Abstract
Electricity price forecasting plays an important role in the power system network, in order to promote the decision-making process for power generation and consumption. Long term forecasting is not viable as there is an uncertainty in the forecast due to increasing the integration of renewable sources with the existing grids. Since the behavior of the electricity price time sequence signal is highly non-linear and seasonal, deep neural network is the best model for learning the non-linear behavior within the data and for the purpose of forecasting. Hence this paper proposes an enhanced particle swarm optimization based long short-term memory (LSTM) neural network model, which is used to forecast the closing price of the Indian Energy Exchange. Particle swarm optimization technique is used to optimize the LSTM network input weights, which in turn minimize the forecast error with reduced architecture. This paper discusses the statistical analysis for input data selection and investigates the performance analysis for the optimal selection of layers with hidden units’ combination. Finally, the analysis deploys the best-suited configuration for forecasting the market clearing price with the least mean absolute percentage error.
Similar content being viewed by others
References
Alahi A et al (2016) Social LSTM: Human trajectory prediction in crowded spaces. In: Proceedings of 29th CVPR, Las Vegas, NV, USA, pp 961–71
Behera MK, Majumder I, Nayak N (2018) Solar photovoltaic power forecasting using optimized modified extreme learning machine technique. Eng Sci Technol Int J 21:428–438
Conejo AJ, Contreras J, Espínola R, Plazas MA (2005) Forecasting electricity prices for a day-ahead pool-based electric energy market. Int J Forecast 21(3):435–462
Duan Y, Harley RG, Habetler TG (2009) Comparison of particle swarm optimization and genetic algorithm in the design of permanent magnet motors. In: IEEE 6th international power electronics and motion control conference
Eapen RR, Simon SP, Sundareswaran K, Nayak PS (2018) User centric economic demand response management in a secondary distribution system in India. IET Renew Power Gener 13(6):834–846
Ebtehaj I, Bonakdari H, Zaji AH, Azimi H, Khoshbin F (2015) GMDH-type neural network approach for modeling the discharge coefficient of rectangular sharp-crested side weirs. Eng Sci Technol Int J 18:746–757
Feinberg EA, Genethliou D (2006) Chapter 12 load forecasting, weather. Springer, Berlin, pp 269–285
Gupta S, Chitkara P (2017) Day ahead price forecasting models in thin electricity market. In: IEEE power and energy conference at Illinois (PECI).
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Hong W-C (2016) Application of seasonal SVR with chaotic immune algorithm in traffic flow forecasting. Neural Comput Appl 21(3):583–593
Hua Y, Zhao Z, Li R, Chen X, Liu Z, Zhang H (2019) Deep learning with long short-term memory for time series prediction. IEEE Commun Mag 57(6):114–119
Mansouri V, Akbari ME (2014) Efficient short-term electricity load forecasting using recurrent neural networks. J Artif Intell Electr Eng 3(9):46–54
Moayedi H et al (2020) Optimization of ANFIS with GA and PSO estimating α ratio in driven piles. Eng Comput 36(1):227–238
Peter SE, Raglend IJ, Simon SP (2014) An architectural frame work of ANN based short term electricity price forecast engine for Indian energy exchange using similar day approach. Int J Res Eng Technol 2(4):111–122
Ravanelli M, Brakel P, Omologo M, Bagnio Y (2018) Light gated recurrent units for speech recognitio. IEEE Trans Emerg Top Comput Intell 2(2):92–102
Sapankevych NI, Sankar R (2009) Time series prediction using support vector machines: a survey. IEEE Comput Intell Mag 4(2):24–38
Saremi S, Mirjalili S (2020) A New 3D hand model, hand shape optimisation and evolutionary population dynamics for PSO and MOPSO. Optimisation algorithms for hand posture estimation. Springer, Berlin, pp 37–60
Seo J-H, Im C-H, Heo C-G, Kim J-K, Jung H-K, Lee C-G (2006) Multimodal function optimization based on particle swarm optimization. IEEE Trans Magn 42(4):1095–1098
WangJ et al (2017) Spatiotemporal modeling and prediction in cellular networks: a big data enabled deep learning approach. In: Proceedings of 36th IEEE INFOCOM, Atlanta, GA, USA, pp 1–9
Witten IH et al (2019) Data mining: practical machine learning tools and techniques, 4th edn. Morgan Kaufmann, Burlington. https://www.amazon.com/exec/obidos/ASIN/0128042915. Accessed 30 Dec 2019
Yamin HY, Shahidehpour SM, Li Z (2004) Adaptive short-term electricity price forecasting using artificial neural networks in the restructured power markets. Electr Power Energy Syst 26(8):571–581
Zhang L, Luh PB (2005) Neural network-based market clearing price prediction and confidence interval estimation with an improved extended Kalman filter method. IEEE Trans Power Syst 20(1):59–66
Zhao T, Wang J, Zhang Y (2019) Day-ahead hierarchical probabilistic load forecasting with linear quantile regression and empirical copulas. IEEE Access 7:80969–80979
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gundu, V., Simon, S.P. PSO–LSTM for short term forecast of heterogeneous time series electricity price signals. J Ambient Intell Human Comput 12, 2375–2385 (2021). https://doi.org/10.1007/s12652-020-02353-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-020-02353-9