Short-Term Load Forecasting for Electric Bus Charging Stations Based on Fuzzy Clustering and Least Squares Support Vector Machine Optimized by Wolf Pack Algorithm

Accurate short-term load forecasting is of momentous significance to ensure safe and economic operation of quick-change electric bus (e-bus) charging stations. In order to improve the accuracy and stability of load prediction, this paper proposes a hybrid model that combines fuzzy clustering (FC), least squares support vector machine (LSSVM), and wolf pack algorithm (WPA). On the basis of load characteristics analysis for e-bus charging stations, FC is adopted to extract samples on similar days, which can not only avoid the blindness of selecting similar days by experience, but can also overcome the adverse effects of unconventional load data caused by a sudden change of factors on training. Then, WPA with good global convergence and computational robustness is employed to optimize the parameters of LSSVM. Thus, a novel hybrid load forecasting model for quick-change e-bus charging stations is built, namely FC-WPA-LSSVM. To verify the developed model, two case studies are used for model construction and testing. The simulation test results prove that the proposed model can obtain high prediction accuracy and ideal stability.

[1]  Tom Molinski,et al.  PEV Charging Profile Prediction and Analysis Based on Vehicle Usage Data , 2012, IEEE Transactions on Smart Grid.

[2]  Chia-Hung Lin,et al.  Synchronizing chaotification with support vector machine and wolf pack search algorithm for estimation of peripheral vascular occlusion in diabetes mellitus , 2014, Biomed. Signal Process. Control..

[3]  Hongjie Jia,et al.  Clean, affordable and reliable energy systems for low carbon city transition , 2017 .

[4]  Chunyan Miao,et al.  Optimal Electric Vehicle Fast Charging Station Placement Based on Game Theoretical Framework , 2018, IEEE Transactions on Intelligent Transportation Systems.

[5]  Igor Škrjanc,et al.  Short-Term Load Forecasting by Separating Daily Profiles and Using a Single Fuzzy Model Across the Entire Domain , 2018, IEEE Transactions on Industrial Electronics.

[6]  Agostino Tarsitano,et al.  Short-term load forecasting using a two-stage sarimax model , 2017 .

[7]  Mano Ranjan Kumar,et al.  Frequency dependent piecewise fractional-order modelling of ultracapacitors using hybrid optimization and fuzzy clustering , 2016 .

[8]  Hamid Hassanpour,et al.  Gender classification based on fuzzy clustering and principal component analysis , 2016, IET Comput. Vis..

[9]  V. Singh,et al.  Drought forecasting in eastern Australia using multivariate adaptive regression spline, least square support vector machine and M5Tree model , 2017 .

[10]  Feng Zhao,et al.  Stochastic Modeling and Forecasting of Load Demand for Electric Bus Battery-Swap Station , 2014, IEEE Transactions on Power Delivery.

[11]  Husheng Wu,et al.  Wolf Pack Algorithm for Unconstrained Global Optimization , 2014 .

[12]  Xin Yao,et al.  A Survey on Evolutionary Computation Approaches to Feature Selection , 2016, IEEE Transactions on Evolutionary Computation.

[13]  Hemanshu R. Pota,et al.  Forecasting the EV charging load based on customer profile or station measurement , 2016 .

[14]  Jinxing Che,et al.  An incremental electric load forecasting model based on support vector regression , 2016 .

[15]  Adrião Duarte Dória Neto,et al.  A multi-level approach using genetic algorithms in an ensemble of Least Squares Support Vector Machines , 2016, Knowl. Based Syst..

[16]  Song Li,et al.  A Novel Wavelet-Based Ensemble Method for Short-Term Load Forecasting with Hybrid Neural Networks and Feature Selection , 2016, IEEE Transactions on Power Systems.

[17]  Yanbin Yuan,et al.  Wind power prediction using hybrid autoregressive fractionally integrated moving average and least square support vector machine , 2017 .

[18]  Jiuping Xu,et al.  ROI-based study on impact factors of distributed PV projects by LSSVM-PSO , 2017 .

[19]  Laurent Bitjoka,et al.  Robust and Fast Segmentation Based on Fuzzy Clustering Combined with Unsupervised Histogram Analysis , 2017, IEEE Intelligent Systems.

[20]  Tao Zhang,et al.  Forecasting carbon price using empirical mode decomposition and evolutionary least squares support vector regression , 2017 .

[21]  Yi Liang,et al.  Short-Term Load Forecasting Based on Wavelet Transform and Least Squares Support Vector Machine Optimized by Improved Cuckoo Search , 2016 .

[22]  Theofanis Sapatinas,et al.  Short-Term Load Forecasting: The Similar Shape Functional Time-Series Predictor , 2012, IEEE Transactions on Power Systems.

[23]  Dongxiao Niu,et al.  A Short-Term Load Forecasting Model with a Modified Particle Swarm Optimization Algorithm and Least Squares Support Vector Machine Based on the Denoising Method of Empirical Mode Decomposition and Grey Relational Analysis , 2017 .

[24]  Jose I. Bilbao,et al.  A review and analysis of regression and machine learning models on commercial building electricity load forecasting , 2017 .

[25]  Long Wang,et al.  The Crucial Problem of the NSS in the Ecommerce , 2007 .

[26]  Yi Liang,et al.  Icing Forecasting of Transmission Lines with a Modified Back Propagation Neural Network-Support Vector Machine-Extreme Learning Machine with Kernel (BPNN-SVM-KELM) Based on the Variance-Covariance Weight Determination Method , 2017 .

[27]  Whei-Min Lin,et al.  Particle swarm optimisation aided least-square support vector machine for load forecast with spikes , 2016 .

[28]  Jin Yang,et al.  A holistic low carbon city indicator framework for sustainable development , 2017 .

[29]  Lei Zhang,et al.  A Novel Hybrid Based on Wolf Pack Algorithm and Differential Evolution Algorithm , 2017, 2017 10th International Symposium on Computational Intelligence and Design (ISCID).

[30]  Yi Song,et al.  Sustainability Evaluation of Power Grid Construction Projects Using Improved TOPSIS and Least Square Support Vector Machine with Modified Fly Optimization Algorithm , 2018 .

[31]  Wei Sun,et al.  Daily PM2.5 concentration prediction based on principal component analysis and LSSVM optimized by cuckoo search algorithm. , 2017, Journal of environmental management.

[32]  Chao Zhang,et al.  A Forecasting Method of Short-Term Electric Power Load Based on BP Neural Network , 2014 .

[33]  Jing Ma,et al.  Research and application of a hybrid wavelet neural network model with the improved cuckoo search algorithm for electrical power system forecasting , 2017 .

[34]  Xiangzhi Bai,et al.  Symmetry Information Based Fuzzy Clustering for Infrared Pedestrian Segmentation , 2018, IEEE Transactions on Fuzzy Systems.

[35]  Cunbin Li,et al.  A least squares support vector machine model optimized by moth-flame optimization algorithm for annual power load forecasting , 2016, Applied Intelligence.