10.1007/s40095-022-00480-x

Deep learning-based load forecasting considering data reshaping using MATLAB\Simulink

  • Zhalla Hamad1,
  • Ismael Abdulrahman*1,
  1. Department of Information System Engineering Techniques, Erbil Technical Engineering College, Erbil Polytechnic University, Erbil, Kurdistan region, 44001, IQ

Published in Issue 2022-02-16

How to Cite

Hamad, Z., & Abdulrahman, I. (2022). Deep learning-based load forecasting considering data reshaping using MATLAB\Simulink. International Journal of Energy and Environmental Engineering, 13(2 (June 2022). https://doi.org/10.1007/s40095-022-00480-x
Crossref
Scopus
Google Scholar
Europe PMC

Abstract

Abstract Load forecasting is a nonlinear problem and complex task that plays a key role in power system planning, operation, and control. A recent study proposed a deep learning approach called historical data augmentation (HDA) to improve the accuracy of the load forecasting model by dividing the input data into several yearly sub-datasets. When the original data is associated with high time step changes from 1 year to another, the approach was not found as effective as it should be for long-term forecasting because the time-series information is disconnected by the approach between the end of 1-year sub-data and the beginning of the next-year sub-data. Alternatively, this paper proposes the use of 2-year sub-dataset in order to connect the two ends of the yearly subsets. A correlation analysis is conducted to show how the yearly datasets are correlated to each other. In addition, a Simulink-based program is introduced to simulate the problem which has an advantage of visualizing the algorithm. To increase the model generalization, several inputs are considered in the model including load demand profile, weather information, and some important categorical data such as week-day and weekend data that are embedded using one-hot encoding technique. The deep learning methods used in this study are the long short-term memory (LSTM) and gated rest unit (GRU) neural networks which have been increasingly employed in the recent years for time series and sequence problems. To provide a theoretical background on these models, a new picturized detail is presented. The proposed method is applied to the Kurdistan regional load demands and compared with classical methods of data inputting demonstrating improvements in both the model accuracy and training time.

Keywords

  • Load forecasting,
  • Deep learning,
  • LSTM,
  • GRU,
  • MATLAB,
  • Simulink,
  • Kurdistan region

References

  1. Jacob (2020) Springer https://doi.org/10.1007/978-3-030-28669-9
  2. Tudose et al. (2021) Short-term load forecasting using convolutional neural networks in COVID-19 context: the Romanian case study https://doi.org/10.3390/en14134046
  3. Proedrou (2021) A comprehensive review of residential electricity load profile models (pp. 12114-12133) https://doi.org/10.1109/ACCESS.2021.3050074
  4. Burg et al. (2021) Comparative analysis of load forecasting models for varying time horizons and load aggregation levels 14(21) https://doi.org/10.3390/en14217128
  5. Haben (2021) Review of low voltage load forecasting: methods, applications, and recommendations https://doi.org/10.1016/j.apenergy.2021.117798
  6. Vanting et al. (2021) A scoping review of deep neural networks for electric load forecasting https://doi.org/10.1186/s42162-021-00148-6
  7. Azeem et al. (2021) Electrical load forecasting models for different generation modalities: a review (pp. 142239-142263) https://doi.org/10.1109/ACCESS.2021.3120731
  8. Mamun et al. (2020) A comprehensive review of the load forecasting techniques using single and hybrid predictive models (pp. 134911-134939) https://doi.org/10.1109/ACCESS.2020.3010702
  9. Li (2021) A survey on investment demand assessment models for power grid infrastructure (pp. 9048-9054) https://doi.org/10.1109/ACCESS.2021.3049601
  10. Kuster et al. (2017) Electrical load forecasting models: a critical systematic review (pp. 257-270) https://doi.org/10.1016/j.scs.2017.08.009
  11. Hong et al. (2020) Energy forecasting: a review and outlook (pp. 376-388) https://doi.org/10.1109/OAJPE.2020.3029979
  12. Acaroğlu and Márquez (2021) Comprehensive review on electricity market price and load forecasting based on wind energy https://doi.org/10.3390/en14227473
  13. Hoori et al. (2020) Electric load forecasting model using a multicolumn deep neural networks 67(8) (pp. 6473-6482) https://doi.org/10.1109/TIE.2019.2939988
  14. Lai (2020) Load forecasting based on deep neural network and historical data augmentation 14(24) (pp. 5927-5934) https://doi.org/10.1049/iet-gtd.2020.0842
  15. Sehovac and Grolinger (2020) Deep learning for load forecasting: sequence to sequence recurrent neural networks with attention (pp. 36411-36426) https://doi.org/10.1109/ACCESS.2020.2975738
  16. Goh (2021) Multi-convolution feature extraction and recurrent neural network dependent model for short-term load forecasting (pp. 118528-118540) https://doi.org/10.1109/ACCESS.2021.3107954
  17. Kong et al. (2020) Multimodal feature extraction and fusion deep neural networks for short-term load forecasting (pp. 185373-185383) https://doi.org/10.1109/ACCESS.2020.3029828
  18. Deng et al. (2019) Multi-scale convolutional neural network with time-cognition for multi-step short-term load forecasting (pp. 88058-88071) https://doi.org/10.1109/ACCESS.2019.2926137
  19. Shao and Kim (2020) Multi-step short-term power consumption forecasting using multi-channel LSTM with time location considering customer behavior (pp. 125263-125273) https://doi.org/10.1109/ACCESS.2020.3007163
  20. Li (2021) A novel hybrid short-term load forecasting method of smart grid using MLR and LSTM neural network 17(4) (pp. 2443-2452) https://doi.org/10.1109/TII.2020.3000184
  21. Sajjad (2020) A novel CNN-GRU-based hybrid approach for short-term residential load forecasting (pp. 143759-143768) https://doi.org/10.1109/ACCESS.2020.3009537
  22. A novel short-term load forecasting method by combining the deep learning with singular spectrum analysis
  23. Rafi et al. (2021) A short-term load forecasting method using integrated CNN and LSTM network (pp. 32436-32448) https://doi.org/10.1109/ACCESS.2021.3060654
  24. Pirbazari et al. (2021) An ensemble approach for multi-step ahead energy forecasting of household communities (pp. 36218-36240) https://doi.org/10.1109/ACCESS.2021.3063066
  25. Gunawan and Huang (2021) An extensible framework for short-term holiday load forecasting combining dynamic time warping and LSTM network (pp. 106885-106894) https://doi.org/10.1109/ACCESS.2021.3099981
  26. Yu et al. (2019) Deep learning for daily peak load forecasting–a novel gated recurrent neural network combining dynamic time warping (pp. 17184-17194) https://doi.org/10.1109/ACCESS.2019.2895604
  27. Shao et al. (2020) Domain fusion CNN-LSTM for short-term power consumption forecasting (pp. 188352-188362) https://doi.org/10.1109/ACCESS.2020.3031958
  28. Neeraj et al. (2020) EMD-Att-LSTM: a data-driven strategy combined with deep learning for short-term load forecasting https://doi.org/10.35833/MPCE.2020.000626
  29. Razavi et al. (2020) From load to net energy forecasting: short-term residential forecasting for the blend of load and PV behind the meter (pp. 224343-224353) https://doi.org/10.1109/ACCESS.2020.3044307
  30. Alhussein et al. (2020) Hybrid CNN-LSTM model for short-term individual household load forecasting (pp. 180544-180557) https://doi.org/10.1109/ACCESS.2020.3028281
  31. Jiang et al. (2021) Hybrid multitask multi-information fusion deep learning for household short-term load forecasting 12(6) (pp. 5362-5372) https://doi.org/10.1109/TSG.2021.3091469
  32. Kong et al. (2019) Short-term residential load forecasting based on LSTM recurrent neural network 10(1) (pp. 841-851) https://doi.org/10.1109/TSG.2017.2753802
  33. Obst et al. (2021) Adaptive methods for short-term electricity load forecasting during COVID-19 lockdown in France 36(5) (pp. 4754-4763) https://doi.org/10.1109/TPWRS.2021.3067551
  34. Park et al. (2020) Missing-insensitive short-term load forecasting leveraging autoencoder and LSTM (pp. 206039-206048) https://doi.org/10.1109/ACCESS.2020.3036885
  35. Farsi et al. (2021) On short-term load forecasting using machine learning techniques and a novel parallel deep LSTM-CNN approach (pp. 31191-31212) https://doi.org/10.1109/ACCESS.2021.3060290
  36. Dudek et al. (2020) A hybrid residual dilated LSTM and exponential smoothing model for midterm electric load forecasting https://doi.org/10.1109/TNNLS.2020.3046629
  37. Han et al. (2019) Enhanced deep networks for short-term and medium-term load forecasting (pp. 4045-4055) https://doi.org/10.1109/ACCESS.2018.2888978
  38. Motepe et al. (2019) Improving load forecasting process for a power distribution network using hybrid AI and deep learning algorithms (pp. 82584-82598) https://doi.org/10.1109/ACCESS.2019.2923796
  39. Vu et al. (2021) Recurring multi-layer moving window approach to forecast day-ahead and week-ahead load demand considering weather conditions https://doi.org/10.35833/MPCE.2021.000210
  40. Mustaqeem and Kwon (2021) Short-term energy forecasting framework using an ensemble deep learning approach (pp. 94262-94271) https://doi.org/10.1109/ACCESS.2021.3093053
  41. Shang et al. (2021) Short-term load forecasting based on PSO-KFCM daily load curve clustering and CNN-LSTM model (pp. 50344-50357) https://doi.org/10.1109/ACCESS.2021.3067043
  42. Zheng et al. (2020) Short-term load forecasting of power system based on neural network intelligent algorithm https://doi.org/10.1109/ACCESS.2020.3021064
  43. Jiao et al. (2018) Short-term non-residential load forecasting based on multiple sequences LSTM recurrent neural network (pp. 59438-59448) https://doi.org/10.1109/ACCESS.2018.2873712
  44. Tan et al. (2020) Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning 35(4) (pp. 2937-2948) https://doi.org/10.1109/TPWRS.2019.2963109
  45. Wang et al. (2020) Ensemble learning for load forecasting 4(2) (pp. 616-628) https://doi.org/10.1109/TGCN.2020.2987304
  46. Ali (2020) Midterm load forecasting analysis for Erbil Governorate based on predictive model 32(3) (pp. 20-29)
  47. E. Taherifard: Load and demand forecasting in Iraqi Kurdistan using time series modelling. Degree Project in Engineering, First Level, 15 Hp Stockholm, Sweden (2019)
  48. J. Brownlee: Long short-term memory networks with python: develop sequence prediction models with deep learning. Machine Learning Mastery, (2017)
  49. Kurdistan central dispatch control, ministry of electricity–Kurdistan regional government, Iraq, (2021)
  50. Directory of dispatch control in Erbil, ministry of electricity–Kurdistan regional government, Iraq, (2021). KT