Use of weighted local constant method to short-term forecasting of electric load in cities at weekends

被引:4
作者
Fan, Guo-Feng [1 ]
Peng, Li-Ling [1 ]
Huang, Hsin-Pou [2 ]
Hong, Wei-Chiang [2 ,3 ,4 ]
机构
[1] Ping Ding Shan Univ, Coll Math & Informat Sci, Ping Ding Shan 467000, Peoples R China
[2] Chihlee Univ Technol, Dept Informat Management, New Taipei 220305, Taiwan
[3] Asia Eastern Univ Sci & Technol, Dept Informat Management, New Taipei 22042, Taiwan
[4] Yuan Ze Univ, Dept Informat Management, Chungli 22042, Taiwan
关键词
Weekend electric load forecast; Phase space reconstruction; Weighted first -order local forecast method; Energy economy; FEATURE-SELECTION TECHNIQUE; ENERGY-CONSUMPTION; NEURAL-NETWORKS; REGRESSION; MODEL; PREDICTION; ARIMA; ALGORITHM; ENGINE; SPACE;
D O I
10.1016/j.epsr.2023.109464
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
To forecast accurately the electric load of a city at the weekend, aiming at the problems of nonlinearity and model interpretability in power behavior, a local constant first-order weighted forecasting model is developed. First of all, the values of the electric load are reconstructed in phase space, stability analysis can effectively describe the operation mechanism and law of weekend power. Then, the weights of neighbors are used in the first-order local forecasting model, and the nearest neighbors are used in grid optimization. The forecasted values are then separated to be the phase forecasting points in terms of the spatial dimension of the electric loads and the lags of the time delay obtained in the training stage. Numerical experimental results of samples at different scales show the following: (1)The forecasting performance of the proposed model is better than other models in the forecasting errors in this work (among three types of measurements: root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE)); (2) the significance test (KSPA) also confirmed the universality and consistency of the method, and the effective diagnosis and statistical analysis of the weekend power mechanism are helpful to promote weekend power management and commercial design.
引用
收藏
页数:14
相关论文
共 52 条
[21]   Global energy forecasting competition 2017: Hierarchical probabilistic load forecasting [J].
Hong, Tao ;
Xie, Jingrui ;
Black, Jonathan .
INTERNATIONAL JOURNAL OF FORECASTING, 2019, 35 (04) :1389-1399
[22]   Neural network model ensembles for building-level electricity load forecasts [J].
Jetcheva, Jorjeta G. ;
Majidpour, Mostafa ;
Chen, Wei-Peng .
ENERGY AND BUILDINGS, 2014, 84 :214-223
[23]   Priority index considering temperature and date proximity for selection of similar days in knowledge-based short term load forecasting method [J].
Karimi, M. ;
Karami, H. ;
Gholami, M. ;
Khatibzadehazad, H. ;
Moslemi, N. .
ENERGY, 2018, 144 :928-940
[24]   Identifying residential daily electricity-use profiles through time-segmented regression analysis [J].
Khan, Imran ;
Jack, Michael W. ;
Stephenson, Janet .
ENERGY AND BUILDINGS, 2019, 194 :232-246
[25]   Boosted neural networks for improved short-term electric load forecasting [J].
Khwaja, A. S. ;
Zhang, X. ;
Anpalagan, A. ;
Venkatesh, B. .
ELECTRIC POWER SYSTEMS RESEARCH, 2017, 143 :431-437
[26]   Short term electricity demand forecasting using partially linear additive quantile regression with an application to the unit commitment problem [J].
Lebotsa, Moshoko Emily ;
Sigauke, Caston ;
Bere, Alphonce ;
Fildes, Robert ;
Boylan, John E. .
APPLIED ENERGY, 2018, 222 :104-118
[27]   A local limit load model for J prediction via the reference stress method [J].
Lei, Yuebao .
ECF22 - LOADING AND ENVIRONMENTAL EFFECTS ON STRUCTURAL INTEGRITY, 2018, 13 :571-577
[28]   Electricity consumption and economic growth nexus in Beijing: A causal analysis of quarterly sectoral data [J].
Liu, Da ;
Ruan, Liang ;
Liu, Jinchen ;
Huan, Huang ;
Zhang, Guowei ;
Feng, Yi ;
Li, Ying .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2018, 82 :2498-2503
[29]   A novel random fuzzy neural networks for tackling uncertainties of electric load forecasting [J].
Lou, Chin Wang ;
Bong, Ming Chui .
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2015, 73 :34-44
[30]   Short-term residential load forecasting: Impact of calendar effects and forecast granularity [J].
Lusis, Peter ;
Khalilpour, Kaveh Rajab ;
Andrew, Lachlan ;
Liebman, Ariel .
APPLIED ENERGY, 2017, 205 :654-669