Abstract
The accurate short-term load forecasting can pave the way for improving, planning and maintenance of electric power systems. In this work, a novel Bayesian deep learning framework has been developed on BiLSTM + dropout network for analyzing short-term load prediction. The proposed framework improves the prediction accuracy by learning the uncertainties as well as reducing the data overfitting. Furthermore, a hierarchical clustering technique is applied to group consumers of similar behaviors in utilizing the power to improve the accuracy of load forecasting. The proposed framework is implemented using the MATLAB platform and tested on CER smart meter data. The RMSE, MAE and MAPE benchmark parameters are considered for comparing the proposed framework with the existing state-of-the-art techniques, viz., LSTM dropout, GRU, SVR and ARIMA. From the experimental results, it is evident that the proposed framework has achieved a better prediction accuracy despite the dataset having different load profiles, huge number of customers, uncertainties and volatility.
Similar content being viewed by others
References
Deng R, Yang Z, Chow MY, Chen J (2015) A survey on demand response in smart grids: mathematical models and approaches. IEEE Trans Ind Inform 11(3):570–582
Khashei M, Bijari M (2011) A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Appl Soft Comput 11(2):2664–2675
Yun Z, Quan Z, Caixin S, Shaolan L, Yuming L, Yang S (2008) RBF neural network and ANFIS-based short-term load forecasting approach in real-time price environment. IEEE Trans Power Syst 23(3):853–858
Taylor JW (2012) Short-term load forecasting with exponentially weighted methods. IEEE Trans Power Syst 27(1):458–464
Dejan I, Per GDS, Stamatis K, Malte J (2013) Impact assessment of smart meter grouping on the accuracy of forecasting algorithms. In: SAC '13: proceedings of the 28th annual ACM symposium on applied computing, pp 673–679
Erick MO, Fernando LO (2018) Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods. Energy 144:776–788
Marino DL, Amarasinghe K, Manic M (2016) Building energy load forecasting using deep neural networks. In: IECON 2016—42nd annual conference of the IEEE industrial electronics society, Florence, pp 7046–7051
Petra V, Anna BE, Viera R, Slavomír S, Arun KS (2018) Smart grid load forecasting using online support vector regression. Comput Electr Eng 65:102–117
Zheng J, Xu C, Zhang Z, Li X (2017) Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network. In: 51st annual conference on information sciences and systems (CISS), Baltimore, MD, pp 1–6
Alberg D, Last M (2018) Short-term load forecasting in smart meters with sliding window-based ARIMA algorithms. Vietnam J Comput Sci 2:241–249
Shahzadeh A, Khosravi A, Nahavandi S (2015) Improving load forecast accuracy by clustering consumers using smart meter data. In: International joint conference on neural networks (IJCNN), Killarney, pp 1–7
Siami-Namini S, Tavakoli N, Namin AS (2019) A comparative analysis of forecasting financial time series using ARIMA, LSTM, and BiLSTM. abs/1911.09512
Zhang R, Dong Y, Xu Y, Meng K, Wong KP (2013) Short-term load forecasting of Australian National Electricity Market by an ensemble model of an extreme learning machine. IET Gener Transm Distrib 7(4):391–397
Chaouch M (2014) Clustering-based improvement of nonparametric functional time series forecasting: application to intra-day household-level load curves. IEEE Trans Smart Grid 5(1):411–419
Ryu S, Noh J, Kim H. Deep neural network based demand side short term load forecasting. In: Proceedings of 2016 IEEE international conference on smart grid communications (SmartGridComm), Sydney, NSW, 2016, pp 308–313
Fan G-F, Guo Y-H, Zheng J-M, Hong W-C (2019) Application of the weighted K-nearest neighbor algorithm for short-term load forecasting. Energies 12:916
Kong W, Dong ZY, Jia Y, Hill DJ, Xu Y, Zhang H (2017) Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Trans Smart Grid 10(1):841–851
Kwac J, Flora J, Rajagopal R (2014) Household energy consumption segmentation using hourly data. IEEE Trans Smart Grid 5(1):420–430
Quilumba FL, Lee W, Huang H, Wang DY, Szabados RL (2015) Using smart meter data to improve the accuracy of intraday load forecasting considering customer behavior similarities. IEEE Trans Smart Grid 6(2):911–918
Stephen B, Tang X, Harvey PR, Galloway S, Jennett KI (2017) Incorporating practice theory in sub-profile models for short term aggregated residential load forecasting. IEEE Trans Smart Grid 8(4):1591–1598
Wang Y, Chen Q, Sun M, Kang C, Xia Q (2018) An ensemble forecasting method for the aggregated load with subprofiles. IEEE Trans Smart Grid 9(4):3906–3908
Chen H, Wang S, Wan S, Li Y (2019) Day-ahead aggregated load forecasting based on two-terminal sparse coding and deep neural network fusion. Electric Power Syst Res 177:105987
Fahiman F, Erfani SM, Rajasegarar S, Palaniswami M, Leckie C (2017) Improving load forecasting based on deep learning and K-shape clustering. In: 2017 international joint conference on neural networks (IJCNN), Anchorage, AK, pp 4134–4141 (2017)
Gajowniczek K, Ząbkowski T (2018) Simulation study on clustering approaches for short-term electricity forecasting. Complexity
Hochreite S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Yang Y, Li W, Gulliver TA, Li S (2020) Bayesian deep learning-based probabilistic load forecasting in smart grids. IEEE Trans Ind Inform 16(7):4703–4713
Acknowledgements
This research work is supported by CIT—TLC under the PMMMNMTT scheme of MHRD, Govt. of India. The authors sincerely acknowledge the Commission for Energy Regulation (CER) and Irish Social Science Data Archive (ISSDA) for providing smart meter dataset.
Funding
Funding was provided by Ministry of Human Resource Development (Grant No. 1-25/2017-PN.II).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared that there is no conflict of interest.
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
Kiruthiga, D., Manikandan, V. Intraday time series load forecasting using Bayesian deep learning method—a new approach. Electr Eng 104, 1697–1709 (2022). https://doi.org/10.1007/s00202-021-01411-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-021-01411-5