Skip to main content
SpringerLink
Log in

Load Prediction Based on Optimization Ant Colony Algorithm

  • Original Article
  • Published:
Journal of Electrical Engineering & Technology Aims and scope Submit manuscript

Abstract

Short-term load in the power system is associated with huge computational consumption and low model utilization. Large input fluctuation tends to increase the training error of the neural network prediction model and reduce its generalization ability. To cope with this problem, this study aimed to introduce a method of radial basis function neural network algorithm based on least squares support vector machine algorithm. Based on the electricity market in an area of Yunnan province, the short-term loads were forecasted with historical data. First, the ant colony algorithm was improved using the chaos theory. Second, the improved ant colony was used to search least squares support vector machine and output the optimal parameters of the model. Then, the optimized model was used to train the data samples, and the output regression machine was used to provide better structures and parameters for the radial basis function neural network. The findings showed that compared with multiple prediction methods, the algorithm in this paper reduces the learning time and improves the fitting degree of the algorithm on the basis of improving the prediction accuracy. It shows that the algorithm in this paper has great advantages and good application prospects.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. El Desouky A, Elkateb M (2000) Hybrid adaptive techniques for electric-load forecast using ANN and ARIMA. IEEE Proc Gener Transm Distrib 147(4):213–217. https://doi.org/10.1049/ip-gtd:20000521

    Article  Google Scholar 

  2. Wang L, Zhu WG, Yang WQ et al (2019) Forecast of the medium-and long-term daily load curve based on grey neural network and gray correlation. J Wuhan Uni Eng Ed 52(1):58–64

    Google Scholar 

  3. Peng H, Jiang QY (2018) Application of improved BP neural network in short-term load forecasting of power systems. Heilongjiang Electr Power 40(5):414–419

    Google Scholar 

  4. Peng XG, Hu SF, Lv DY (2011) Summary of short-term load prediction methods based on RBF neural network. Electricity Syst Protect Control 39(17):144–148

    Google Scholar 

  5. Wan S L (2018) Short-term load prediction of neural net-works based on weather data blurring. Jiangxi Institute of Electrical Engineering: Proceedings of the 2017Annual Conference of Jiangxi Institute of Electrical Engineering, Nanchang, pp 112–116

  6. Shi HF (2013) Load prediction model based on Bayesian theory MCMC optimization parameters. North China Electric University, Beijing

    Google Scholar 

  7. Yang JF, Cheng HZ (2004) SVM applied research in short-term load prediction of power grid. Electr Autom Equip 24(2):30–32

    Google Scholar 

  8. Long W, Liang XM, Long ZQ et al (2011) LSSVM short-term load prediction based on improved ant colony algorithm optimization parameters. J Cent South Univ Nat Sci Ed 42(11):3408–3414

    Google Scholar 

  9. Deng CH, Wang M (2017) Research on short-term power load prediction based on similarity day and gray theory. J Chongqing Ind Commer Univ Nat Sci Ed 34(3):93–97

    Google Scholar 

  10. Pan E, Peng D, Long W, Xue Y, Zhao L, Li J (2019) Provincial grid investment scale forecasting based on MLR and RBF neural network. Math Probl Eng

  11. Vatankhah R, Etemadi S, Alasty A, Bourbaki M (2012) Active leading through obstacles using ant-colony algorithm. Neuro Comput 88:67–77

    Google Scholar 

  12. Javed F, Arshad N, Wallin F (2012) Forecasting for Demand response in smart grids: an analysis on use of anthropologic and structural data and short term multiple loads forecasting. Appl Energy 96:150–160

    Article  Google Scholar 

  13. Oshabaa AS, Alib ES, AbdElazim SM (2015) ACO based speed control of SRM fed by photovoltaic system. Electr Power Energy Syst 67:529–536

    Article  Google Scholar 

  14. Chunxiang Li, Xiaoda D, Jihong Ye (2016) Pulsating wind speed prediction based on hybrid ant colony and particle swarm optimization LSSVM. J Vib Shock 35(21):131–136

    Google Scholar 

  15. Weiping Tu, Chunxiang Li (2019) Short-term wind pressure prediction based on hybrid intelligent algorithm optimization of LSSVM. J Shanghai Univ (Nat Sci Ed) 25(02):347–356

    Google Scholar 

  16. Alia ES, AbdElazim SM, Abdelaziz AY (2016) Ant lion optimization algorithm for renewable distributed generations. Energy 116:445–458

    Article  Google Scholar 

  17. Dalvand MM, Azami S, Tarimoradi H (2008) Long-term load forecasting of Iranian power grid using fuzzy and artificial neural networks. In: Universities power engineering conference, 2008. UPEC 2008. 43rd international

  18. Li X, Zhu W, Bin J et al (2010) Shape feature selection and weed recognition based on image processing and ant colony optimization. Trans Chin Soc Agric Eng (Trans CSAE) 26(10):178–182

    Google Scholar 

  19. Fang WANG (2015) Prediction of Shanghai and Shenzhen 300 index regression based on support vector machines. Shandong University, Shandong, pp 15–50

    Google Scholar 

  20. Yitian REN (2016) Research on parallelization of massive text categorization based on support vector machines. Beijing University of Technology, Beijing, pp 1–40

    Google Scholar 

  21. Kumar L, Sripada SK, Sureka A (2018) Effective fault prediction model developed using least square support vector machine (LSSVM). J Syst Softw 137:686–712

    Article  Google Scholar 

  22. Zhao Donglei Ku, Wei LD, Wenhao Li, Guangru H (2017) The influence of meteorological factors on the accuracy of power system short-term load forecasting. Yunnan Electr Power Technol 45(03):49–52

    Google Scholar 

  23. Haiyun W, Xiaoxin G, Jian S, Mingwei G, Nan Y (2013) Analysis of the influence of meteorological factors on electric load changes in Beijing. Electr Appl 32(S1):223–226

    Google Scholar 

  24. Xianghua Li, Jian S, Yangsheng L, Bin Z, Jiayu C (2012) The influence of typical meteorological factors on the maximum daily load of provincial grid in summer. J Electr Power Sci Technol 27(02):70–75

    Google Scholar 

  25. Dongxiao NIU, Yanan WEI (2013) Short term power load forecasting combination based on FNN similar daily clustering weights. Autom Electr Power Syst 37(03):54–57

    Google Scholar 

  26. Yanhui X, Chenyu W (2017) Analysis of influencing factors of load characteristics of Shaanxi power grid based on gray correlation. Electr Appl 36(14):16–20

    Google Scholar 

  27. Yugang S (2007) Research on grey relational analysis and its application. Nanjing University of Aeronautics and Astronautics, Nanjing

    Google Scholar 

  28. Donglin C, Wenjian L, Lili H (2020) Cloud computing resource load prediction based on BPNN-LSTM combination model. J Beijing Univ Posts Telecommun (Soc Sci Ed) 22(1):53–60

    Google Scholar 

  29. Penghui L, Chenggang C, Ning Y, Hui C (2019) Research on short-term load forecasting method for buildings based on ARIMA LSTM composite model. J Shanghai Electr Power Univ 35(06):573–579

    Google Scholar 

  30. Jinji F (2018) Daily load prediction of power grid based on ARMA and ANN model combined crossover method. Zhejiang Electr Power 37(08):35–41

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Kunming University of Science and Technology, Kunming, Yunnan Province, China

    Wei Li, Jingmin Tang, Han Ma, Min Fan, Simiao Liu & Jie Wang

Authors
  1. Wei Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jingmin Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Han Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Min Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Simiao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jie Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jingmin Tang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, W., Tang, J., Ma, H. et al. Load Prediction Based on Optimization Ant Colony Algorithm. J. Electr. Eng. Technol. 18, 27–37 (2023). https://doi.org/10.1007/s42835-022-01147-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s42835-022-01147-7

Keywords

Search

Navigation