{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T16:17:45Z","timestamp":1781540265879,"version":"3.54.5"},"reference-count":24,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:00:00Z","timestamp":1768435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>This paper addresses the critical need for efficient energy management in healthcare facilities, where fluctuating energy demands pose challenges to both operational reliability and sustainability objectives. Traditional energy management approaches often fall short in healthcare settings, resulting in inefficiencies and increased operational costs. To address this gap, the paper explores AI-driven methods for demand forecasting and load balancing and proposes an integrated framework combining Long Short-Term Memory (LSTM) networks, a genetic algorithm (GA), and SHAP (Shapley Additive Explanations), specifically tailored for healthcare energy management. While LSTM has been widely applied in time-series forecasting, its use for healthcare energy demand prediction remains relatively underexplored. In this study, LSTM is shown to significantly outperform conventional forecasting models, including ARIMA and Prophet, in capturing complex and non-linear demand patterns. Experimental results demonstrate that the LSTM model achieved a Mean Absolute Error (MAE) of 21.69, a Root Mean Square Error (RMSE) of 29.96, and an R2 of approximately 0.98, compared to Prophet (MAE: 59.78, RMSE: 81.22, R2 \u2248 0.86) and ARIMA (MAE: 87.73, RMSE: 125.22, R2 \u2248 0.66), confirming its superior predictive performance. The genetic algorithm is employed both to support forecasting optimisation and to enhance load balancing strategies, enabling adaptive energy allocation under dynamic operating conditions. Furthermore, SHAP analysis is used to provide interpretable, within-model insights into feature contributions, improving transparency and trust in AI-driven energy decision-making. Overall, the proposed LSTM\u2013GA\u2013SHAP framework improves forecasting accuracy, supports efficient energy utilisation, and contributes to sustainability in healthcare environments. Future work will explore real-time deployment and further integration with reinforcement learning to enable continuous optimisation.<\/jats:p>","DOI":"10.3390\/systems14010094","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T08:08:21Z","timestamp":1768550901000},"page":"94","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["AI-Based Demand Forecasting and Load Balancing for Optimising Energy Use in Healthcare Systems: A Real Case Study"],"prefix":"10.3390","volume":"14","author":[{"given":"Isha","family":"Patel","sequence":"first","affiliation":[{"name":"Faculty of Engineering & Information Technology, University of Technology Sydney, Sydney, NSW 2007, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3780-4726","authenticated-orcid":false,"given":"Iman","family":"Rahimi","sequence":"additional","affiliation":[{"name":"Faculty of Engineering & Information Technology, University of Technology Sydney, Sydney, NSW 2007, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"101205","DOI":"10.1016\/j.esr.2023.101205","article-title":"Optimal location selection for a distributed hybrid renewable energy system in rural Western Australia: A data mining approach","volume":"50","author":"Holloway","year":"2023","journal-title":"Energy Strategy Rev."},{"key":"ref_2","first-page":"100855","article-title":"Optimizing renewable energy site selection in rural Australia: Clustering algorithms and energy potential analysis","volume":"25","author":"Rahimi","year":"2025","journal-title":"Energy Convers. Manag. X"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Prananda, R., Dini, H.S., and Putri, T.W. (2021, January 5\u20136). Design of Load Balancing Method on Secondary Distribution Network Using Artificial Intelligence Based on Fuzzy Logic. Proceedings of the 3rd International Conference on High Voltage Engineering and Power Systems, ICHVEPS, Bandung, Indonesia.","DOI":"10.1109\/ICHVEPS53178.2021.9600977"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Masri, D., Zeineldin, H., and Woon, W.L. (2015, January 10\u201313). Electricity price and demand forecasting under smart grid environment. Proceedings of the IEEE International Conference on Environmental and Electrical Engineering (EEEIC), Rome, Italy.","DOI":"10.1109\/EEEIC.2015.7165472"},{"key":"ref_5","unstructured":"(2025, November 14). Benefits of Energy Efficiency in Healthcare. Available online: https:\/\/www.sitelogiq.com\/blog\/benefits-energy-efficiency-healthcare."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Huang, Y., Xu, C., Ji, M., Xiang, W., and He, D. (2020). Medical service demand forecasting using a hybrid model based on ARIMA and self-adaptive filtering method. BMC Med. Inform. Decis. Mak., 20.","DOI":"10.1186\/s12911-020-01256-1"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"48737","DOI":"10.1109\/ACCESS.2024.3380159","article-title":"Energy Efficient Load Balancing Algorithm for Cloud Computing Using Rock HYrax Optimisation","volume":"12","author":"Singhal","year":"2024","journal-title":"IEEE Access"},{"key":"ref_8","first-page":"109899","article-title":"Artificial Intelligence and Machine Learning Approaches to energy demand side response: A systematic review","volume":"130","author":"Antonopoulos","year":"2020","journal-title":"Energy Rev."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Junaid, S., Imam, A., Balogun, A., De Silva, L., Surakat, Y., Kumar, G., Abdulkarim, M., Shuaibu, A.N., Garba, A., and Sahalu, Y. (2022). Recent Advancements in Emerging Technologies for Healthcare Management Systems: A Survey. Healthcare, 10.","DOI":"10.3390\/healthcare10101940"},{"key":"ref_10","unstructured":"Bajaj, A. (2025, November 14). ARIMA & SARIMA: Real-World Time Series Forecasting. Neptune.ai. Available online: https:\/\/neptune.ai\/blog\/arima-sarima-real-world-time-series-forecasting-guide."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Bolstad, D.A., Cali, U., Kuzlu, M., and Halden, U. (2022, January 24\u201328). Day-ahead Load Forecasting using Explainable Artificial Intelligence. Proceedings of the IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), New Orleans, LA, USA.","DOI":"10.1109\/ISGT50606.2022.9817538"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Patni, J.C., and Aswal, M.S. (2015, January 4\u20135). Dynamic load balancing model for layered grid architecture. Proceedings of the 1st International Conference on Next Generation Computing Technologies (NGCT), Dehradun, India.","DOI":"10.1109\/NGCT.2015.7375095"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lan, W., Li, F., Liu, X., and Qiu, Y. (2018, January 10\u201311). A Dynamic Load Balancing Mechanism for Distributed Controllers in Software-Defined Networking. Proceedings of the 10th Inetrnational Confereence on Measuring Technology and Mechatronics Automation (ICMTMA), Changsha, China.","DOI":"10.1109\/ICMTMA.2018.00069"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Rani, S., Kumar, D., and Dhingra, S. (2022, January 4\u20135). A review on dynamic load balancing algorithms. Proceedings of the International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), Greater Noida, India.","DOI":"10.1109\/ICCCIS56430.2022.10037671"},{"key":"ref_15","unstructured":"Praveena, S., and Prasanna Devi, S. (2022, January 9\u201310). A Hybrid Demand Forecasting for Intermittent Demand Patterns using Machine Learning Technqiues. Proceedings of the 1st International Conference on Computational Science and Technology (ICCST), Chennai, India."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hameed, Z., Hashemi, S., and Tr\u00e6holt, C. (2021, January 10\u201312). Applications of AI-Based Forecasts in Renewable Based Electricity Balancing Markets. Proceedings of the 22nd IEEE International Conference on Industrial Technology (ICIT), Valencia, Spain.","DOI":"10.1109\/ICIT46573.2021.9453469"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Doshi, R., Mridha, K., Kumar, D., and Ved, A. (2021, January 27\u201329). Medium and Short-Term Energy Forecasting using LSTM Neural Network Method of Gujrat State. Proceedings of the Asian Conference on Innovation in Technology (ASIANCON), Pune, India.","DOI":"10.1109\/ASIANCON51346.2021.9544812"},{"key":"ref_18","unstructured":"Tam, A. (2025, November 14). LSTM for Time Series Prediction in PyTorch. Machine Learning Mastery. Available online: https:\/\/machinelearningmastery.com\/lstm-for-time-series-prediction-in-pytorch\/."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100640","DOI":"10.1016\/j.tbs.2023.100640","article-title":"Machine learning techniques for evaluating the nonlinear link between built-environment characteristics and travel behaviours: A systematic review","volume":"33","author":"Aghaabbasi","year":"2023","journal-title":"Travel Behav. Soc."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"115736","DOI":"10.1016\/j.eswa.2021.115736","article-title":"Explaining anomalies detected by autoencoders using Shapley Additive Explanations","volume":"186","author":"Antwarg","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1016\/j.accre.2021.07.008","article-title":"Hospital healthcare costs attributable to heat and future estimations in the context of climate change in perth, Western Australia","volume":"12","author":"Tong","year":"2021","journal-title":"Adv. Clim. Change Res."},{"key":"ref_22","unstructured":"Australian Energy Market Operator (2021). Renewable Energy Integration\u2014SWIS Update, AEMO."},{"key":"ref_23","unstructured":"(2025, November 14). File:Australia Location map.svg\u2014Wikimedia Commons. Available online: https:\/\/commons.wikimedia.org\/wiki\/File:Australia_location_map.svg."},{"key":"ref_24","unstructured":"NSW Governemnt (2025, November 14). Building Energy Use in NSW Public Hospitals. Data.NSW, Available online: https:\/\/data.nsw.gov.au\/data\/dataset\/3-12844-building-energy-use-in-nsw-public-hospitals."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/94\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T08:45:46Z","timestamp":1768553146000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/94"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,15]]},"references-count":24,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["systems14010094"],"URL":"https:\/\/doi.org\/10.3390\/systems14010094","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,15]]}}}