SpringerLink
Log in

Transfer learning: a cross domain LSTM way towards sustainable power predictive analytics

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The most prevalent sustainable power generating resource that is reliable and widely installed for household or smaller localities is solar panels. With government subsidies and grants it has much more monetary benefits than rising cost of electricity generated by fossil fuels. However, with very basic working of solar power the power generation and consumption peaks are quite contrasting. Power is generated at peak in the afternoon time and hit its low in the evening and night; but, the usage is at the peak after sun sets. To boot, they can minimize and eventually eliminate the need for electric grid connectivity and create isolated off-grid systems. However, this needs a strong analytics system both pre and post installation of renewable power generation system. Data driven predictive modelling is a prevalent and effective technique but requires sufficient amount of data for training. Furthermore, with the new ventures under consideration for installation this history is either not available or insufficient for training the deep learning (DL) model. Nevertheless, history is available in abundance for older plants or farms with same or similar domains.This paper proposes a novel cross domain LSTM based parameterized transfer learning (TL) model for short term predictive analytics. The model is trained using temporal and uncertain characteristics of wind power NREL data available in sufficiency for training LSTM and used for the predictive analytics of newly built ventures with insufficient data availability. A parameterized transfer technique is applied to two different domains. One has characteristics related to source wind power domain i.e. solar plant and second one is completely unrelated i.e. Electric Vehicle charging station (EVCS). Both the target domains have unrelated tasks from source domain to make predictions using knowledge gained from the source domain. Quantitative analysis of experiments show Root mean square error (RMSE) for solar power domain is improved as high as 517% using TL and for EV domain upto 133%. The results show TL can be a new effective power analytics method across domains with this improved RMSE for cross domain predictive analytics having a target with insufficient historic data.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Algorithm 1
Algorithm 2
Algorithm 3
Algorithm 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

Data Availibility Statement

Data is available in the public domain.

Code Availibility

Available on demand.

Notes

  1. https://www.nrel.gov/wind/data-tools.html

  2. https://www.kaggle.com/datasets/pythonafroz/solar-power

References

  1. U.S. Department of Energy (2021) Installing and maintaining a small wind electric system. https://www.energy.gov/energysaver/installing-and-maintaining-small-wind-electric-system Accessed 2022-07-14

  2. Solar Energy Industries Association (2021) Solar industry research data. https://www.seia.org/solar-industry-research-data Accessed Jul 18 2022

  3. Busseti E, Osband I, Wong S (2012) Deep learning for time series modeling. Technical report, Stanford University, pp 1–5

  4. Guarino A, Grilli L, Santoro D, Messina F, Zaccagnino R (2022) To learn or not to learn? Evaluating autonomous, adaptive, automated traders in cryptocurrencies financial bubbles. Neural Comput Appl 34(23):20715–20756

    Google Scholar 

  5. Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Know Data Eng 22(10):1345–1359

    Google Scholar 

  6. Xun L, Zhang J, Yao F, Cao D (2022) Improved identification of cotton cultivated areas by applying instance-based transfer learning on the time series of modis ndvi. CATENA 213:106130

    Google Scholar 

  7. He Q-Q, Siu SWI, Si Y-W (2022) Instance-based deep transfer learning with attention for stock movement prediction. Appl Intell 1–22

  8. Vincent V, Wannes M, Jesse D (2020) Transfer learning for anomaly detection through localized and unsupervised instance selection. Proc AAAI Conf Artif Intell 34:6054–6061

    Google Scholar 

  9. Molina-Cabanillas M, Jiménez-Navarro M, Arjona R, Martínez-Álvarez F, Asencio-Cortés G (2022) Diafan-tl: an instance weighting-based transfer learning algorithm with application to phenology forecasting. Knowledge-Based Syst 109644

  10. Wang T, Huan J, Zhu M (2019) Instance-based deep transfer learning. In: 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 367–375

  11. Shang J, Wu J (2017) A robust sign language recognition system with sparsely labeled instances using wi-fi signals. In: 2017 IEEE 14th international conference on mobile ad hoc and sensor systems (MASS). IEEE, pp 99–107

  12. Long M, Wang J, Ding G, Pan SJ, Philip SY (2013) Adaptation regularization: a general framework for transfer learning. IEEE Trans Know Data Eng 26(5):1076–1089

    Google Scholar 

  13. Long M, Wang J, Ding G, Sun J, Yu PS (2013) Transfer feature learning with joint distribution adaptation. In: Proceedings of the IEEE international conference on computer vision, pp 2200–2207

  14. Pan SJ, Tsang IW, Kwok JT, Yang Q (2010) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22(2):199–210

    Google Scholar 

  15. Arief-Ang IB, Hamilton M, Salim FD (2018) A scalable room occupancy prediction with transferable time series decomposition of co2 sensor data. ACM Trans Sensor Netw (TOSN) 14(3–4):1–28

    Google Scholar 

  16. Qin X, Chen Y, Wang J, Yu C (2019) Cross-dataset activity recognition via adaptive spatial-temporal transfer learning. Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies 3(4):1–25

    Google Scholar 

  17. Bagnall A, Lines J, Bostrom A, Large J, Keogh E (2017) The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Mining Knowledge Discovery 31(3):606–660

    MathSciNet  Google Scholar 

  18. **e J, Zhang L, Duan L, Wang J (2016) On cross-domain feature fusion in gearbox fault diagnosis under various operating conditions based on transfer component analysis. In: 2016 IEEE international conference on prognostics and health management (icphm). IEEE, pp 1–6

  19. Wang J, Chen Y, Hu L, Peng X, Philip SY (2018) Stratified transfer learning for cross-domain activity recognition. In: 2018 IEEE international conference on pervasive computing and communications (PerCom). IEEE, pp 1–10

  20. Qian X, Zhang C, Yella J, Huang Y, Huang MC, Bom S (2021) Soft sensing model visualization: fine-tuning neural network from what model learned. Proceedings - 2021 IEEE international conference on big data, big data 2021, vol 128, pp 1900–1908. ar**v:2111.06982, https://doi.org/10.1109/BigData52589.2021.9671850

  21. Hu Q, Zhang R, Zhou Y (2016) Transfer learning for short-term wind speed prediction with deep neural networks. Renew Energy 85:83–95

    Google Scholar 

  22. Lu W, Liang B, Cheng Y, Meng D, Yang J, Zhang T (2016) Deep model based domain adaptation for fault diagnosis. IEEE Trans Industrial Electron 64(3):2296–2305

    Google Scholar 

  23. Deng J, Zhang Z, Marchi E, Schuller B (2013) Sparse autoencoder-based feature transfer learning for speech emotion recognition. In: 2013 Humaine association conference on affective computing and intelligent interaction. IEEE, pp 511–516

  24. Banerjee D, Islam K, Xue K, Mei G, **ao L, Zhang G, Xu R, Lei C, Ji S, Li J (2019) A deep transfer learning approach for improved post-traumatic stress disorder diagnosis. Knowl Inf Syst 60(3):1693–1724

    Google Scholar 

  25. Fahimi F, Zhang Z, Goh WB, Lee T-S, Ang KK, Guan C (2019) Inter-subject transfer learning with an end-to-end deep convolutional neural network for eeg-based bci. J Neural Eng 16(2):026007

    Google Scholar 

  26. Hasan MJ, Kim J-M (2018) Bearing fault diagnosis under variable rotational speeds using stockwell transform-based vibration imaging and transfer learning. Appl Sci 8(12):2357

    Google Scholar 

  27. Hasan MJ, Islam MM, Kim J-M (2019) Acoustic spectral imaging and transfer learning for reliable bearing fault diagnosis under variable speed conditions. Measurement 138:620–631

    Google Scholar 

  28. Wen T, Keyes R (2019) Time series anomaly detection using convolutional neural networks and transfer learning. ar**v:1905.13628

  29. Fawaz HI, Forestier G, Weber J, Idoumghar L, Muller P-A (2018) Transfer learning for time series classification. In: 2018 IEEE international conference on big data (Big Data). IEEE, pp 1367–1376

  30. Zhang R, Tao H, Wu L, Guan Y (2017) Transfer learning with neural networks for bearing fault diagnosis in changing working conditions. IEEE Access 5:14347–14357

    Google Scholar 

  31. Van Kasteren T, Englebienne G, Kröse BJ (2010) Transferring knowledge of activity recognition across sensor networks. In: International conference on pervasive computing. Springer, pp 283–300

  32. Kearney D, McLoone S, Ward TE (2019) Investigating the application of transfer learning to neural time series classification. In: 2019 30th Irish signals and systems conference (ISSC). IEEE, pp 1–5

  33. Fan C, Sun Y, **ao F, Ma J, Lee D, Wang J, Tseng YC (2020) Statistical investigations of transfer learning-based methodology for short-term building energy predictions. Appl Energy 262:114499

    Google Scholar 

  34. Buffelli D, Vandin F (2021) Attention-based deep learning framework for human activity recognition with user adaptation. IEEE Sens J 21(12):13474–13483

    Google Scholar 

  35. Kimura N, Yoshinaga I, Sekijima K, Azechi I, Baba D (2019) Convolutional neural network coupled with a transfer-learning approach for time-series flood predictions. Water 12(1):96

    Google Scholar 

  36. Hooshmand A, Sharma R (2019) Energy predictive models with limited data using transfer learning. In: Proceedings of the Tenth ACM international conference on future energy systems, pp 12–16

  37. Rokni SA, Nourollahi M, Alinia P, Mirzadeh I, Pedram M, Ghasemzadeh H (2020) Transnet: minimally supervised deep transfer learning for dynamic adaptation of wearable systems. ACM Trans Des Autom Electron Syst (TODAES) 26(1):1–31

    Google Scholar 

  38. Taleb C, Likforman-Sulem L, Mokbel C, Khachab M (2020) Detection of parkinson’s disease from handwriting using deep learning: a comparative study. Evol Intell 1–12

  39. Marczewski A, Veloso A, Ziviani N (2017) Learning transferable features for speech emotion recognition. Proc Thematic Workshops ACM Multimed 2017:529–536

    Google Scholar 

  40. Ullah S, Kim D-H (2020) Lightweight driver behavior identification model with sparse learning on in-vehicle can-bus sensor data. Sensors 20(18):5030

    Google Scholar 

  41. Strodthoff N, Wagner P, Schaeffter T, Samek W (2020) Deep learning for ecg analysis: benchmarks and insights from ptb-xl. IEEE J Biomed Health Inf 25(5):1519–1528

    Google Scholar 

  42. Mun S, Shon S, Kim W, Han DK, Ko H (2017) Deep neural network based learning and transferring mid-level audio features for acoustic scene classification. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 796–800

  43. Chen H, Chen G, Lu Q, Peng L (2019) Mmse-based optimized transfer strategy for transfer prediction of parking data. In: 2019 IEEE intelligent transportation systems conference (ITSC). IEEE, pp 407–412

  44. Matsui S, Inoue N, Akagi Y, Nagino G, Shinoda K (2017) User adaptation of convolutional neural network for human activity recognition. In: 2017 25th European signal processing conference (EUSIPCO). IEEE, pp 753–757

  45. Martinez M, De Leon PL (2019) Falls risk classification of older adults using deep neural networks and transfer learning. IEEE J Biomed Health Inform 24(1):144–150

    Google Scholar 

  46. Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V (2016) Domain-adversarial training of neural networks. The journal of machine learning research 17(1):2096–2030

    MathSciNet  Google Scholar 

  47. Guo L, Lei Y, **ng S, Yan T, Li N (2018) Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Trans Industrial Electron 66(9):7316–7325

    Google Scholar 

  48. Jiang W, Miao C, Ma F, Yao S, Wang Y, Yuan Y, Xue H, Song C, Ma X, Koutsonikolas D et al (2018) Towards environment independent device free human activity recognition. In: Proceedings of the 24th annual international conference on mobile computing and networking, pp 289–304

  49. Wilson G, Doppa JR, Cook DJ (2020) Multi-source deep domain adaptation with weak supervision for time-series sensor data. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp 1768–1778

  50. Li X, Zhang W, Ding Q, Sun J-Q (2019) Multi-layer domain adaptation method for rolling bearing fault diagnosis. Sig Process 157:180–197

    Google Scholar 

  51. Zhu J, Chen N, Shen C (2019) A new deep transfer learning method for bearing fault diagnosis under different working conditions. IEEE Sensors J 20(15):8394–8402

    Google Scholar 

  52. Yang B, Lei Y, Jia F, **ng S (2019) An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mech Syst Signal Process 122:692–706

    Google Scholar 

  53. Xu X, Meng Z (2020) A hybrid transfer learning model for short-term electric load forecasting. Electr Eng 102(3):1371–1381

    Google Scholar 

  54. Marcelino P, de Lurdes Antunes M, Fortunato E, Gomes MC (2020) Transfer learning for pavement performance prediction. Int J Pavement Res Technol 13(2):154–167

    Google Scholar 

  55. Chen T, Guestrin C (2016) Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd Acm Sigkdd international conference on knowledge discovery and data mining, pp 785–794

  56. Benchaira K, Bitam S, Mellouk A, Tahri A, Okbi R (2019) Afibpred: a novel atrial fibrillation prediction approach based on short single-lead ecg using deep transfer knowledge. In: Proceedings of the 4th international conference on big data and internet of things, pp 1–6

  57. Shen S, Sadoughi M, Li M, Wang Z, Hu C (2020) Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries. Appl Energy 260:114296

    Google Scholar 

  58. Di Z, Shao H, **ang J (2021) Ensemble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation conditions. Sci China Technol Sci 64(3):481–492

    Google Scholar 

  59. Li J, Qiu S, Shen Y-Y, Liu C-L, He H (2019) Multisource transfer learning for cross-subject eeg emotion recognition. IEEE Trans Cybernetics 50(7):3281–3293

    Google Scholar 

  60. Chen Y, Wang J, Huang M, Yu H (2019) Cross-position activity recognition with stratified transfer learning. Pervasive Mobile Comput 57:1–13

    Google Scholar 

  61. **ao J, **ao Y, Fu J, Lai KK (2014) A transfer forecasting model for container throughput guided by discrete pso. J Syst Sci Complex 27(1):181–192

    Google Scholar 

  62. Meiseles A, Rokach L (2020) Source model selection for deep learning in the time series domain. IEEE Access 8:6190–6200

    Google Scholar 

  63. Almonacid-Olleros G, Almonacid G, Gil D, Medina-Quero J (2022) Evaluation of transfer learning and fine-tuning to nowcast energy generation of photovoltaic systems in different climates. Sustainability 14(5):3092

    Google Scholar 

  64. Luo X, Zhang D, Zhu X (2022) Combining transfer learning and constrained long short-term memory for power generation forecasting of newly-constructed photovoltaic plants. Renew Energy 185:1062–1077

    Google Scholar 

  65. Goswami S, Malakar S, Ganguli B, Chakrabarti A (2022) A novel transfer learning-based short-term solar forecasting approach for india. Neural Comput Appl 34(19):16829–16843

    Google Scholar 

  66. Genovese A, Bernardoni V, Piuri V, Scotti F, Tessore F (2022) Photovoltaic energy prediction for new-generation cells with limited data: a transfer learning approach. In: 2022 IEEE international instrumentation and measurement technology conference (I2MTC). IEEE, pp 1–6

  67. Sarmas E, Dimitropoulos N, Marinakis V, Mylona Z, Doukas H (2022) Transfer learning strategies for solar power forecasting under data scarcity. Sci Rep 12(1):14643

    Google Scholar 

  68. Banda P, Bhuiyan MA, Hasan KN, Zhang K, Song A (2021) Timeseries based deep hybrid transfer learning frameworks: a case study of electric vehicle energy prediction. In: International conference on computational science. Springer, pp 259–272

  69. Wang K, Wang H, Yang Z, Feng J, Li Y, Yang J, Chen Z (2023) A transfer learning method for electric vehicles charging strategy based on deep reinforcement learning. Appl Energy 343:121186

    Google Scholar 

  70. Lu K, Sun WX, Wang X, Meng XR, Zhai Y, Li HH, Zhang RG (2018) Short-term wind power prediction model based on encoder-decoder lstm. In: IOP conference series: earth and environmental science. IOP Publishing, vol 186, p 012020

  71. Cama-Pinto D, Martínez-Lao JA, Solano-Escorcia AF, Cama-Pinto A (2020) Forecasted datasets of electric vehicle consumption on the electricity grid of Spain. Data in Brief 31:105823

Download references

Funding

No funding source.

Author information

Author notes

  1. Rajalakshmi Krishnamurthi contributed equally to this work.

Authors and Affiliations

  1. Department of Computer Science Engineering and Information Technology, Noida, Jaypee Institute of Information Technology, Sector 62, Noida, 201309, U.P., India

    Sherry Garg & Rajalakshmi Krishnamurthi

Authors
  1. Sherry Garg
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rajalakshmi Krishnamurthi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Both the authors contributed equally to this work.

Corresponding author

Correspondence to Sherry Garg.

Ethics declarations

Conflicts of interest

Each author attests that they are not connected to or a part of any group or organization that has a financial or non-financial stake in the topics or materials covered in this text. There are no proprietary or financial interests held by the authors in any of the topics covered in this article.

Competing interests

The authors affirm that they are free of any known financial conflicts of interest or close personal ties that might have looked to have affected the research presented in this study. The following financial and personal connections that the authors have disclosed could be viewed as potential conflicting interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Garg, S., Krishnamurthi, R. Transfer learning: a cross domain LSTM way towards sustainable power predictive analytics. Multimed Tools Appl 83, 54097–54123 (2024). https://doi.org/10.1007/s11042-023-17635-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-17635-5

Keywords

Search

Navigation