Short-Term Load Forecasting Based on Elastic Net Improved GMDH and Difference Degree Weighting Optimization
Source abstract
Abstract
As objects of load prediction are becoming increasingly diversified and complicated, it is extremely important to improve the accuracy of load forecasting under complex systems. When using the group method of data handling (GMDH), it is easy for the load forecasting to suffer from overfitting and be unable to deal with multicollinearity under complex systems. To solve this problem, this paper proposes a GMDH algorithm based on elastic net regression, that is, group method of data handling based on elastic net (EN-GMDH), as a short-term load forecasting model. The algorithm uses an elastic net to compress and punish the coefficients of the Kolmogorov–Gabor (K–G) polynomial and select variables. Meanwhile, based on the difference degree of historical data, this paper carries out variable weight processing on the input data of load forecasting, so as to solve the impact brought by the abrupt change of load law. Ten characteristic variables, including meteorological factors, meteorological accumulation factors, and holiday factors, are taken as input variables. Then, EN-GMDH is used to establish the relationship between the characteristic variables and the load, and a short-term load forecasting model is established. The results demonstrate that, compared with other algorithms, the evaluation index of EN-GMDH is significantly better than that of the rest algorithm models in short-term load forecasting, and the accuracy of prediction is obviously improved.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Neural Networks and Applications · Statistical and Computational Modeling
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Electrical and Electronic Engineering, Shandong University of Technology, Zibo 255000, China
The Department of Electronic Inform, Jingmen Vocational College, Jingmen 448000, China
References (55)
Show source-provided references
1. Kong, C.Q., Xia, Q., and Liu, M. (2017). Power System Analysis, China Electric Power Press. [2nd ed.].
2. Review of the short-term load forecasting methods of electric power system
3. Zheng, H.T., Yuan, J.B., and Chen, L. (2017). Short-term load forecasting using Emd-Lstm neural networks with a xgboost algorithm for feature importance evaluation. Energies, 10.10.3390/en10081168 ↗
4. Method of short-term load forecasting based on mean generating function-optimal subset regression
5. Short-term load forecasting using SVR (support vector regression)-based radial basis function neural network with dual extended Kalman filter10.1016/j.energy.2012.11.015 ↗
6. A new hybrid modified firefly algorithm and support vector regression model for accurate short term load forecasting10.1016/j.eswa.2014.03.053 ↗
7. A modified feature selection and artificial neural network-based day-ahead load forecasting model for a smart grid10.3390/app5041756 ↗
8. Wang, J., Li, P., Ran, R., Che, Y., and Zhou, Y. (2018). A short-term photovoltaic power prediction model based on the gradient boost decision tree. Appl. Sci., 8.10.3390/app8050689 ↗
9. Bagging exponential smoothing methods using STL decomposition and Box–Cox transformation10.1016/j.ijforecast.2015.07.002 ↗
10. Pattern-based local linear regression models for short-term load forecasting10.1016/j.epsr.2015.09.001 ↗
11. Electric load forecasting by using dynamic neural network10.1016/j.ijhydene.2017.03.101 ↗
12. Cross-validation aggregation for combining autoregressive neural network forecasts10.1016/j.ijforecast.2015.12.011 ↗
13. Research and application of a combined model based on multi-objective optimization for electrical load forecasting10.1016/j.energy.2016.11.035 ↗
14. Ryu, S., Noh, J., and Kim, H. (2017). Deep Neural Network Based Demand Side Short Term Load Forecasting. Energies, 10.10.3390/en10010003 ↗
15. Ping, H.K., and Huang, C.J. (2017). A high precision artificial neural networks model for short-term energy load forecasting. Energies, 11.10.3390/en11010213 ↗
16. Sun, W., and Zhang, C.C. (2018). A hybrid BA-ELM model based on factor analysis and similar-day approach for short-term load forecasting. Energies, 11.10.3390/en11051282 ↗
17. Bouktif, S., Fiaz, A., Ouni, A., and Serhani, M.A. (2018). Optimal deep learning lstm model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches. Energies, 11.10.3390/en11071636 ↗
18. Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond10.1016/j.ijforecast.2016.02.001 ↗
19. Review on probabilistic forecasting of photovoltaic power production and electricity consumption
20. Parallel and reliable probabilistic load forecasting via quantile regression forest and quantile determination10.1016/j.energy.2018.07.019 ↗
21. Forecasting with temporal hierarchies10.1016/j.ejor.2017.02.046 ↗
22. Short-term residential load forecasting based on resident behaviour learning10.1109/TPWRS.2017.2688178 ↗
23. Bracale, A., Carpinelli, G., Falco, P.D., and Hong, T. (2017, January 26–29). Short-term Industrial Load Forecasting: A Case Study in an Italian Factory. Proceedings of the 2017 IEEE PES Innovative Smart Grid Technologies Conference, Torino, Italy.10.1109/ISGTEurope.2017.8260176 ↗
24. Probabilistic forecasting of industrial electricity load with regime switching behavior10.1016/j.ijforecast.2017.09.006 ↗
25. Lasso estimation for GEFCom2014 probabilistic electric load forecasting10.1016/j.ijforecast.2016.01.001 ↗
26. A review and analysis of regression and machine learning models on commercial building electricity load forecasting10.1016/j.rser.2017.02.023 ↗
27. The review of problems solvable by algorithms of the group method of data handling (GMDH)
28. Onwubolu, G. (2016). GMDH-Methodology and Implementation in MATLAB, Imperial College Press. [1st ed.].
29. Application of GMDH and variable co-integration theory in power load forecasting, Power Syst
30. Using GMDH Neural Networks to Model the Power and Torque of a Stirling Engine10.3390/su7022243 ↗
31. Yang, L.T., Yang, H.G., and Liu, H.T. (2018). GMDH-based semi-supervised feature selection for electricity load classification forecasting. Sustainability, 10.10.3390/su10010217 ↗
32. NF-GMDH-Based self-organized systems to predict bridge pier scour depth under debris flow effects10.1080/1064119X.2017.1355944 ↗
33. A D-GMDH model for time series forecasting10.1016/j.eswa.2011.11.100 ↗
34. Survey on the regularized sparse models
35. Application of elastic net method in balanced longitudinal data models
36. Lu, Y. (2011). Variable Selection Method via the Elastic Net in Generalized Linear Models. [Master’s Thesis, Beijing Jiaotong University].
37. Uniejewski, B., Nowotarski, J., and Weron, R. (2016). Automated variable selection and shrinkage for day-ahead electricity price forecasting. Energies, 9.10.3390/en9080621 ↗
38. Putting big data analytics to work: Feature selection for forecasting electricity prices using the lasso and random forests10.1080/12460125.2015.994290 ↗
39. Study on combination forecasting model for mid-long term power load based on GMDH
40. Problems of further development of the group method of data handling algorithms
41. Regularization paths for generalized linear models via coordinate descent10.18637/jss.v033.i01 ↗
42. Important variable assessment and electricity price forecasting based on regression tree models: Classification and regression trees, bagging and random forests10.1049/iet-gtd.2014.0655 ↗
43. A general theory of classificatory sorting strategies: 1. hierarchical systems10.1093/comjnl/9.4.373 ↗
44. Impact analysis of hourly weather factors in short-term load forecasting and its processing strategy
45. A novel hybrid short term load forecasting model considering the error of numerical weather prediction10.3390/en9120994 ↗
46. Acclimation and the response of hourly electricity loads to meteorological variables10.1016/j.energy.2017.10.037 ↗
47. Short-term load forecasting considering the accumulative effects of temperatures
48. An analysis of accumulative effect of temperature in short-term load forecasting
49. Temperature sensitive method for short term load forecasting during holidays
50. Load characteristics analysis and load forecasting during spring festival in Nanjing district
51. Using the ensemble Kalman filter for electricity load forecasting and analysis10.1016/j.energy.2016.03.070 ↗
52. Cause of multi-collinearity and its diagnosis and treatment
53. Another look at measures of forecast accuracy10.1016/j.ijforecast.2006.03.001 ↗
54. On the use of cross-validation for time series predictor evaluation10.1016/j.ins.2011.12.028 ↗
55. A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms10.1016/j.swevo.2011.02.002 ↗