DEEP LEARNING APPROACH TO FORECASTING ELECTRICITY PRICE FROM LOAD DATA

Vladimir BABUSHKIN, Gheorghe CĂPĂȚÂNĂ

Abstract


The accurate forecasting of electricity price and load is essential for maintaining a stable interplay between demand and supply in the dynamic electricity market. In this work we propose a deep Convolutional Neural Network-based model for day-ahead electricity price forecasting from historical price/load data and predicted load values. The model was tested on the data for New York and New South Wales and demonstrated high prediction accuracy for both datasets.

 

APLICAREA INVĂȚĂRII PROFUNDE LA PROGNOZA PREȚULUI ELECTRICITĂȚII  DIN DATE DE ÎNCĂRCARE

Previziunea exactă a prețului și încărcării energiei electrice este esențială pentru menținerea unei interacțiuni stabile între cerere și ofertă pe piața dinamică a energiei electrice. În articol este descris un model profund bazat pe rețeaua neuronală convoluțională pentru prognozele viitoare ale prețului energiei electrice din datele istorice ale prețului / tarifelor și valorile prognozate ale tarifelor. Modelul a fost testat pe datele pentru New York și New South Wales și a demonstrat o precizie ridicată a predicțiilor pentru ambele seturi de date.


Keywords


Deep Learning, Machine Learning, Long-Short Term Memory Networks, Convolutional Neural Networks.

Full Text:

PDF

References


STOFT, S. Power system economics: designing markets for electricity, Piscataway, NJ: IEEE Press, 2002, p.1-46, ISBN 0-471-15040-1, Available: http://stoft.com/metaPage/lib/Stoft-2002-PSE-Ch-1-3,4,5,6.pdf [Accessed: 27.07.2020]

Energy Market & Operational Data, New York Independent System Operator, [Online]. Available: https://www.nyiso.com/energy-market-operational-data [Accessed: 20.04.2020]

Aggregated price and demand data, Australian Energy Market Operator, [Online]. Available: https://www.aemo.com.au/energy-systems/electricity/national-electricity-market-nem/data-nem/aggregated-data [Accessed: 20.04.2020]

SINGHAL, D., SWARUP, S. Electricity price forecasting using artificial neural networks. In: International Journal of Electrical Power & Energy Systems, vol.33, p.550-555, March 2011. ISSN: 0142-0615. DOI: 10.1016/j.ijepes.2010.12.009

HIPPERT, H.S., PEDREIRA, C.E., SOUZA, R., C. Neural Networks for Short-Term Load Forecasting: A review and Evaluation. In: IEEE Transactions on Power Systems, Vol.16, No.1, 2011, p.44-55. Print ISSN: 0885-8950. Electronic ISSN: 1558-0679. DOI: 10.1109/59.910780

EKONOMOU L., CHRISTODOULOU, C., A., MLADENOV, V. A short-term load forecasting method using artificial neural networks and wavelet analysis. In: International Journal of Power Systems, vol.1, p.64-68, 2016. Available: http://www.iaras.org/iaras/journals/ijps [Accessed: 27.07.2020]. ISSN: 2367-8976

REIS, A.J.R., A.P.A. da SILVA. Feature extraction via multiresolution analysis for short-term load forecasting. In: IEEE Transactions on Power Systems, Vol.20, Issue: 1, Feb. 2005, p.189–198, Available: https://ieeexplore.ieee.org/document/1388509 [Accessed: 27.07.2020]. Print ISSN: 0885-8950. Electronic ISSN: 1558-0679. DOI: 10.1109/TPWRS.2004.840380

KOPRINSKA, I., RANA, M., TRONCOSO, A., MARTÍNEZ-ÁLVAREZ, F. Combining Pattern Sequence Similarity with neural networks for forecasting electricity demand time series. In: Proceedings of the International Joint Conference on Neural Networks, Dallas, Texas, USA, August 4-9, 2013, p.940-947. ISBN 9781467361279

HINTON, G., E., OSINDERO, S, TEH, Y-W. A fast learning algorithm for deep belief nets. In: Neural computation, 2006, vol.18, p.1527-54. ISSN: 0941-0643 (Print) 1433-3058 (Online). Available: http://www.cs.toronto.edu/~fritz/absps/ncfast.pdf [Accessed: 27.07.2020]

BOUKTIF, S., FIAZ, A., OUNI, A., SERHANI, M. A. Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches. In: Energies, June 2018, no.11(7), p.1636. ISSN (electronic) 1996-1073. DOI: 10.3390/en11071636

QIU, X., ZHANG, L., REN, Y., SUGANTHAN, P. N., AMARATUNDA, G. Ensemble deep learning for regression and time series forecasting. In: IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL), December 2014. DOI: 10.1109/CIEL.2014.7015739

BUSSETI, E., OSBAND, I., WONG, S. Deep learning for time series modeling, CS 229 Final Project Report, Stanford University, December 14th, 2012. Available: http://cs229.stanford.edu/proj2012/BussetiOsbandWong-DeepLearning¬ForTimeSeriesModeling.pdf [Accessed: 27.07.2020]

MERKEL, G.D., POVINELLI, R.J., BROWN, R., H. Short-Term Load Forecasting of Natural Gas with Deep Neural Network Regression. In: Energies, 2008, vol.11. ISSN (electronic) 1996-1073. DOI: 10.3390/en11082008

KUREMOTO, T., KIMURA, S., KOBAYASHI, K., OBAYASHI, M. Time Series Forecasting Using Restricted Boltzmann Machine. In: Neurocomputing 137:47-56, August 2014. ISSN 0925-2312 DOI: 10.1016/j.neucom.2013.03.047

MOCANU, E., NGUYEN, H., P., GIBESCU, M., KLING, W., L. Deep Learning for Estimating Building Energy Consump¬tion. In: Sustainable Energy, Grids and Networks, 6, 91–99. ISSN: 2352-4677. https://doi.org/10.1016/j.segan.2016.02.005

WEI, L.-Y., CHIH-HUNG, T., CHUNG, Y.-C., KUO-HSIUNG, L., CHUEH, H.-E., C., LIN, J.-S. A Study of the Hybrid Recurrent Neural Network Model for Electricity Loads Forecasting. In: International Journal of Academic Research in Accounting, Finance and Management Sciences, vol.7, no.2, April 2017, p.21-29. E-ISSN: 2225-8329, P-ISSN: 2308-0337. DOI: 10.6007/IJARAFMS/v7-i2/2786

SHI, H., XU, M., Li, R. Deep Learning for Household Load Forecasting - A Novel Pooling Deep RNN. In: IEEE Transactions on Smart Grid, vol.9, Issue: 5 Sept. 2018, p.5271-5280. Print ISSN: 1949-3053. Electronic ISSN: 1949-3061DOI: 10.1109/TSG.2017.2686012

HOCHREITER, S., SCHMIDHUBER, J. Long-short term memory, In: Neural Computation, vol.9, no.8, p.1735-1780, November 1997. Print ISSN 0941-0643. Electronic ISSN 1433-3058. https://doi.org/10.1162/neco.1997.9.8.1735

GENSLER, A. HENZE, J., SICK, B., RAABE, N. Deep Learning for solar power forecasting - An approach using Auto Encoder and LSTM Neural Networks. In: 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), October 2016. DOI: 10.1109/SMC.2016.7844673

SHAHZAD, M., AFSHIN, A. Short-Term Load Forecasts Using LSTM Networks. In: Science Direct, 10th International Conference on Applied Energy (ICAE2018), 22-25 August 2018, Hong Kong, China. Energy Procedia, 158 (2019) 2922-2927, vol.158, p.2922-2927, 2019. Available online at www.sciencedirect.com

MARINO, D., L., AMARASINGHE, K., MANIC, M. Building energy load forecasting using Deep Neural Networks. In: IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society, 2016, p.1-6. Electronic ISBN: 978-1-5090-3474-1. Print on Demand(PoD) ISBN: 978-1-5090-3475-8DOI: 10.1109/IECON.2016.7793413

ZHENG, J., XU, C., ZNANG Z., LI, X. Electric Load Forecasting in Smart Grids Using Long-Short-Term-Memory based Recurrent Neural Network. In: 2017 51st Annual Conference on Information Sciences and Systems (CISS). 22-24 March 2017, Baltimore, MD, USA, Electronic ISBN: 978-1-5090-4780-2. Print on Demand(PoD) ISBN: 978-1-5090-2697-5. DOI: 10.1109/CISS.2017.7926112

DU, S., LI, T., GONG, X., Yu Y., HORNG, S.-J. Traffic flow forecasting based on hybrid deep learning framework. In: 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), 2017. ISBN: 9781538618301

KUO, P.-H., HUANG, C.-J. A High Precision Artificial Neural Networks Model for Short-Term Energy Load Forecasting. In: Energies, vol.11(1): 213, January 2018, p.1-13. ISSN (electronic) 1996-1073. DOI: 10.3390/en11010213

AMARASINGHE K., A., MARINO, D. L., MILOS, M. Deep neural networks for energy load forecasting. In: 2017 IEEE 26th International Symposium on Industrial Electronics (ISIE 2017), 19-21 June 2017, Edinburgh, Scotland, United Kingdom, p.1-6. ISBN: 9781509014132. Available: http://www.people.vcu.edu/~mmanic/papers/2017/ISIE2017_AmarMarinoManic_DLEnergyPrediction.pdf [Accessed: 27.07.2020]

KUO, P.-H., HUANG, C.-J. An Electricity Price Forecasting Model by Hybrid Structured Deep Neural Networks. In: Sustainability, vol.10(4), April 2018, p.1-17. ISSN 2071-1050. https://doi.org/10.3390/su10041280

HU, L., TAYLOR, G., WAN, H.-B., IRVING, M. A review of short-term electricity price forecasting techniques in deregulated electricity markets. In: 44th International Universities Power Engineering Conference (UPEC 2009), 1-4 September 2009, Glasgow, United Kingdom, p.1-6. ISBN: 9780947649456.

CONTRERAS, J., ESPINOLA, R., NOGALES, F. G., CONEJO, A. J. ARIMA models to predict next-day electricity prices. In: IEEE Transactions on Power Systems, vol.18, Issue: 3, Aug. 2003, p.1014-1020. ISSN 08858950, DOI: 10.1109/TPWRS.2002.804943

TAN, Z., ZHANG, J., WANG, J., XU, J. Day-ahead electricity price forecasting using wavelet transform combined with ARIMA and GARCH models. In: Applied Energy, vol.87, no.11, p.3606-3610, 2010. ISSN: 0306-2619, https://doi.org/10.1016/j.apenergy.2010.05.012

VORONIN, S., PARTANEN, J. Price forecasting in the day-ahead energy market by an iterative method with separate normal price and price spike frameworks. In: Energies, vol.6 (11), p.5897-5920, November 2013. ISSN (electronic) 1996-1073. DOI: 10.3390/en6115897

SINGH, N. K., TRIPATHY, M., SINGH, A. K. A radial basis function neural network approach for multi-hour short term load-price forecasting with type of day parameter. In: 6th International Conference on Industrial and Information Systems, 16-19 August 2011, p.316-321. Print ISSN: 2164-7011. DOI: 10.1109/ICIINFS.2011.6038087

JESUS, L., RIDDER F., D., SCHUTTER B., D. Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms. In: Applied Energy, vol.221, p.386-405, July 2018. ISSN: 0306-2619. DOI: 10.1016/j.apenergy.2018.02.069

DORFFNER, G. Neural Networks for Time Series Processing. Vol.6. Neural Network World, 1996, p.447-468. ISSN 23364335, 12100552

NEUPANE, B., WOON, W. L., AUNG, Z. Ensemble Prediction Model with Expert Selection for Electricity Price Forecasting. In: Energies, 10(1), January, 2017. ISSN (electronic) 1996-1073. DOI: 10.3390/en10010077


Refbacks

  • There are currently no refbacks.