Skip to main content
SpringerLink
Log in

An Improved Leaky-ESN for Electricity Load Forecasting

  • Conference paper
  • First Online:
Book cover Green, Pervasive, and Cloud Computing (GPC 2020)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 12398))

Included in the following conference series:

  • 1152 Accesses

Abstract

In the recent decade, recurrent neural networks become a hot research field, with the powerful capability to capture temporal information from time series. To avoid the vanishing/exploding gradient problem caused by the gradient descent algorithm involved in most recurrent networks, echo state network (ESN) was proposed to contain a large but sparse reservoir instead of traditional hidden layers. However, the performance of ESN is very sensitive to the parameters of the reservoir. In this paper, we focus on the improvements of ESN in the background of electricity load forecasting. With the goal of effectively and efficiently computation in the context of pervasive and cloud computing, two versions of adaptive echo state network (AESN) are designed to adopt a modular control strategy to automatically adjust some parameters of the reservoir. Applying AESN on two synthetic datasets and two real world electricity datasets, experimental results demonstrate that AESN is viable.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Amjady, N., Keynia, F.: Short-term load forecasting of power systems by combination of wavelet transform and neuro-evolutionary algorithm. Energy 34(1), 46–57 (2009)

    Article  Google Scholar 

  2. Ertugrul, Ö.F.: Forecasting electricity load by a novel recurrent extreme learning machines approach. Int. J. Electrical Power Energy Syst. 78, 429–435 (2016)

    Article  Google Scholar 

  3. Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks-with an erratum note. German National Res. Center for Inf. Technol. GMD Tech. Report 148(34), 13 (2001)

    Google Scholar 

  4. Løkse, S., Bianchi, F.M., Jenssen, R.: Training echo state networks with regularization through dimensionality reduction. Cogn. Comput. 9(3), 364–378 (2017)

    Article  Google Scholar 

  5. Alfares, H.K., Nazeeruddin, M.: Electric load forecasting: literature survey and classification of methods. Int. J. Syst. Sci. 33(1), 23–34 (2002)

    Article  MATH  Google Scholar 

  6. Islam, B.U.: Comparison of conventional and modern load forecasting techniques based on artificial intelligence and expert systems. Int. J. Comput. Sci. Issues (IJCSI) 8(5), 504 (2011)

    Google Scholar 

  7. BVBCET, H., SSIT, T.: Short Term Load Forecasting Using Time Series Analysis: A Case Study for Karnataka, India (2012)

    Google Scholar 

  8. Anand, N.C, Scoglio, C., Natarajan, B.: GARCH—Non-linear time series model for traffic modeling and prediction. In: Network Operations and Management Symposium. pp. 694–697, IEEE (2008)

    Google Scholar 

  9. Bahrami, S., Hooshmand, R.A., Parastegari, M.: Short term electric load forecasting by wavelet transform and grey model improved by PSO (particle swarm optimization) algorithm. Energy 72, 434–442 (2014)

    Article  Google Scholar 

  10. Dudek, G.: Artificial immune system with local feature selection for short-term load forecasting. IEEE Trans. Evol. Comput. 21(1), 116–130 (2016)

    Article  Google Scholar 

  11. Mateo, F., Carrasco, J.J., Millán-Giraldo, M., et al.: Machine learning techniques for short-term electric power demand prediction. In: European Symposium on Artificial Neural Networks (2013)

    Google Scholar 

  12. Hu, Z., Bao, Y., Xiong, T.: Comprehensive learning particle swarm optimization based memetic algorithm for model selection in short-term load forecasting using support vector regression. Appl. Soft Comput. 25, 15–25 (2014)

    Article  Google Scholar 

  13. Hu, Z., Bao, Y., Xiong, T., et al.: Hybrid filter–wrapper feature selection for short-term load forecasting. Eng. Appl. Artif. Intell. 40, 17–27 (2015)

    Article  Google Scholar 

  14. Cheepati, K.R., Prasad, T.N.: Performance comparison of short term load forecasting techniques. Int. J. Grid Distrib. Comput 9(4), 287–302 (2016)

    Article  Google Scholar 

  15. Vermaak, J., Botha, E.C.: Recurrent neural networks for short-term load forecasting. IEEE Trans. Power Syst. 13(1), 126–132 (1998)

    Article  Google Scholar 

  16. Khan, G.M., Zafari, F., Mahmud, S.A.: Very short term load forecasting using Cartesian genetic programming evolved recurrent neural networks (CGPRNN). In: 12th International Conference on Machine Learning and Applications. vol. 2, pp. 152–155, IEEE (2013)

    Google Scholar 

  17. Zhang, B., Wu, J.L., Chang, P.C.: A multiple time series-based recurrent neural network for short-term load forecasting. Soft. Comput. 22(12), 4099–4112 (2017). https://doi.org/10.1007/s00500-017-2624-5

    Article  Google Scholar 

  18. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  19. Kobialka, H.U., Kayani, U.: Echo state networks with sparse output connections. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010. LNCS, vol. 6352, pp. 356–361. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15819-3_47

    Chapter  Google Scholar 

  20. Deihimi, A., Showkati, H.: Application of echo state networks in short-term electric load forecasting. Energy 39(1), 327–340 (2012)

    Article  Google Scholar 

  21. Han, M., Xu, M.: Laplacian echo state network for multivariate time series prediction. IEEE Trans. Neural Netw. Learn. Syst. 29(1), 238–244 (2017)

    Article  MathSciNet  Google Scholar 

  22. Dedinec, A., Filiposka, S., Dedinec, A., et al.: Deep belief network based electricity load forecasting: An analysis of Macedonian case. Energy 115, 1688–1700 (2016)

    Article  Google Scholar 

  23. Butcher, J.B.: Reservoir Computing with high non-linear separation and long-term memory for time-series data analysis. Keele University (2012)

    Google Scholar 

  24. Lukoševičius, M.: A practical guide to applying echo state networks. In: Montavon, G., Orr, G.B., Müller, K.R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 659–686. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_36

    Chapter  Google Scholar 

  25. Yildiz, I.B., Jaeger, H., Kiebel, S.J.: Re-visiting the echo state property. Neural Netw. 35, 1–9 (2012)

    Article  MATH  Google Scholar 

  26. Jiang, F., Berry, H., Schoenauer, M.: Supervised and evolutionary learning of echo state networks. In: Rudolph, G., Jansen, T., Beume, N., Lucas, S., Poloni, C. (eds.) PPSN 2008. LNCS, vol. 5199, pp. 215–224. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-87700-4_22

    Chapter  Google Scholar 

  27. Jaeger, H.: Short term memory in echo state networks. GMD-Report 152. GMD-German National Research Institute for Computer Science (2002)

    Google Scholar 

  28. Shi, Z., Han, M.: Ridge regression learning in ESN for chaotic time series prediction. Control Decis. 22(3), 258 (2007)

    MathSciNet  MATH  Google Scholar 

  29. Lukoševicius, M, Popovici D, Jaeger H, et al.: Time warping invariant echo state networks. International University Bremen, Technical Report (2006)

    Google Scholar 

  30. Lun, S.X., Yao, X.S., Qi, H.Y., et al.: A novel model of leaky integrator echo state network for time-series prediction. Neurocomputing 159, 58–66 (2015)

    Article  Google Scholar 

  31. Lun, S., Yao, X., Hu, H.: A new echo state network with variable memory length. Inf. Sci. 370, 103–119 (2016)

    Article  MATH  Google Scholar 

  32. Koutnik, J., Greff, K., Gomez, F., et al.: A Clockwork RNN. Computer ence. pp. 1863–1871 (2014)

    Google Scholar 

  33. Holzmann, G., Hauser, H.: Echo state networks with filter neurons and a delay&sum readout. Neural Netw. 23(2), 244–256 (2010)

    Article  MATH  Google Scholar 

  34. Jaeger, H., Lukoševičius, M., Popovici, D., et al.: Optimization and applications of echo state networks with leaky-integrator neurons. Neural networks 20(3), 335–352 (2007)

    Article  MATH  Google Scholar 

  35. Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78–80 (2004)

    Article  Google Scholar 

  36. Ceperic, V., Baric, A.: Reducing complexity of echo state networks with sparse linear regression algorithms. In: 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation. pp. 26–31, IEEE (2014)

    Google Scholar 

  37. Australian Energy Market Operator. https://aemo.com.au/energy-systems/electricity/national-electricity-market-nem/data-nem/data-dashboard-nemAccessed 31 March 2020

Download references

Acknowledgments

This work is supported by the National Natural Science Foundation of China under Grant No. 61772136, 61672159, the Technology Innovation Platform Project of Fujian Province under Grant No. 2014H2005, the Research Project for Young and Middle-aged Teachers of Fujian Province under Grant No. JT180045, the Fujian Collaborative Innovation Center for Big Data Application in Governments, the Fujian Engineering Research Center of Big Data Analysis and Processing.

Author information

Authors and Affiliations

  1. College of Mathematics and Computer Science, Fuzhou University, Fuzhou, China

    Qiaoying Lin, Fangwan Huang, Zhiyong Yu & Li Li

  2. Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University, Fuzhou, China

    Qiaoying Lin, Fangwan Huang, Zhiyong Yu & Li Li

  3. Key Laboratory of Spatial Data Mining and Information Sharing, Ministry of Education, Fuzhou, China

    Zhiyong Yu

Authors
  1. Qiaoying Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fangwan Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhiyong Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Li Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fangwan Huang .

Editor information

Editors and Affiliations

  1. Northwestern Polytechnical University, Xi’an, China

    Zhiwen Yu

  2. University of Mannheim, Mannheim, Germany

    Christian Becker

  3. Chinese University of Hong Kong, Shatin, Hong Kong

    Guoliang Xing

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Lin, Q., Huang, F., Yu, Z., Li, L. (2020). An Improved Leaky-ESN for Electricity Load Forecasting. In: Yu, Z., Becker, C., Xing, G. (eds) Green, Pervasive, and Cloud Computing. GPC 2020. Lecture Notes in Computer Science(), vol 12398. Springer, Cham. https://doi.org/10.1007/978-3-030-64243-3_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-64243-3_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-64242-6

  • Online ISBN: 978-3-030-64243-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation