Hybrid CNN-LSTM Forecasting and Demand Response Optimization for Energy Flexibility and Cost Reduction in Grid-Connected Renewable Microgrids

Article Sidebar

PDF
Published: 2025-07-23
DOI: https://doi.org/10.15662/IJRPETM.2025.0804024
Keywords:
CNN-LSTM, demand response, load forecasting, energy flexibility, renewable microgrid, cost optimization, peak shaving

Main Article Content

Md Sadik Hassan Arik, Md Samiul Islam, Md Ahsan Habib, Md Sabiruzzaman
Department of Industrial Engineering, College of Engineering, Lamar University, Beaumont, TX 77710, United States

Abstract

Grid-connected renewable microgrids increasingly rely on accurate short-term forecasting and active demand-side management to reduce operating cost and exploit energy flexibility while maintaining reliable supply. This paper proposes an integrated framework that couples a hybrid convolutional neural network–long short-term memory (CNN-LSTM) forecasting model with a demand response (DR) optimization engine to jointly minimize electricity procurement cost and peak grid exchange in a grid-connected microgrid comprising solar photovoltaics (PV), wind generation, battery energy storage, and flexible/shiftable industrial and commercial loads. The CNN-LSTM model forecasts renewable generation, aggregate load, and real-time/time-of-use electricity prices over rolling 1-hour to 24-hour horizons, extracting local temporal features via convolutional layers before modeling longer-range dependencies with stacked LSTM layers. These forecasts feed a mixed-integer linear programming (MILP)-based demand response optimizer that schedules shiftable loads, curtailable loads, and battery charge/discharge to minimize total cost subject to comfort/production constraints, contractual demand charge limits, and grid import/export bounds. A case study on a representative grid-connected microgrid with 1.8 MW PV, 1.2 MW wind, 1.5 MWh battery storage, and 30% flexible load share demonstrates that the hybrid CNN-LSTM model reduces load and price forecast RMSE by 24.3% and 21.7% respectively compared to a standalone LSTM baseline, and that the integrated forecasting-DR optimization framework achieves an 18.9% reduction in daily electricity cost and a 22.4% reduction in peak grid demand relative to a forecast-agnostic rule-based baseline. These results demonstrate that combining accurate deep-learning-based forecasting with formal DR optimization can substantially improve both the economic performance and grid-friendliness of renewable microgrids without additional hardware investment.

Article Details

Issue

Vol. 8 No. 4 (2025): International Journal of Research Publications in Engineering, Technology and Management

Section

Articles

How to Cite

Hybrid CNN-LSTM Forecasting and Demand Response Optimization for Energy Flexibility and Cost Reduction in Grid-Connected Renewable Microgrids. (2025). International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 8(4), 12583-12593. https://doi.org/10.15662/IJRPETM.2025.0804024

References

[1]. Wang, H., Lei, Z., Zhang, X., Zhou, B., & Peng, J. (2019). A review of deep learning for renewable energy forecasting. Energy Conversion and Management, 198, 111799.

[2]. Kim, T. Y., & Cho, S. B. (2019). Predicting residential energy consumption using CNN-LSTM neural networks. Energy, 182, 72–81.

[3]. Siano, P. (2014). Demand response and smart grids—A survey. Renewable and Sustainable Energy Reviews, 30, 461–478.

[4]. Zhang, D., Shah, N., & Papageorgiou, L. G. (2013). Efficient energy consumption and operation management in a smart building with microgrid. Energy Conversion and Management, 74, 209–222.

[5]. Vardakas, J. S., Zorba, N., & Verikoukis, C. V. (2015). A survey on demand response programs in smart grids: Pricing methods and optimization algorithms. IEEE Communications Surveys & Tutorials, 17(1), 152–178.

[6]. Qiu, X., Ren, Y., Suganthan, P. N., & Amaratunga, G. A. J. (2017). Empirical mode decomposition based ensemble deep learning for load demand time series forecasting. Applied Soft Computing, 54, 246–255.

[7]. Mesarić, P., & Krajcar, S. (2015). Home demand side management integrated with electric vehicles and renewable energy sources. *Energy and Buildings*, 108, 1–9.

[8]. Parisio, A., Rikos, E., & Glielmo, L. (2014). A model predictive control approach to microgrid operation optimization. IEEE Transactions on Control Systems Technology, 22(5), 1813–1827.

[9]. Aghaei, J., & Alizadeh, M. I. (2013). Demand response in smart electricity grids equipped with renewable energy sources: A review. Renewable and Sustainable Energy Reviews, 18, 64–72.

[10]. Shi, H., Xu, M., & Li, R. (2018). Deep learning for household load forecasting—A novel pooling deep RNN. IEEE Transactions on Smart Grid, 9(5), 5271–5280.

[11]. Kong, W., Dong, Z. Y., Jia, Y., Hill, D. J., Xu, Y., & Zhang, Y. (2019). Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Transactions on Smart Grid, 10(1), 841–851.

[12]. Rahman, A., Srikumar, V., & Smith, A. D. (2018). Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks. Applied Energy, 212, 372–385.

[13]. Lim, S.-C., Huh, J.-H., Hong, S.-H., Park, C.-Y., & Kim, J.-C. (2022). Solar power forecasting using CNN–LSTM hybrid model. Energies, 15(21), 8034.

[14]. Albogamy, F. R., Hafeez, G., Khan, I., Khan, S., Alkhammash, H. I., Ali, F., & Rukh, G. (2021). Efficient energy optimization day-ahead energy forecasting in smart grid considering demand response and microgrids. Sustainability, 13(20), 11350.

[15]. Vinothine, S., Widanagama Arachchige, L. N., & Rajapakse, A. D. (2022). Microgrid energy management and methods for managing forecast uncertainties. Energies, 15(22), 8510.

[16]. Koltsaklis, N. E., Panapakidis, I. P., Pozo, D., & Christoforidis, G. C. (2021). A prosumer model based on smart home energy management and forecasting techniques. Energies, 14(6), 1645.

[17]. Agga, A., Abbou, A., Labbadi, M., & El Houm, Y. (2021). Short-term self-consumption PV plant power production forecasts based on hybrid CNN–LSTM. Energy, 225, 120250.

[18]. Shahid, F., Zameer, A., & Muneeb, M. (2021). A novel genetic LSTM model for wind power forecast. Energy, 223, 120069.

[19]. Dittmer, C., Krümpel, J., & Lemmer, A. (2021). Power demand forecasting for demand-driven energy production with biogas plants. Renewable Energy, 163, 1871–1877.

[20]. Maślak, G., & Orłowski, P. (2025). A robust energy flow predictor based on CNN–LSTM for prosumer-oriented microgrids considering changes in biogas generation. Energy, 326, 136050.

[21]. Sekhar, C., & Dahiya, R. (2023). Robust framework based on hybrid deep learning approach for short-term load forecasting of building electricity demand. Energy, 268, 126602.

[22]. Cheng, Z., Wang, L., & Yang, Y. (2023). A hybrid feature pyramid CNN–LSTM model with seasonal inflection month correction for medium- and long-term power load forecasting. Energies, 16(7), 3126.

[23]. Biswas, M. A. R., Robinson, M. D., & Fumo, N. (2016). Prediction of residential building energy consumption: A neural network approach. Energy, 117, 84–92.

[24]. Wazirali, R., et al. (2023). State-of-the-art review on energy and load forecasting in microgrids using artificial neural networks, machine learning, and deep learning techniques. Electric Power Systems Research.

[25]. Kim, T.-Y., & Cho, S.-B. (2019). Predicting residential energy consumption using CNN–LSTM neural networks. Energy, 182, 72–81.