Electrical Energy Prediction in Residential Buildings for Short-Term Horizons Using Hybrid Deep Learning Strategy
Source abstract
Abstract
Smart grid technology based on renewable energy and energy storage systems are attracting considerable attention towards energy crises. Accurate and reliable model for electricity prediction is considered a key factor for a suitable energy management policy. Currently, electricity consumption is rapidly increasing due to the rise in human population and technology development. Therefore, in this study, we established a two-step methodology for residential building load prediction, which comprises two stages: in the first stage, the raw data of electricity consumption are refined for effective training; and the second step includes a hybrid model with the integration of convolutional neural network (CNN) and multilayer bidirectional gated recurrent unit (MB-GRU). The CNN layers are incorporated into the model as a feature extractor, while MB-GRU learns the sequences between electricity consumption data. The proposed model is evaluated using the root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) metrics. Finally, our model is assessed over benchmark datasets that exhibited an extensive drop in the error rate in comparison to other techniques. The results indicated that the proposed model reduced errors over the individual household electricity consumption prediction (IHEPC) dataset (i.e., RMSE (5%), MSE (4%), and MAE (4%)), and for the appliances load prediction (AEP) dataset (i.e., RMSE (2%), and MAE (1%)).
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Smart Grid Energy Management · Building Energy and Comfort Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Sejong University, Seoul 143-747, Korea
References (64)
Show source-provided references
1. Deep Learning for Estimating Building Energy Consumption10.1016/j.segan.2016.02.005 ↗
2. Residential Electricity Consumption Behavior: Influencing Factors, Related Theories and Intervention Strategies10.1016/j.rser.2017.07.046 ↗
3. IEA (2014). International Energy Outlook, IEA.
4. A Global Review of Energy Consumption, CO 2 Emissions and Policy in the Residential Sector (with an Overview of the Top Ten CO 2 Emitting Countries)10.1016/j.rser.2014.11.066 ↗
5. Amarasinghe, K., Wijayasekara, D., Carey, H., Manic, M., He, D., and Chen, W.-P. (2015, January 9–12). Artificial Neural Networks Based Thermal Energy Storage Control for Buildings. Proceedings of the 41st Annual Conference of the IEEE Industrial Electronics Society, Jokohama, Japan.10.1109/IECON.2015.7392953 ↗
6. Short-Term Electricity Load Forecasting Based on Feature Selection and Least Squares Support Vector Machines10.1016/j.knosys.2018.08.027 ↗
7. Correlation and Instance Based Feature Selection for Electricity Load Forecasting10.1016/j.knosys.2015.02.017 ↗
8. Joint Bagged-Boosted Artificial Neural Networks: Using Ensemble Machine Learning to Improve Short-Term Electricity Load Forecasting10.1016/j.epsr.2019.106080 ↗
9. Short-Term Electricity Price and Load Forecasting in Isolated Power Grids Based on Composite Neural Network and Gravitational Search Optimization Algorithm10.1016/j.apenergy.2020.115503 ↗
10. A Hybrid Deep Learning-Based Method for Short-Term Building Energy Load Prediction Combined with an Interpretation Process10.1016/j.enbuild.2020.110301 ↗
11. Experimental Study on occupants’ Interaction with Windows and Lights in Mediterranean Offices during the Non-Heating Season10.1016/j.buildenv.2017.11.009 ↗
12. Stazi, F. (2017). Thermal Inertia in Energy Efficient Building Envelopes, Elsevier.10.1016/B978-0-12-813970-7.00004-2 ↗
13. Assessing Window Area and Potential for Electricity Savings by Using Daylighting and Hybrid Ventilation in Office Buildings in Southern Brazil10.1177/0037549717706171 ↗
14. Influence of Occupant Behaviour on the State of Charge of a Storage Battery in a Nearly-Zero Energy Building10.1051/e3sconf/202017216010 ↗
15. Energy Performance of Buildings With on-site Energy Generation and Storage—An Integrated Assessment Using Dynamic Simulation10.1016/j.jobe.2019.100769 ↗
16. An Efficient Deep Learning Framework for Intelligent Energy Management in IoT Networks
17. Khan, Z.A., Hussain, T., Ullah, A., Rho, S., Lee, M., and Baik, S.W. (2020). Towards Efficient Electricity Forecasting in Residential and Commercial Buildings: A Novel Hybrid CNN with a LSTM-AE Based Framework. Sensors, 20.10.3390/s20051399 ↗
18. Wei, L., and Zhen-Gang, Z. (2009, January 28–29). Based on Time Sequence of ARIMA Model in the Application of Short-Term Electricity Load Forecasting. Proceedings of the International Conference on Research Challenges in Computer Science, Shanghai, China.10.1109/ICRCCS.2009.12 ↗
19. Hong, T., Gui, M., Baran, M.E., and Willis, H.L. (2010, January 25–29). Modeling and Forecasting Hourly Electric Load by Multiple Linear Regression with Interactions. Proceedings of the IEEE PES General Meeting, Minneapolis, MN, USA.
20. Fuzzy Short-Term Electric Load Forecasting Using Kalman Filter10.1049/ip-gtd:20050088 ↗
21. Ullah, A., Haydarov, K., Haq, I.U., Muhammad, S., Rho, S., Lee, M.Y., and Baik, S.W. (2020). Deep Learning Assisted Buildings Energy Consumption Profiling Using Smart Meter Data. Sensors, 20.10.3390/s20030873 ↗
22. GMM Clustering for Heating Load Patterns in-depth Identification and Prediction Model Accuracy Improvement of District Heating System10.1016/j.enbuild.2019.02.014 ↗
23. Day-Ahead Load Forecast Using Random Forest and Expert Input Selection10.1016/j.enconman.2015.07.041 ↗
24. Short-Term Load Forecasting: Similar Day-Based Wavelet Neural networks10.1109/TPWRS.2009.2030426 ↗
25. Secondary Forecasting Based on Deviation Analysis for Short-Term Load Forecasting10.1109/TPWRS.2010.2052638 ↗
26. An Optimized Adaptive Neural Network for Annual Midterm Energy Forecasting10.1109/TPWRS.2005.860926 ↗
27. A Novel Wavelet-Based Ensemble Method for Short-Term Load Forecasting With Hybrid Neural Networks and Feature Selection10.1109/TPWRS.2015.2438322 ↗
28. Amarasinghe, K., Marino, D.L., and Manic, M. (2017, January 19–21). Deep Neural Networks for Energy Load Forecasting. Proceedings of the 26th International Symposium on Industrial Electronics (ISIE), Edinburgh, UK.10.1109/ISIE.2017.8001465 ↗
29. Khan, S., Javaid, N., Chand, A., Khan, A.B.M., Rashid, F., and Afridi, I.U. (2019). Electricity Load Forecasting for Each Day of Week Using Deep CNN. Advances in Intelligent Systems and Computing, Springer.10.1007/978-3-030-15035-8_107 ↗
30. Tokgoz, A., and Unal, G. (2018, January 2–5). A RNN Based Time Series Approach for Forecasting Turkish Electricity Load. Proceedings of the 26th Signal Processing and Communications Applications Conference (SIU), Izmir, Turkey.10.1109/SIU.2018.8404313 ↗
31. LSTM Based Long-Term Energy Consumption Prediction with Periodicity10.1016/j.energy.2020.117197 ↗
32. Predicting Electricity Consumption for Commercial and Residential Buildings Using Deep Recurrent Neural Networks10.1016/j.apenergy.2017.12.051 ↗
33. Predicting Residential Energy Consumption Using CNN-LSTM Neural Networks10.1016/j.energy.2019.05.230 ↗
34. Short-Term Prediction of Residential Power Energy Consumption via CNN and Multi-Layer Bi-Directional LSTM Networks10.1109/ACCESS.2019.2963045 ↗
35. A Novel CNN-GRU-Based Hybrid Approach for Short-Term Residential Load Forecasting10.1109/ACCESS.2020.3009537 ↗
36. Deep-Based Conditional Probability Density Function Forecasting of Residential Loads10.1109/TSG.2020.2972513 ↗
37. Forecasting Loads and Prices in Competitive Power Markets10.1109/5.823996 ↗
38. Analysis of the Value for Unit Commitment of Improved Load Forecasts10.1109/59.801894 ↗
39. Anomaly Detection: A survey10.1145/1541880.1541882 ↗
40. Human Behavior Understanding in Big Multimedia Data Using CNN Based Facial Expression Recognition10.1007/s11036-019-01366-9 ↗
41. Personalized Movie Summarization Using Deep CNN-Assisted Facial Expression Recognition10.1155/2019/3581419 ↗
42. Recent Trends in Deep Learning Based Natural Language Processing [Review Article]10.1109/MCI.2018.2840738 ↗
43. and Kwon, S. (2020). MLT-DNet: Speech Emotion Recognition Using 1D Dilated CNN Based on Multi-Learning Trick Approach. Expert Syst. Appl., 114177.10.1016/j.eswa.2020.114177 ↗
44. Short-Term Load Forecasting with Deep Residual Networks10.1109/TSG.2018.2844307 ↗
45. Deterministic and Probabilistic Forecasting of Photovoltaic Power Based on Deep Convolutional Neural Network10.1016/j.enconman.2017.10.008 ↗
46. Khan, N., Ullah, A., Haq, I.U., Menon, V.G., and Baik, S.W. (2020). SD-Net: Understanding Overcrowded Scenes in Real-Time via an Efficient Dilated Convolutional Neural Network. J. Real Time Image Process., 1–15.10.1007/s11554-020-01020-8 ↗
47. Jozefowicz, R., Zaremba, W., and Sutskever, I. (2015, January 6–11). An Empirical Exploration of Recurrent Network architectures. Proceedings of the International Conference on Machine Learning, Lille, France.
48. Yin, W., Kann, K., Yu, M., and Schütze, H.J.A.P.A. (2017). Comparative Study of cnn and rnn for Natural Language processing. arXiv.
49. DSTP-RNN: A Dual-Stage Two-Phase Attention-Based Recurrent Neural Network for Long-Term and Multivariate Time Series Prediction10.1016/j.eswa.2019.113082 ↗
50. Guo, J., Tiwari, G., Droppo, J., Van Segbroeck, M., Huang, C.-W., Stolcke, A., and Maas, R. (2020). Efficient Minimum Word Error Rate Training of RNN-Transducer for End-to-End Speech Recognition. Interspeech.10.21437/Interspeech.2020-1557 ↗
51. Ullah, A., Muhammad, K., Hussain, T., and Baik, S.W. (2020). Conflux LSTMs Network: A Novel Approach for Multi-View Action Recognition. Neurocomputing.10.1016/j.neucom.2019.12.151 ↗
52. Ullah, A., Muhammad, K., Hussain, T., Lee, M., and Baik, S.W. (2020). Deep LSTM-Based Sequence Learning Approaches for Action and Activity Recognition. Deep Learning in Computer Vision, Informa UK Limited.10.1201/9781351003827-5 ↗
53. Ullah, W., Ullah, A., Haq, I.U., Muhammad, K., Sajjad, M., and Baik, S.W. (2020). CNN Features with Bi-Directional LSTM for Real-Time Anomaly Detection in Surveillance Networks. Multimed. Tools Appl., 1–17.10.1007/s11042-020-09406-3 ↗
54. Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv.
55. Bidirectional Recurrent Neural Networks10.1109/78.650093 ↗
56. Hussain, T., Muhammad, K., Ullah, A., Cao, Z., Baik, S.W., and De Albuquerque, V.H.C. (2019). Cloud-Assisted Multi-View Video Summarization Using CNN and Bi-Directional LSTM. IEEE Trans. Ind. Inform.10.1109/TII.2019.2929228 ↗
57. Short-Term Power Load Forecasting Based on Multi-Layer Bidirectional Recurrent Neural Network10.1049/iet-gtd.2018.6687 ↗
58. (2020, October 15). Repository Appliances Energy Prediction Data Set. Available online: https://archive.ics.uci.edu/ml/Datasets/Appliances+energy+prediction.
59. UCI (2020, October 15). Individual Household Electric Power Consumption Data Set. Available online: https://archive.ics.uci.edu/ml/datasets/Individual+household+electric+power+consumption.
60. Rajabi, R., and Estebsari, A. (2019). Deep Learning Based Forecasting of Individual Residential Loads Using Recurrence Plots. IEEE Milan PowerTech, IEEE.10.1109/PTC.2019.8810899 ↗
61. Kim, J.-Y., and Cho, S.-B. (2019). Electric Energy Consumption Prediction by Deep Learning with State Explainable Autoencoder. Energies, 12.10.3390/en12040739 ↗
62. Zhang, T., Liao, L., Lai, H., Liu, J., Zou, F., and Cai, Q. (2018). Electrical Energy Prediction with Regression-Oriented Models. Advances in Intelligent Systems and Computing, Springer.10.1007/978-3-030-03766-6_16 ↗
63. Bandic, L., and Kevric, J. (2018). Near Zero-Energy Home Prediction of Appliances Energy Consumption Using the Reduced Set of Features and Random Decision Tree Algorithms. Advances on P2P, Parallel, Grid, Cloud and Internet Computing, Springer.10.1007/978-3-030-02574-8_13 ↗
64. An End-to-End Adaptive Input Selection with Dynamic Weights for Forecasting Multivariate Time Series10.1109/ACCESS.2019.2930069 ↗