An intelligent approach towards very short-term load forecasting
-
Uttamarani Pati
and
Arvind R. Singh
Abstract
Very short term load forecasting (VSTLF) plays a pivotal role in helping the utility workers make proper decisions regarding generation scheduling, size of spinning reserve, and maintaining equilibrium between the power generated by the utility to fulfil the load demand. However, the development of an effective VSTLF model is challenging in gathering noisy real-time data and complicates features found in load demand variations from time to time. A hybrid approach for VSTLF using an incomplete fuzzy decision system (IFDS) combined with a genetic algorithm (GA) based feature selection technique for load forecasting in an hour ahead format is proposed in this research work. This proposed work aims to determine the load features and eliminate redundant features to form a less complex forecasting model. The proposed method considers the time of the day, temperature, humidity, and dew point as inputs and generates output as forecasted load. The input data and historical load data are collected from the Northern Regional Load Dispatch Centre (NRLDC) New Delhi for December 2009, January 2010 and February 2010. For validation of proposed method efficacy, it’s performance is further compared with other conventional AI techniques like ANN and ANFIS, which are integrated with genetic algorithm-based feature selection technique to boost their performance. These techniques’ accuracy is tested through their mean absolute percentage error (MAPE) and normalized root mean square error (nRMSE) value. Compared to other conventional AI techniques and other methods provided through previous studies, the proposed method is found to have acceptable accuracy for 1 h ahead of electrical load forecasting.
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: None declared.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
Parameters for ANN.
| Network Type | Feed forward back | ||
|---|---|---|---|
| Training function | Levenberg-Marquardt | ||
| Size of hidden layer | 1 | ||
| No. of nodes of hidden layer | Without feature selection | With feature selection | |
| 10 | 10 | ||
| No. of inputs | 4 | 8 | |
| Size of output layer | 1 | ||
| Performance function | MAPE | ||
| Epoch | 1000 | ||
Structural details for ANFIS.
| Feature selection based on GA | Excluded | Included |
|---|---|---|
| Structure | Subclustering | |
| Optimization | Hybrid | |
| No. of inputs | 4 | 8 |
| No. of membership function of each input | 10 | 21 |
| No. of rules | 11 | 21 |
Structure of ANFIS model used in IFDS.
| Feature selection based on GA | Excluded | Included |
|---|---|---|
| Structure | Subclustering | |
| Optimization | Hybrid | |
| No. of inputs | 3 | 6 |
| No. of membership function of each input | 6 | 10 |
| No. of rules | 10 | 11 |
References
1. Nti, IK, Teimeh, M, Nyarko-Boateng, O, Adekoya, AF. Electricity load forecasting: a systematic review. J Electr Syst Inf Technol 2020;7. https://doi.org/10.1186/s43067-020-00021-8.Search in Google Scholar
2. Masa-Bote, D, Castillo-Cagigal, M, Matallanas, E, Caamaño-Martín, E, Gutiérrez, A, Monasterio-Huelín, F, et al.. Improving photovoltaics grid integration through short time forecasting and self-consumption. Appl Energy 2014;125:103–13. https://doi.org/10.1016/j.apenergy.2014.03.045.Search in Google Scholar
3. Li, S, Wang, P, Goel, L. Short-term load forecasting by wavelet transform and evolutionary extreme learning machine. Elec Power Syst Res 2015;122:96–103. https://doi.org/10.1016/j.epsr.2015.01.002.Search in Google Scholar
4. Wang, R, Wang, J, Xu, Y. A novel combined model based on hybrid optimization algorithm for electrical load forecasting. Appl Soft Comput 2019;82. https://doi.org/10.1016/j.asoc.2019.105548.Search in Google Scholar
5. Walther, J, Spanier, D, Panten, N, Abele, E. Very short-term load forecasting on factory level – a machine learning approach. Procedia CIRP 2019;80:705–10. https://doi.org/10.1016/j.procir.2019.01.060.Search in Google Scholar
6. Kong, X, Li, C, Wang, C, Zhang, Y, Zhang, J. Short-term electrical load forecasting based on error correction using dynamic mode decomposition. Appl Energy 2020:261.10.1016/j.apenergy.2019.114368Search in Google Scholar
7. Hammad, MA, Jereb, B, Rosi, B, Dragan, D. Methods and models for electric load forecasting: a comprehensive review. Logist Sustain Transport 2020;11:51–76. https://doi.org/10.2478/jlst-2020-0004.Search in Google Scholar
8. Mamlook, R, Badran, O, Abdulhadi, E. A fuzzy inference model for short-term load forecasting. Energy Pol 2009;37:1239–48. https://doi.org/10.1016/j.enpol.2008.10.051.Search in Google Scholar
9. Çevik, HH, Çunkaş, M. Short-term load forecasting using fuzzy logic and ANFIS. Neural Comput Appl 2015;26:1355–67. https://doi.org/10.1007/s00521-014-1809-4.Search in Google Scholar
10. Ali, D, Yohanna, M, Puwu, MI, Garkida, BM. Long-term load forecast modelling using a fuzzy logic approach. Pac Sci Rev A: Nat Sci Eng 2016;18:123–7. https://doi.org/10.1016/j.psra.2016.09.011.Search in Google Scholar
11. Ebrahimi, A, Moshari, A. Holidays short-term load forecasting using fuzzy improved similar day method. Int Trans Electr Energy Syst 2012;23:1254–71. https://doi.org/10.1002/etep.1650.Search in Google Scholar
12. Wi, Y-M, Joo, S-K, Song, K-B. Holiday load forecasting using fuzzy polynomial regression with weather feature selection and adjustment. IEEE Trans Power Syst 2012;27:596–603. https://doi.org/10.1109/tpwrs.2011.2174659.Search in Google Scholar
13. Panapakidis, IP. Clustering based day-ahead and hour-ahead bus load forecasting models. Int J Electr Power Energy Syst 2016;80:171–8. https://doi.org/10.1016/j.ijepes.2016.01.035.Search in Google Scholar
14. Chang, GW, Lu, H-J, Wang, P-K, Chang, Y-R, Lee, Y-D. Gaussian mixture model-based neural network for short-term wind power forecast. Int Trans Electr Energy Syst 2017;27. https://doi.org/10.1002/etep.2320.Search in Google Scholar
15. Xiao, L, Wang, J, Yang, X, Xiao, L. A hybrid model based on data preprocessing for electrical power forecasting. Int J Electr Power Energy Syst 2015;64:311–27. https://doi.org/10.1016/j.ijepes.2014.07.029.Search in Google Scholar
16. Chen, K, Chen, K, Wang, Q, He, Z, Hu, J, He, J. Short-term load forecasting with deep residual networks. IEEE Trans Smart Grid 2019;10:3943–52. https://doi.org/10.1109/tsg.2018.2844307.Search in Google Scholar
17. Kebir, N, Lamallam, A, Moussa, A. Daily peak-based short-term demand prediction using backpropagation combined to chi-squared distribution. Int J Emerg Elec Power Syst 2020;21.10.1515/ijeeps-2020-0098Search in Google Scholar
18. Barak, S, Sadegh, SS. Forecasting energy consumption using ensemble ARIMA–ANFIS hybrid algorithm. Int J Electr Power Energy Syst 2016;82:92–104. https://doi.org/10.1016/j.ijepes.2016.03.012.Search in Google Scholar
19. Laouafi, A, Mordjaoui, M, Dib, D. One-hour ahead electric load forecasting using neuro-fuzzy system in a parallel approach. In: Azar, A, Vaidyanathan, S, editors. Computational intelligence applications in modeling and control. Studies in computational intelligence. Cham, Switzerland AG: Springer; 2015:95–121 pp.10.1007/978-3-319-11017-2_5Search in Google Scholar
20. Heydari, A, Astiaso Garcia, D, Keynia, F, Bisegna, F, De Santoli, L. Hybrid intelligent strategy for multifactor influenced electrical energy consumption forecasting. Energy Sources B Energy Econ Plann 2019;14:341–58. https://doi.org/10.1080/15567249.2020.1717678.Search in Google Scholar
21. Capuno, M, Kim, J-S, Song, H. Very short-term load forecasting using hybrid algebraic prediction and support vector regression. Math Probl Eng 2017:1–9. https://doi.org/10.1155/2017/8298531.Search in Google Scholar
22. Alamaniotis, M, Ikonomopoulos, A, Tsoukalas, LH. Evolutionary multiobjective optimization of Kernel-based very-short-term load forecasting. IEEE Trans Power Syst 2012;27:1477–84. https://doi.org/10.1109/tpwrs.2012.2184308.Search in Google Scholar
23. Guan, C, Luh, PB, Michel, LD, Wang, Y, Friedland, PB. Very short-term load forecasting: wavelet neural networks with data pre-filtering. IEEE Trans Power Syst 2013;28:30–41. https://doi.org/10.1109/tpwrs.2012.2197639.Search in Google Scholar
24. Guan, C, Luh, PB, Michel, LD, Chi, Z. Hybrid Kalman filters for very short-term load forecasting and prediction interval estimation. IEEE Trans Power Syst 2013;28:3806–17. https://doi.org/10.1109/tpwrs.2013.2264488.Search in Google Scholar
25. Li, S, Goel, L, Wang, P. An ensemble approach for short-term load forecasting by extreme learning machine. Appl Energy 2016;170:22–9. https://doi.org/10.1016/j.apenergy.2016.02.114.Search in Google Scholar
26. Pindoriya, NM, Singh, SN, Singh, SK. Forecasting of short-term electric load using application of wavelets with feed-forward neural networks. Int J Emerg Elec Power Syst 2010;11:1–24. https://doi.org/10.2202/1553-779x.2289.Search in Google Scholar
27. Tarsitano, A, Amerise, IL. Short-term load forecasting using a two-stage sarimax model. Energy 2017;133:108–14. https://doi.org/10.1016/j.energy.2017.05.126.Search in Google Scholar
28. Park, DC, El-Sharkawi, MA, Marks, RJ, Atlas, LE, Damborg, MJ. Electric load forecasting using an artificial neural network. IEEE Trans Power Syst 1991;6:442–9. https://doi.org/10.1109/59.76685.Search in Google Scholar
29. Mustapha, M, Mustafa, MW, Khalid, SN, Abubakar, I, Abdilahi, AM. Correlation and wavelet-based short-term load forecasting using anfis. Indian J Sci Technol 2016;9. https://doi.org/10.17485/ijst/2016/v9i46/107141.Search in Google Scholar
30. Pawlak, Z. Rough set theory and its applications to data analysis. Cybern Syst 1998;29:661–88. https://doi.org/10.1080/019697298125470.Search in Google Scholar
31. Li, F, Qiu, J-J, Cao, YJ. Performance of the novel rough fuzzy-neural network on short-term load forecasting. In: IEEE PES power systems conference and exposition. IEEE, New York, NY; 2004.Search in Google Scholar
32. Daubechies, I, Heil, C. Ten lectures on wavelets. Philadelphia, PA: Society For Industrial and Applied Mathematics; 1992:6.10.1137/1.9781611970104Search in Google Scholar
33. Ray, P, Senroy, N, Panigrahi, BK. Hybrid methodology for fault distance estimation in series compensated transmission line. IET Gener., Transm Distrib 2013;7:431–9. https://doi.org/10.1049/iet-gtd.2012.0243.Search in Google Scholar
34. Holland, JH. Genetic algorithms. Sci Am 1992;267:66–72. https://doi.org/10.1038/scientificamerican0792-66.Search in Google Scholar
35. Ray, P, Sen, S, Barisal, AK. Hybrid methodology for short-term load forecasting. In: 2014 IEEE international conference on power electronics, drives and energy systems (PEDES). IEEE, Mumbai; 2014.10.1109/PEDES.2014.7041963Search in Google Scholar
36. Khair, U, Fahmi, H, Hakim, SA, Rahim, R. Forecasting error calculation with mean absolute deviation and mean absolute percentage error. J Phys Conf 2017;930. https://doi.org/10.1088/1742-6596/930/1/012002.Search in Google Scholar
37. Lusis, P, Khalilpour, KR, Andrew, L, Liebman, A. Short-term residential load forecasting: impact of calendar effects and forecast granularity. Appl Energy 2017;205:654–69. https://doi.org/10.1016/j.apenergy.2017.07.114.Search in Google Scholar
38. Kouhi, S, Keynia, F, Najafi Ravadanegh, S. A new short-term load forecast method based on neuro-evolutionary algorithm and chaotic feature selection. Int J Electr Power Energy Syst 2014;62:862–7. https://doi.org/10.1016/j.ijepes.2014.05.036.Search in Google Scholar
39. Rodrigues, F, Cardeira, C, Calado, JMF. The daily and hourly energy consumption and load forecasting using artificial neural network method: a case study using a set of 93 households in Portugal. Energy Procedia 2014;62:220–9. https://doi.org/10.1016/j.egypro.2014.12.383.Search in Google Scholar
40. Rana, M, Koprinska, I. Forecasting electricity load with advanced wavelet neural networks. Neurocomputing 2016;182:118–32. https://doi.org/10.1016/j.neucom.2015.12.004.Search in Google Scholar
41. Muzaffar, S, Afshari, A. Short-term load forecasts using LSTM networks. Energy Procedia 2019;158:2922–7. https://doi.org/10.1016/j.egypro.2019.01.952.Search in Google Scholar
42. Liu, J, Li, C. The short-term power load forecasting based on sperm whale algorithm and wavelet least square support vector machine with DWT-IR for feature selection. Sustainability 2017;9:1188. https://doi.org/10.3390/su9071188.Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- Pre-diagnosis technology for short-circuit withstand capability of distribution transformer based on big data
- Residual flux impact in controlled switching of HVDC converter transformer
- A novel transient search optimization for optimal allocation of multiple distributed generator in the radial electrical distribution network
- Characterization of nano-additive filled epoxy resin composites (ERC) for high voltage gas insulated switchgear (GIS) applications
- An intelligent approach towards very short-term load forecasting
- Allocation of active power losses to generators in electric power networks
- Optimization of controller gains to enhance power quality of standalone wind energy conversion system
- A flexible power management strategy for PV-battery based interconnected DC microgrid
- Slow flow solutions and stability analysis of single machine to infinite bus power systems
Articles in the same Issue
- Frontmatter
- Research Articles
- Pre-diagnosis technology for short-circuit withstand capability of distribution transformer based on big data
- Residual flux impact in controlled switching of HVDC converter transformer
- A novel transient search optimization for optimal allocation of multiple distributed generator in the radial electrical distribution network
- Characterization of nano-additive filled epoxy resin composites (ERC) for high voltage gas insulated switchgear (GIS) applications
- An intelligent approach towards very short-term load forecasting
- Allocation of active power losses to generators in electric power networks
- Optimization of controller gains to enhance power quality of standalone wind energy conversion system
- A flexible power management strategy for PV-battery based interconnected DC microgrid
- Slow flow solutions and stability analysis of single machine to infinite bus power systems
