Hybridizing Deep Learning and Neuroevolution: Application to the Spanish Short-Term Electric Energy Consumption Forecasting
Source abstract
Abstract
The electric energy production would be much more efficient if accurate estimations of the future demand were available, since these would allow allocating only the resources needed for the production of the right amount of energy required. With this motivation in mind, we propose a strategy, based on neuroevolution, that can be used to this aim. Our proposal uses a genetic algorithm in order to find a sub-optimal set of hyper-parameters for configuring a deep neural network, which can then be used for obtaining the forecasting. Such a strategy is justified by the observation that the performances achieved by deep neural networks are strongly dependent on the right setting of the hyper-parameters, and genetic algorithms have shown excellent search capabilities in huge search spaces. Moreover, we base our proposal on a distributed computing platform, which allows its use on a large time-series. In order to assess the performances of our approach, we have applied it to a large dataset, related to the electric energy consumption registered in Spain over almost 10 years. Experimental results confirm the validity of our proposal since it outperforms all other forecasting techniques to which it has been compared.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Grey System Theory Applications · Solar Radiation and Photovoltaics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Data Science and Big Data Lab, Pablo de Olavide University, ES-41013 Seville, Spain
Computer Engineer Department, Universidad Americana de Paraguay, Asunción 1029, Paraguay
Funding
Ministerio de Economía y Competitividad · Consejo Nacional de Ciencia y Tecnología, Paraguay
References (58)
Show source-provided references
1. U.S. Energy Information Administration (2020, August 05). International Energy Outlook, Available online: https://www.eia.gov/outlooks/ieo/index.php.
2. Narayanaswamy, B., Jayram, T.S., and Yoong, V.N. (2012, January 14–17). Hedging strategies for renewable resource integration and uncertainty management in the smart grid. Proceedings of the 3rd IEEE PES Innovative Smart Grid Technologies Europe, ISGT, Berlin, Germany.10.1109/ISGTEurope.2012.6465718 ↗
3. Haque, R., Jamal, T., Maruf, M.N.I., Ferdous, S., and Priya, S.F.H. (2015, January 21–23). Smart management of PHEV and renewable energy sources for grid peak demand energy supply. Proceedings of the 2015 International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), Dhaka, Bangladesh.10.1109/ICEEICT.2015.7307497 ↗
4. Short term electricity load forecasting for institutional buildings10.1016/j.egyr.2019.08.086 ↗
5. Nazeriye, M., Haeri, A., and Martínez-Álvarez, F. (2020). Analysis of the Impact of Residential Property and Equipment on Building Energy Efficiency and Consumption-A Data Mining Approach. Appl. Sci., 10.10.3390/app10103589 ↗
6. Machine learning based system for managing energy efficiency of public sector as an approach towards smart cities
7. (2020, August 05). Energy 2020—A Strategy for Competitive, Sustainable and Secure Energy. Available online: http://eur-lex.europa.eu/legal-content/EN/TXT/PDF/?uri=CELEX:52010DC0639&from=EN.
8. A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings10.1016/j.rser.2015.04.065 ↗
9. A scalable approach based on deep learning for big data time series forecasting10.3233/ICA-180580 ↗
10. Miikkulainen, R., Liang, J.Z., Meyerson, E., Rawal, A., Fink, D., Francon, O., Raju, B., Shahrzad, H., Navruzyan, A., and Duffy, N. (2017). Evolving Deep Neural Networks. CoRR, Available online: https://arxiv.org/abs/1703.00548.
11. Designing neural networks through neuroevolution10.1038/s42256-018-0006-z ↗
12. Deep learning10.1038/nature14539 ↗
13. Such, F.P., Madhavan, V., Conti, E., Lehman, J., Stanley, K.O., and Clune, J. (2017). Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning. CoRR, Available online: https://arxiv.org/abs/1712.06567.
14. Divina, F., Gilson, A., Goméz-Vela, F., Torres, M.G., and Torres, J.F. (2018). Stacking Ensemble Learning for Short-Term Electricity Consumption Forecasting. Energies, 11.10.3390/en11040949 ↗
15. Modeling electricity loads in California: ARMA models with hyperbolic noise10.1016/S0165-1684(02)00318-3 ↗
16. Short-term load forecasting via ARMA model identification including non-Gaussian process considerations10.1109/TPWRS.2003.811010 ↗
17. A survey on data mining techniques applied to energy time series forecasting
18. Neural network based optimization approach for energy demand prediction in smart grid10.1016/j.neucom.2017.08.017 ↗
19. Electric load forecasting by using dynamic neural network10.1016/j.ijhydene.2017.03.101 ↗
20. Application of improved artificial neural networks in short-term power load forecasting10.1063/1.4926771 ↗
21. Short Term Electricity Forecasting Using Individual Smart Meter Data10.1016/j.procs.2014.08.140 ↗
22. Min, Z., and Qingle, P. (2010, January 11–12). Very Short-Term Load Forecasting Based on Neural Network and Rough Set. Proceedings of the Intelligent Computation Technology and Automation, International Conference on(ICICTA), Changsha, China.10.1109/ICICTA.2010.38 ↗
23. Electricity Market Price Forecasting Based on Weighted Nearest Neighbours Techniques10.1109/TPWRS.2007.901670 ↗
24. Energy time series forecasting based on pattern sequence similarity10.1109/TKDE.2010.227 ↗
25. Shen, W., Babushkin, V., Aung, Z., and Woon, W.L. (2013, January 22–24). An ensemble model for day-ahead electricity demand time series forecasting. Proceedings of the International Conference on Future Energy Systems, Berkeley, CA, USA.10.1145/2487166.2487173 ↗
26. Koprinska, I., Rana, M., Troncoso, A., and Martínez-Álvarez, F. (2013, January 4–9). Combining pattern sequence similarity with neural networks for forecasting electricity demand time series. Proceedings of the IEEE International Joint Conference on Neural Networks, Dallas, TX, USA.10.1109/IJCNN.2013.6706838 ↗
27. Improved pattern sequence-based forecasting method for electricity load10.1002/tee.22024 ↗
28. Wang, Z., Koprinska, I., and Rana, M. (2017, January 11–14). Pattern sequence-based energy demand forecast using photovoltaic energy records. Proceedings of the International Conference on Artificial Neural Networks, Nagasaki, Japan.
29. PSF: Introduction to R Package for Pattern Sequence Based Forecasting Algorithm10.32614/RJ-2017-021 ↗
30. Big data time series forecasting based on pattern sequence similarity and its application to the electricity demand10.1016/j.ins.2020.06.014 ↗
31. Forecasting the natural gas demand in China using a self-adapting intelligent grey model10.1016/j.energy.2016.06.090 ↗
32. Fan, G.F., Wang, A., and Hong, W.C. (2018). Combining Grey Model and Self-Adapting Intelligent Grey Model with Genetic Algorithm and Annual Share Changes in Natural Gas Demand Forecasting. Energies, 11.10.3390/en11071625 ↗
33. Application of a novel time-delayed polynomial grey model to predict the natural gas consumption in China10.1016/j.cam.2017.04.020 ↗
34. Grey-related least squares support vector machine optimization model and its application in predicting natural gas consumption demand10.1016/j.cam.2018.01.033 ↗
35. Coronavirus Optimization Algorithm: A Bioinspired Metaheuristic Based on the COVID-19 Propagation Model
36. Torres, J.F., Fernández, A.M., Troncoso, A., and Martínez-Álvarez, F. (2017). Deep Learning-Based Approach for Time Series Forecasting with Application to Electricity Load. Biomedical Applications Based on Natural and Artificial Computing, Springer International Publishing.10.1007/978-3-319-59773-7_21 ↗
37. Berriel, R.F., Lopes, A.T., Rodrigues, A., Varejão, F.M., and Oliveira-Santos, T. (2017, January 14–19). Monthly energy consumption forecast: A deep learning approach. Proceedings of the 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, AK, USA.10.1109/IJCNN.2017.7966398 ↗
38. Deep Learning for Household Load Forecasting: A Novel Pooling Deep RNN10.1109/TSG.2017.2686012 ↗
39. A deep learning model for short-term power load and probability density forecasting10.1016/j.energy.2018.07.090 ↗
40. Big data time series forecasting based on nearest neighbours distributed computing with Spark10.1016/j.knosys.2018.07.026 ↗
41. Neuroevolution: From architectures to learning10.1007/s12065-007-0002-4 ↗
42. Kandasamy, K., Neiswanger, W., Schneider, J., Póczos, B., and Xing, E. (2018). Neural Architecture Search with Bayesian Optimisation and Optimal Transport. CoRR, Available online: https://arxiv.org/abs/1802.07191.
43. Snoek, J., Larochelle, H., and Adams, R.P. (2012). Practical Bayesian Optimization of Machine Learning Algorithms. NIPS’12, Proceedings of the 25th International Conference on Neural Information Processing Systems—Volume 2, Curran Associates Inc.
44. Hu, T., Lourenço, N., Medvet, E., and Divina, F. (2020). Incremental Evolution and Development of Deep Artificial Neural Networks. Genetic Programming, Springer International Publishing.10.1007/978-3-030-44094-7 ↗
45. Sekanina, L., Hu, T., Lourenço, N., Richter, H., and García-Sánchez, P. (2019). Fast DENSER: Efficient Deep NeuroEvolution. Genetic Programming, Springer International Publishing.
46. Real, E., Aggarwal, A., Huang, Y., and Le, Q.V. (2018). Regularized Evolution for Image Classifier Architecture Search. CoRR, Available online: https://arxiv.org/abs/1802.01548.
47. Large-Scale Evolution of Image Classifiers
48. (2020, August 05). Spanish Electricity Price Market Operator. Available online: http://www.omie.es/files/flash/ResultadosMercado.html.
49. Team, T.H. (2015). H2O: R Interface for H2O. R Package Version 3.1.0.99999, H2O.ai, Inc.
50. On some extensions to GA package: Hybrid optimisation, parallelisation and islands evolution10.32614/RJ-2017-008 ↗
51. A taxonomy for the crossover operator for real-coded genetic algorithms: An experimental study10.1002/int.10091 ↗
52. Salles, R., Assis, L., Guedes, G., Bezerra, E., Porto, F., and Ogasawara, E. (2017, January 14–19). A Framework for Benchmarking Machine Learning Methods Using Linear Models for Univariate Time Series Prediction. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.10.1109/IJCNN.2017.7966139 ↗
53. Top-down Induction of Decision Trees Classifiers-a Survey10.1109/TSMCC.2004.843247 ↗
54. Therneau, T.M., Atkinson, B., and Ripley, B. (2020, August 05). rpart: Recursive Partitioning. Available online: https://rdrr.io/cran/rpart/.
55. Ridgeway, G. (2020, August 05). Generalized Boosted Models: A Guide to the Gbm Package. Available online: https://rdrr.io/cran/gbm/man/gbm.html.
56. Classification and Regression by randomForest
57. Venables, W.N., and Ripley, B.D. (2002). Modern Applied Statistics with S, Springer. [4th ed.].10.1007/978-0-387-21706-2 ↗
58. evtree: Evolutionary Learning of Globally Optimal Classification and Regression Trees in R10.18637/jss.v061.i01 ↗