The research field of energy prediction plays a vital role in making future forecasts and is an essential task of smart grid management. This study aims to develop a novel electricity consumption forecasting model, SBiGRU, which integrates Gated Recurrent Unit, Bidirectional Technique, and Symbiotic Organisms Search algorithm. In this framework, based on three datasets, namely Residential, Commercial, and Industrial, GRU was applied in both directions, including forward and backward, for training to develop BiGRU. Using SOS, the optimal hyperparameters of GRU were identified, and the prediction’s accuracy was improved. The experimental results were also conducted to compare the performance based on the evaluation criteria of the SBiGRU model with other models for each of the three datasets and showed that the SBiGRU model outperformed with higher accuracy than the linear model (LR), hybrid-nonlinear model (SOS-LSSVR), and the traditional version of RNN variants (LSTM/BiLSTM, GRU/BiGRU). In case of supply exceeds demand, the prediction results can decide the quantity of timely electricity supply to power plants. In contrast, Time-of-Use Tariff is advised as a management strategy to level demand and implement variable power consumption tariff rates during different time frames, resulting in a fall in the demand curve during peak and off-peak hours.

The research field of energy prediction plays a vital role in making future forecasts and is an essential task of smart grid management. This study aims to develop a novel electricity consumption forecasting model, SBiGRU, which integrates Gated Recurrent Unit, Bidirectional Technique, and Symbiotic Organisms Search algorithm. In this framework, based on three datasets, namely Residential, Commercial, and Industrial, GRU was applied in both directions, including forward and backward, for training to develop BiGRU. Using SOS, the optimal hyperparameters of GRU were identified, and the prediction’s accuracy was improved. The experimental results were also conducted to compare the performance based on the evaluation criteria of the SBiGRU model with other models for each of the three datasets and showed that the SBiGRU model outperformed with higher accuracy than the linear model (LR), hybrid-nonlinear model (SOS-LSSVR), and the traditional version of RNN variants (LSTM/BiLSTM, GRU/BiGRU). In case of supply exceeds demand, the prediction results can decide the quantity of timely electricity supply to power plants. In contrast, Time-of-Use Tariff is advised as a management strategy to level demand and implement variable power consumption tariff rates during different time frames, resulting in a fall in the demand curve during peak and off-peak hours.

REFERENCES
Abhishek, K., Singh, M., Ghosh, S., & Anand, A. (2012). Weather forecasting model using artificial neural network. Procedia Technology, 4, 311-318.
Amarasinghe, K., Marino, D. L., & Manic, M. (2017). Deep neural networks for energy load forecasting. 2017 IEEE 26th international symposium on industrial electronics (ISIE),
Ariyo, A. A., Adewumi, A. O., & Ayo, C. K. (2014). Stock price prediction using the ARIMA model. 2014 UKSim-AMSS 16th international conference on computer modelling and simulation,
Center, B. P. (2020). Annual energy outlook 2020. Energy Information Administration, Washington, DC, 12, 1672-1679.
Černe, G., Dovžan, D., & Škrjanc, I. (2018). Short-Term Load Forecasting by Separating Daily Profiles and Using a Single Fuzzy Model Across the Entire Domain. IEEE Transactions on Industrial Electronics, 65(9), 7406-7415. https://doi.org/10.1109/TIE.2018.2795555
Cheng, M.-Y., Cao, M.-T., & Herianto, J. G. (2020). Symbiotic organisms search-optimized deep learning technique for mapping construction cash flow considering complexity of project. Chaos, Solitons & Fractals, 138, 109869.
Cheng, M.-Y., & Prayogo, D. (2014). Symbiotic organisms search: a new metaheuristic optimization algorithm. Computers & Structures, 139, 98-112.
Cheng, M.-Y., & Roy, A. F. (2011). Evolutionary fuzzy decision model for cash flow prediction using time-dependent support vector machines. International journal of project management, 29(1), 56-65.
Cho, K., Van Merriënboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259.
Chou, J. S., & Hsu, S. M. (2022). Automated prediction system of household energy consumption in cities using web crawler and optimized artificial intelligence. International Journal of Energy Research, 46(1), 319-339.
Chou, J. S., & Truong, D. N. (2021). Multistep energy consumption forecasting by metaheuristic optimization of time‐series analysis and machine learning. International Journal of Energy Research, 45(3), 4581-4612.
Cousins, T. (2009). Using time of use (TOU) tariffs in industrial, commercial and residential applications effectively. TLC Engineering Solutions.
DoE, U. (2010). Smart grid research & development: multi-year program plan (mypp) 2010–2014. US Department of Energy, Office of Electricity Delivery & Energy Reliability.
Eseye, A. T., Lehtonen, M., Tukia, T., Uimonen, S., & Millar, R. J. (2019). Short-term forecasting of electricity consumption in buildings for efficient and optimal distributed energy management. 2019 IEEE 17th International Conference on Industrial Informatics (INDIN),
Hebrail, G., & Berard, A. (2012). Individual household electric power consumption data set. É. d. France, Ed., ed: UCI Machine Learning Repository.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
Hong, W.-C. (2011). Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artificial bee colony algorithm. Energy, 36(9), 5568-5578.
Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the national academy of sciences, 79(8), 2554-2558.
Hurst, W., Montañez, C. A. C., & Shone, N. (2020). Time-pattern profiling from smart meter data to detect outliers in energy consumption. IoT, 1(1), 6.
Hussin, N., Abdullah, M., Ali, A., Hassan, M., & Hussin, F. (2014). Residential electricity time of use (ToU) pricing for Malaysia. 2014 IEEE Conference on Energy Conversion (CENCON),
Interconnection, P. (1999). About PJM. In: May.
Jordan, M. I. (1997). Serial order: A parallel distributed processing approach. In Advances in psychology (Vol. 121, pp. 471-495). Elsevier.
Kaur, H., & Ahuja, S. (2017). Time series analysis and prediction of electricity consumption of health care institution using ARIMA model. Proceedings of Sixth International Conference on Soft Computing for Problem Solving,
Khan, Z. A., Ullah, A., Ullah, W., Rho, S., Lee, M., & Baik, S. W. (2020). Electrical energy prediction in residential buildings for short-term horizons using hybrid deep learning strategy. Applied Sciences, 10(23), 8634.
Kong, W., Dong, Z. Y., Hill, D. J., Luo, F., & Xu, Y. (2017). Short-term residential load forecasting based on resident behaviour learning. IEEE Transactions on Power Systems, 33(1), 1087-1088.
Koprinska, I., Rana, M., & Agelidis, V. G. (2015). Correlation and instance based feature selection for electricity load forecasting. Knowledge-Based Systems, 82, 29-40.
Kumar, N. M., Chand, A. A., Malvoni, M., Prasad, K. A., Mamun, K. A., Islam, F., & Chopra, S. S. (2020). Distributed energy resources and the application of AI, IoT, and blockchain in smart grids. Energies, 13(21), 5739.
Lahouar, A., & Slama, J. B. H. (2015). Day-ahead load forecast using random forest and expert input selection. Energy Conversion and Management, 103, 1040-1051.
Ma, Z., Ye, C., Li, H., & Ma, W. (2018). Applying support vector machines to predict building energy consumption in China. Energy Procedia, 152, 780-786.
Mitchell, R. (2018). Web scraping with Python: Collecting more data from the modern web. " O'Reilly Media, Inc.".
Muralitharan, K., Sakthivel, R., & Vishnuvarthan, R. (2018). Neural network based optimization approach for energy demand prediction in smart grid. Neurocomputing, 273, 199-208.
Nazar, N., Abdullah, M., Hassan, M., & Hussin, F. (2012). Time-based electricity pricing for Demand Response implementation in monopolized electricity market. 2012 IEEE Student Conference on Research and Development (SCOReD),
Pombeiro, H., Santos, R., Carreira, P., Silva, C., & Sousa, J. M. (2017). Comparative assessment of low-complexity models to predict electricity consumption in an institutional building: Linear regression vs. fuzzy modeling vs. neural networks. Energy and Buildings, 146, 141-151.
Salehinejad, H., Sankar, S., Barfett, J., Colak, E., & Valaee, S. (2017). Recent advances in recurrent neural networks. arXiv preprint arXiv:1801.01078.
Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE transactions on Signal Processing, 45(11), 2673-2681.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1), 1929-1958.
Tokgöz, A., & Ünal, G. (2018). A RNN based time series approach for forecasting turkish electricity load. 2018 26th Signal Processing and Communications Applications Conference (SIU),
Ullah, A., Haydarov, K., Ul Haq, I., Muhammad, K., Rho, S., Lee, M., & Baik, S. W. (2020). Deep learning assisted buildings energy consumption profiling using smart meter data. Sensors, 20(3), 873.
Yamak, P. T., Yujian, L., & Gadosey, P. K. (2019). A comparison between arima, lstm, and gru for time series forecasting. Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence,
Zhuang, P., & Liang, H. (2019). Hierarchical and decentralized stochastic energy management for smart distribution systems with high BESS penetration. IEEE Transactions on Smart Grid, 10(6), 6516-6527.