AI-Based Energy Management for Renewable-Integrated Smart Grids using Load Forecasting and Battery Optimization
Main Article Content
Abstract
Renewable-integrated smart grids and commercial microgrids need operating strategies that keep photovoltaic (PV) surplus, time-of-use (TOU) prices and peak-demand charges under control. This paper develops and evaluates a forecast-driven energy management framework that combines (i) day-ahead load and PV forecasting, (ii) a linear-programming battery scheduler with incremental demand-charge accounting, hourly re-optimisation and calibrated uncertainty margins, and (iii) a real-time peak guard that protects execution from forecast errors. It is tested on one year of public hourly hospital-load data and NREL TMY3 irradiance processed through a physical PV model (1.95 MWp PV, 1 MW / 2 MWh battery) under an explicit TOU-plus-demand-charge tariff, using rolling-origin evaluation over 214 days. An ensemble of Ridge regression, random forest, LightGBM and a multilayer perceptron lowers day-ahead load RMSE by 19.8% relative to a seasonal-naïve benchmark (51.9 vs 64.7 kW; MAPE 2.61%), whereas the learned PV forecast improves on smart persistence by only 1.6%. The AI-driven scheduler reduces operating cost by 4.52% ($26,243) and mean monthly peak import by 12.0% relative to PV-only operation, capturing 60.9% of a perfect-foresight bound (7.42%); a persistence-driven scheduler attains a comparable 4.98%, so forecast accuracy gains do not translate one-for-one into savings. Removing the real-time guard turns the saving into a 2.34% loss, and error-scaling experiments show that PV forecast error, rather than load-forecast error, governs the value of information
Article Details
Section
How to Cite
References
1. Alhasnawi, B. N., Jasim, B. H., Alhasnawi, A. N., Hussain, F. F. K., Homod, R. Z., Hasan, H. A., Khalaf, O. I., Abbassi, R., Bazooyar, B., Zanker, M., Bureš, V., & Sedhom, B. E. (2024). A novel efficient energy optimization in smart urban buildings based on optimal demand side management. Energy Strategy Reviews, 54, 101461. https://doi.org/10.1016/j.esr.2024.101461
2. Almassalkhi, M., Madsen, H., Dvorkin, Y., Oral, H. G., Gayme, D. F., Stoustrup, J., Junker, R. G., Ritschel, T., Tohidi, S., Ebrahimy, R., Hodge, B.-M., Hamilton, D., & Mathiesen, B. V. (2026). Cross-Atlantic research agenda for scalable grid architectures and distributed flexibility. Smart Energy, 22, 100236. https://doi.org/10.1016/j.segy.2026.100236
3. Beichter, M., Phipps, K., Frysztacki, M., Mikut, R., Hagenmeyer, V., & Ludwig, N. (2022). Net load forecasting using different aggregation levels. Energy Informatics, 5. https://doi.org/10.1186/s42162-022-00213-8
4. Borghini, E., Giannetti, C., Flynn, J., & Todeschini, G. (2021). Data-Driven Energy Storage Scheduling to Minimise Peak Demand on Distribution Systems with PV Generation. Energies, 14(12), 3453. https://doi.org/10.3390/en14123453
5. Chalendar, J. A. de, Glynn, P. W., & Benson, S. M. (2019). City-scale decarbonization experiments with integrated energy systems. Energy & Environmental Science, 12(5), 1695–1707. https://doi.org/10.1039/c8ee03706j
6. Dalal, N., Mølnå, M., Herrem, M., Røen, M., & Gundersen, O. E. (2021). Day‐ahead forecasting of losses in the distribution network. AI Magazine, 42(2), 38–49. https://doi.org/10.1609/aimag.v42i2.15097
7. Davarzani, S., Granell, R., Taylor, G., & Pisica, I. (2019). Implementation of a novel multi-agent system for demand response management in low-voltage distribution networks. Applied Energy, 253, 113516. https://doi.org/10.1016/j.apenergy.2019.113516
8. Ghimire, S., Deo, R. C., Pourmousavi, S. A., Casillas-Pérez, D., & Salcedo‐Sanz, S. (2024). Point-based and probabilistic electricity demand prediction with a Neural Facebook Prophet and Kernel Density Estimation model. Engineering Applications of Artificial Intelligence, 135, 108702. https://doi.org/10.1016/j.engappai.2024.108702
9. Groß, A., Lenders, A., Schwenker, F., Braun, D., & Fischer, D. S. (2021). Comparison of short-term electrical load forecasting methods for different building types. Energy Informatics, 4. https://doi.org/10.1186/s42162-021-00172-6
10. Hong, T., Pinson, P., Wang, Y., Weron, R., Yang, D., & Zareipour, H. (2020). Energy Forecasting: A Review and Outlook. IEEE Open Access Journal of Power and Energy, 7, 376–388. https://doi.org/10.1109/oajpe.2020.3029979
11. Jensen, V., Bianchi, F. M., & Anfinsen, S. N. (2022). Ensemble Conformalized Quantile Regression for Probabilistic Time Series Forecasting. IEEE Transactions on Neural Networks and Learning Systems, 35(7), 9014–9025. https://doi.org/10.1109/tnnls.2022.3217694
12. Langenmayr, U., Wang, W., & Jochem, P. (2020). Unit commitment of photovoltaic-battery systems: An advanced approach considering uncertainties from load, electric vehicles, and photovoltaic. Applied Energy, 280, 115972. https://doi.org/10.1016/j.apenergy.2020.115972
13. Ledesma, J. R., Almeida, R. H., Martínez‐Moreno, F., Rossa, C. H., Martín-Rueda, J., Narvarte, L., & Lorenzo, E. (2020). A simulation model of the irradiation and energy yield of large bifacial photovoltaic plants. Solar Energy, 206, 522–538. https://doi.org/10.1016/j.solener.2020.05.108
14. Maheshwari, A., Heleno, M., & Ludkovski, M. (2020). The effect of rate design on power distribution reliability considering adoption of distributed energy resources. Applied Energy, 268, 114964. https://doi.org/10.1016/j.apenergy.2020.114964
15. Mariano-Hernández, D., Hernández-Callejo, L., Zorita-Lamadrid, Á., Duque-Pérez, Ó., & García, F. S. (2020). A review of strategies for building energy management system: Model predictive control, demand side management, optimization, and fault detect & diagnosis. University of Valladolid Documentary Repository (University of Valladolid), 33, 101692. https://doi.org/10.1016/j.jobe.2020.101692
16. Markovics, D., & Mayer, M. J. (2022). Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction. Renewable and Sustainable Energy Reviews, 161, 112364. https://doi.org/10.1016/j.rser.2022.112364
17. Meiers, J., & Frey, G. (2023). A Case Study of the Use of Smart EV Charging for Peak Shaving in Local Area Grids. Energies, 17(1), 47. https://doi.org/10.3390/en17010047
18. Mustafa, M. B., Keatley, P., Huang, Y., Agbonaye, O., Ademulegun, O. O., & Hewitt, N. (2021). Evaluation of a battery energy storage system in hospitals for arbitrage and ancillary services. Journal of Energy Storage, 43, 103183. https://doi.org/10.1016/j.est.2021.103183
19. Nair, U. R., Sandelić, M., Sangwongwanich, A., Dragičević, T., Costa‐Castelló, R., & Blaabjerg, F. (2020). Grid Congestion Mitigation and Battery Degradation Minimisation Using Model Predictive Control in PV-Based Microgrid. IEEE Transactions on Energy Conversion, 36(2), 1500–1509. https://doi.org/10.1109/tec.2020.3032534
20. Nejla, E., Saidani, K., & Besbes, M. (2025). Overcoming the integration bottleneck: a global review of renewable energy and grid adaptation strategies. International Journal of Sustainable Energy, 44(1). https://doi.org/10.1080/14786451.2025.2569922
21. Pimm, A., Palczewski, J., Morris, R., Cockerill, T., & Taylor, P. (2019). Community energy storage: A case study in the UK using a linear programming method. Energy Conversion and Management, 205, 112388. https://doi.org/10.1016/j.enconman.2019.112388
22. Rosewater, D., Baldick, R., & Santoso, S. (2019). Risk-Averse Model Predictive Control Design for Battery Energy Storage Systems. IEEE Transactions on Smart Grid, 11(3), 2014–2022. https://doi.org/10.1109/tsg.2019.2946130
23. Rosewater, D., Copp, D. A., Nguyen, T. A., Byrne, R. H., & Santoso, S. (2019). Battery Energy Storage Models for Optimal Control. IEEE Access, 7, 178357–178391. https://doi.org/10.1109/access.2019.2957698
24. Schmitt, T., Rodemann, T., & Adamy, J. (2021). The Cost of Photovoltaic Forecasting Errors in Microgrid Control with Peak Pricing. Energies, 14(9), 2569. https://doi.org/10.3390/en14092569
25. Talluri, G., Lozito, G. M., Grasso, F., Garcia, C. I., & Luchetta, A. (2021). Optimal Battery Energy Storage System Scheduling within Renewable Energy Communities. Energies, 14(24), 8480. https://doi.org/10.3390/en14248480
26. Vilmarest, J. de, & Goude, Y. (2022). State-Space Models for Online Post-Covid Electricity Load Forecasting Competition. IEEE Open Access Journal of Power and Energy, 9, 192–201. https://doi.org/10.1109/oajpe.2022.3141883
27. Voyant, C., Lauret, P., Notton, G., Duchaud, J.-L., Fouilloy, A., David, M., Yaseen, Z. M., & Soubdhan, T. (2021). A Monte Carlo based solar radiation forecastability estimation. Journal of Renewable and Sustainable Energy, 13(2). https://doi.org/10.1063/5.0042710
28. Voyant, C., & Notton, G. (2018). Solar irradiation nowcasting by stochastic persistence: A new parsimonious, simple and efficient forecasting tool. Renewable and Sustainable Energy Reviews, 92, 343–352. https://doi.org/10.1016/j.rser.2018.04.116
29. Wang, Z., Jochem, P., & Fïchtner, W. (2019). A scenario-based stochastic optimization model for charging scheduling of electric vehicles under uncertainties of vehicle availability and charging demand. Journal of Cleaner Production, 254, 119886. https://doi.org/10.1016/j.jclepro.2019.119886
30. Wood, M. J., Ogliari, E., Nespoli, A., Simpkins, T., & Leva, S. (2023). Day Ahead Electric Load Forecast: A Comprehensive LSTM-EMD Methodology and Several Diverse Case Studies. Forecasting, 5(1), 297–314. https://doi.org/10.3390/forecast5010016
31. Zhang, J., Wang, Y., Jiang, B., He, H., Huang, S., Wang, C., Zhang, Y., Han, X., Guo, D., He, G., & Ouyang, M. (2023). Realistic fault detection of li-ion battery via dynamical deep learning. Nature Communications, 14(1), 5940. https://doi.org/10.1038/s41467-023-41226-5