Midterm Load Forecasting: A Multistep Approach Based on Phase Space Reconstruction and Support Vector Machine

2020 ◽  
Vol 14 (4) ◽  
pp. 4967-4977 ◽  
Author(s):  
Gen Li ◽  
Yunhua Li ◽  
Farzad Roozitalab
Keyword(s):  
Support Vector Machine ◽  
Phase Space ◽  
Load Forecasting ◽  
Phase Space Reconstruction ◽  
Support Vector

scholarly journals Prediction of Energy-Efficient Production of Coalbed Methane Based on Chaotic Time Series and Bayes-Least Squares-Support Vector Machine

2020 ◽  
Vol 38 (4) ◽  
pp. 933-940
Author(s):  
Yan Wang ◽  
Zhongshui Man ◽  
Meihua Lu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Support Vector Machine ◽  
Phase Space ◽  
Energy Efficient ◽  
Coalbed Methane ◽  
Phase Space Reconstruction ◽  
Support Vector ◽  
Proposed Model ◽  
Bayesian Evidence

The productivity of coalbed methane (CBM) depends heavily on the heat environment, and directly reflects the quality of the well. Following the theories of phase space reconstruction and Bayesian evidence framework, this paper puts forward a Bayes-least squares-support vector machine (Bayes-LS-SVM) model for the prediction of energy-efficient productivity of CBM under Bayesian evidence network based on chaotic time series. The energy-efficient productivity stands for the gas and water production of CBM wells at a low energy consumption, despite the disturbance from the heat environment. The proposed model avoids the local optimum trap of backpropagation neural network (BPNN), and overcomes the main defects of the SVM: high time consumption of parameter determination, and proneness to overfitting. In our model, the model parameters are optimized through three-layer Bayesian evidence inference, and the input vector for prediction is selected adaptively. In this way, the model construction is not too empirical, and the constructed model is highly adaptive. Then, the theory on phase space reconstruction was applied to investigate the chaotic property of the time series on CBM production, and the Bayes-LS-SVM was adopted to predict the time series after phase space reconstruction, in comparison with neural network prediction methods like SVM and BPNN. Experimental results show that the proposed model boast quick computing, accurate fitting, flexible structure, and strong generalization ability.

scholarly journals Nearest Neighbors Time Series Forecaster Based on Phase Space Reconstruction for Short-Term Load Forecasting

Energies ◽  
2020 ◽  
Vol 13 (20) ◽  
pp. 5309
Author(s):  
Jose R. Cedeño González ◽  
Juan J. Flores ◽  
Claudio R. Fuerte-Esquivel ◽  
Boris A. Moreno-Alcaide
Keyword(s):  
Phase Space ◽  
National Level ◽  
Load Forecasting ◽  
Nearest Neighbors ◽  
Electric Utility ◽  
Phase Space Reconstruction ◽  
Support Vector ◽  
Short Term ◽  
Essential Information ◽  
Short Term Load Forecasting

Load forecasting provides essential information for engineers and operators of an electric system. Using the forecast information, an electric utility company’s engineers make informed decisions in critical scenarios. The deregulation of energy industries makes load forecasting even more critical. In this article, the work we present, called Nearest Neighbors Load Forecasting (NNLF), was applied to very short-term load forecasting of electricity consumption at the national level in Mexico. The Energy Control National Center (CENACE—Spanish acronym) manages the National Interconnected System, working in a Real-Time Market system. The forecasting methodology we propose provides the information needed to solve the problem known as Economic Dispatch with Security Constraints for Multiple Intervals (MISCED). NNLF produces forecasts with a 15-min horizon to support decisions in the following four electric dispatch intervals. The hyperparameters used by Nearest Neighbors are tuned using Differential Evolution (DE), and the forecaster model inputs are determined using phase-space reconstruction. The developed models also use exogenous variables; we append a timestamp to each input (i.e., delay vector). The article presents a comparison between NNLF and other Machine Learning techniques: Artificial Neural Networks and Support Vector Regressors. NNLF outperformed those other techniques and the forecasting system they currently use.

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

2018 ◽  
Vol 13 ◽  
pp. 174830181879706 ◽  
Author(s):  
Song Qiang ◽  
Yang Pu
Keyword(s):  
Support Vector Machine ◽  
Particle Swarm Optimization ◽  
Influencing Factors ◽  
Load Forecasting ◽  
Particle Swarm ◽  
Forecast Accuracy ◽  
Support Vector ◽  
Model Parameters ◽  
Short Term ◽  
Swarm Optimization

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.

Sign in / Sign up

Export Citation Format

Share Document