urban Power Grid Operation Status Based on Online Sequence Extreme Learning Machine and Self-Coding Network

“…During this stage, RBM stacking learning is used to adjust the network layer weights to reduce errors between input and reconstructed data. In training, for input layer unit i v and hidden layer unit j h , the weights are updated based on the learning rate ε of the product difference of their states in equation (6).…”

“…Traditional evaluation methods are often difficult to handle large-scale power grid data, and there are obvious shortcomings in real-time and prediction accuracy. Therefore, there is an urgent need to develop new evaluation methods to improve the response speed to dynamic changes in the power grid and the accuracy of fault prediction [4][5][6]. This study focuses on the evaluation and prediction of the operational status of urban power grids, and proposes a new strategy for data dimensionality reduction by combining Analytic Hierarchy Process (AHP) with self-coding networks.…”

Prediction Methods of Common Cancers in China Using PCA-ANN and DBN-ELM-BP

“…Based on feedforward neural network (FNN), network structure of ELM includes input, hidden and output layer. Input weights and offsets be initialized randomly, then the corresponding output weights are obtained [38]. Here, assuming that there are M samples (X j , t j ), this neural network representation of L hidden layer nodes is as follows:…”

A hybridized algorithm of combination of modified teaching-learning-based optimization and modified chicken swarm optimization

“…Sampath K D [17] combined Improved Raven Rooster Optimization (IRRO) with CSO to gain a comprehensive algorithm and applied it to resolve the real problem of task scheduling. Chen [18]et alintroduced the nonlinear dynamic inertia weight and levy mutation strategy to CSO to obtain a new optimizer, named NCSO, and used it to optimize extreme learning machine (ELM) to predict power load in energy system. Kang [19] et al modified the updation formula of chick by bringing mutation strategy into CSO to increase their global exploring ability.…”