Effective building energy prediction is essential for optimizing energy management, but existing models struggle with data scarcity and sensor heterogeneity across different buildings. Conventional approaches, including centralized and transfer learning methods, fail to generalize well due to varying sensor configurations and inconsistent data availability. To overcome these challenges, this study proposes a Personalized Federated Learning (pFL) framework that integrates multi-level feature masking, model ensemble techniques, and knowledge transfer to enhance predictive performance across diverse buildings. The proposed feature masking strategy extracts the most relevant time-series features, while model ensemble learning improves generalization, and knowledge transfer enables adaptive fine-tuning for each building. These techniques allow pFL to retain global knowledge while personalizing to local energy consumption patterns, making it more effective than traditional FL methods. Experiments conducted on a campus energy dataset demonstrate that pFL consistently outperforms FedAvg, FedProx, and standalone models in energy prediction accuracy. The most significant improvements are observed in buildings with highly fluctuating consumption patterns, validating the effectiveness of the proposed approach in handling heterogeneous sensing environments. This study highlights the potential of Federated Learning for scalable and adaptive energy prediction. Future work will focus on refining multi-horizon forecasting and developing strategies to enhance knowledge sharing among buildings for improved long-term performance.
This paper describes the method to create the HL7 message dynamically and make the HL7 middleware framework more efficient. The HL7 middleware framework was developed for exchanging the healthcare information in the National Taiwan University Hospital (NTUH). The framework is a Service-Oriented Architecture (SOA) and it contains the HL7Central Web Service. The Web Service makes the HL7 middleware framework more flexible and independent of programming language.
The aim of this paper is to propose a cloud-based data mining (DM) platform for researchers in three different geographic locations (Canada, Taiwan and Mongolia) for sharing research data/results through the Internet while remaining cost effective, flexible, secure and privacy-preserved. In addition, the study evaluates the implementation challenges of the cloud based platform and provides potential solutions to handle the identified issues so that other similar research can use this study as a reference to determine whether (or how) to migrate from traditional to cloud-based services.
Having brief consideration on mathematical modeling and methods of steady state calculation of energy system, analyzed its advantage and lack, chose the Newton-type linear minimization third method, scientific software ldquoPROJECTrdquo initiated based on the method a research work for minimum summer load flow of 2007 electric power system of the central area Mongolia have been carried out.