A Comparative Analysis of BiLSTM-GRU and RNN Models for Smart Home Energy Consumption Forecasting
Abstract
Energy conservation in smart homes is crucial for optimizing electricity usage, reducing costs, and contributing to sustainability efforts. This study evaluates the performance of two deep learning models, the Bidirectional Long Short-Term Memory with Gated Recurrent Units (BiLSTM-GRU) and the traditional Recurrent Neural Network (RNN), in forecasting smart home energy consumption. The research employs comprehensive data preprocessing, model implementation, training, and evaluation to determine the superior model. Experimental results demonstrate that the BiLSTM-GRU model consistently outperforms the RNN model across multiple forecasting windows, offering higher accuracy and robustness. The study provides insights into model selection for energy management applications and discusses the trade-offs between model complexity, interpretability, and computational efficiency.
Keywords
Smart homesMachine learningLong Short-Term Memory (LSTM)Gated Recurrent
References
A Guide to Long Short Term Memory (LSTM) Networks. (2023, September 18). KnowledgeHut. Retrieved September 26, 2023, from https://www.knowledgehut.com/blog/web- development/long-short-term-memory. Abdul Salam, S., Haidawati, N., Muhammad, F., Adidah, L., & Asadullah, S. (2018). A Review on Energy Consumption Optimization Techniques in IoT Based Smart Building Environment. Retrieved from https://www.mdpi.com/journal/information. Abdullah, S. (2022). Survey: Privacy-Preserving in Deep Learning based on Homomorphic Encryption. Alden, R. E., Gong, H., Ababe, C., & Ionel, D. M. (2020, September). LSTM Forecasts for Smart Home Electricity Usage. International Conference on Renewable Energy Research and Applications. Retrieved from https://sparklab.engr.uky.edu/sites/sparklab/files/LSTM_Forecasts_for_Smart_Home_Ele ctricity_Usage.pdf. Alduailij, M., Petri, I., Rana, O., Alduailij, M., & Aldawood, A. (2021). Forecasting Peak Energy Demand for Smart Buildings. The Journal of Supercomputing, 77, 1-25. https://doi.org/10.1007/s11227-020-03540-3. Amidi, A., & Amidi, S. (n.d.). CS 230 - Recurrent Neural Networks Cheatsheet. Retrieved from https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks. Atilla, A., Mammadagha, M., Berna, Y., & Senay, Y. (2007). Comparison of ARIMA, neural networks and hybrid models in time series: tourist arrival forecasting. Journal of Statistical Computation and Simulation, 1(77), 29-53. https://doi.org/10.1080/10629360600564874. Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer. Bontempi, G., Taieb, S. B., & Le Borgne, Y.-A. (2012). Machine learning strategies for time series forecasting. European Business Intelligence Summer School, 62-77. Bourhnane, S., Abid, M. R., Lghou, R., Zine Dine, H., & Elkamoun, N. (2020). Machine learning for energy consumption prediction and scheduling in smart buildings. SN Applied Sciences, 2, 297. https://doi.org/10.1007/s42452-020-2024-9. Box, G. E., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control. Wiley. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. Brownlee, J. (2018, August 6). 1 Classical Time Series Forecasting Methods in Python (Cheat Sheet). Time Series. Retrieved from https://machinelearningmastery.com/time-series- forecasting-methods-in-python-cheat-sheet/. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273-297. Donges, N. (n.d.). What Are Recurrent Neural Networks? Built In. Retrieved from https://builtin.com/data-science/recurrent-neural-networks-and-lstm. Gopikrishna, P. B., & Jiju A., M. (2021, April 6). Power Consumption Analysis and Prediction of a Smart Home Using ARIMA Model. https://doi.org/10.2139/ssrn.3819512. Graves, A. (2012). Supervised Sequence Labelling with Recurrent Neural Networks. Hakpyeong, K., Heeju, C., Hyuna, K., Jongbaek, A., Seungkeun, Y., & Taehoon, H. (2021). A systematic review of the smart energy conservation system: From smart homes to sustainable smart cities. Renewable and Sustainable Energy Reviews, 140(C). https://doi.org/10.1016/j.rser.2021.110755. Hartigan, J. A., & Wong, M. A. (1979). Algorithm AS 136: A k-means clustering algorithm. Journal of the Royal Statistical Society. Series C (Applied Statistics), 28(1), 100-108. Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786), 504-507. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts. In-Depth Guide to Recurrent Neural Networks (RNNs) in 2023. (2023, June 12). AIMultiple. Retrieved September 26, 2023, from https://research.aimultiple.com/rnn/. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An Introduction to Statistical Learning: with Applications in R. Springer. Kahn, J. (2015, December 18). Future Home Tech: 8 Energy-Saving Solutions on the Horizon. Department of Energy. Retrieved from https://www.energy.gov/articles/future-home-tech- 8-energy-saving-solutions-horizon. Khalid, S., Effina, D., Khalid, K. R., & Chaabane, M. S. (2023). The Artificial Intelligence as a Decision-Making Instrument for Modeling and Predicting Small Cities’ Attractiveness: Evidence from Morocco. Applied Mathematics & Information Sciences, 17(5), Article 17. Khaoula, E., Amine, B., & Mostafa, B. (2023, March 01). Evaluation and Comparison of Energy Consumption Prediction Models Case Study: Smart Home. Lecture Notes on Data Engineering and Communications Technologies, 164(272). https://doi.org/10.1007/978-3- 031-27762-7_17. Korstanje, J. (2021). Advanced Forecasting with Python: With State-of-the-Art-Models Including LSTMs, Facebook’s Prophet, and Amazon’s DeepAR. Apress. Le, T., Vo, M. T., Vo, B., Hwang, E., Rho, S., & Baik, S. W. (2019). Improving Electric Energy Consumption Prediction Using CNN and Bi-LSTM. Applied Sciences, 9(20), 4237. https://doi.org/10.3390/app9204237. Lendave, V. (2021, November 1). A Guide to Different Evaluation Metrics for Time Series Forecasting Models. Analytics India Magazine. Retrieved from https://analyticsindiamag.com/a-guide-to-different-evaluation-metrics-for-time-series- forecasting-models/. Mahjoub, S., Chrifi-Alaoui, L., Marhic, B., & Delahoche, L. (2022). Predicting Energy Consumption Using LSTM, Multi-Layer GRU and Drop-GRU Neural Networks. Sensors, 22(11), 4062. https://doi.org/10.3390/s22114062. Merity, S., Keskar, N. S., & Socher, R. (2017). Regularizing and Optimizing LSTM Language Models. Retrieved from https://arxiv.org/pdf/1708.02182.pdf. Mitat, U. (2007). Comparison of ARIMA and RBFN Models to Predict the Bank Transactions. Information Technology Journal, 6(3), 475-477. https://doi.org/10.3923/itj.2007.475.477. Mittal, M., Tanwar, S., Agarwal, B., & Goyal, L. M. (Eds.). (2019). Energy Conservation for IoT Devices: Concepts, Paradigms and Solutions. Springer Nature Singapore. Montgomery, D. C., Jennings, C. L., & Kulahci, M. (2015). Introduction to Time Series Analysis and Forecasting. Wiley. Nugaliyadde, A., Somaratne, U., & Wong, K. W. (2022, October 2). Predicting Electricity Consumption using Deep Recurrent Neural Networks. Retrieved from https://arxiv.org/pdf/1909.08182.pdf. Pathak, P. (2021, September 8). Time Series Forecasting — A Complete Guide | by Puja P. Pathak | Analytics Vidhya. Medium. Retrieved from https://medium.com/analytics-vidhya/time- series-forecasting-a-complete-guide-d963142da33f. Rasha, E.-A. (2021, June). Smart homes: potentials and challenges. Clean Energy, 5(2), 302-315. https://doi.org/10.1093/ce/zkab010. Recurrent Neural Network (RNN) in TensorFlow. (n.d.). Javatpoint. Retrieved from https://www.javatpoint.com/recurrent-neural-network-in-tensorflow. Recurrent Neural Networks (RNN) Tutorial. (2023, June 21). DeepLearning.AI. Retrieved from https://www.deeplearning.ai/resources/recurrent-neural-networks/. Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press. Sharma, P. (2022, May 20). Evaluation Metrics for Time Series Forecasting. Analytics Vidhya. Retrieved from https://www.analyticsvidhya.com/blog/2022/05/evaluation-metrics-for- time-series-forecasting/. Sherin, H. A. (2017, June 16). Load Forecasting for Smart Home using LSTM Recurrent Neural Networks. Retrieved from https://repository.ntu.edu.sg/bitstream/10356/70394/1/Load%20Forecasting%20for%20S mart%20Home%20using%20LSTM%20Recurrent%20Neural%20Networks.pdf. Singh, N., & Malhotra, R. (2018). Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Procedia Computer Science, 132
More Articles from INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY
A Flexible Edge Search Algorithm for Graceful Tree Labeling
Author: Michael Arnold and Fabio Vitor
Advances in Algorithmic Contract Scoring for Pre-Negotiation Yield Optimization and Risk Retention
Author: Ngozi Samuel Uzougbo, Michael Ominyi, Cyril Chimelie Anichukwueze, Blessing, Chika Jones
DevTest flow: Designing a Scalable Continuous Testing Pipeline for High-Velocity Software Delivery
Author: Lawal Ahmed Oladimeji, Achori Busayo, Akeju BusayoZainab, Saka Samson, Damilare, Mbah Demian Chidi, Runsewe Similoluwa Mayowa, Oladiti Luqman, Abiodun
Assessing Blackboard LMS Implementation, Adoption Barriers and Digital Transformation in Tertiary Institutions in Kogi State, Nigeria
Author: Okolo Clement, Eluemuno
Intelligent Cybercrime Prediction and Control Model Using Hybrid Machine Learning Algorithms for Ddos and Phishing Attack Mitigation
Author: Chukumeka Gift Iroanwusi, Davies Isobo Nelson