In the current smart grid, managing high-energy consumption loads, particularly electric vehicles (EVs), become increasingly complex. This paper introduces a framework that employs non-intrusive load monitoring (NILM) techniques for enhanced energy management in smart grids. Our approach encompasses a broader range of common flexible loads and energy related to EV charging. The NILM technology enables the detailed analysis of individual appliance consumption patterns from aggregated smart meter data, addressing privacy concerns and technical limitations. In detail, we propose a new NILM algorithm, Serial Multi-task Transformer with Attention (SMTA), to address the problem of long-term household load disaggregation. SMTA uses a Serial-Correlation mechanism with period-based dependencies and cyclical information aggregation for effective period time series analysis and utilizes the Task-Specific Attention strategy to find the power influence between appliances. Afterwards, based on the NILM results, we develop an energy management model aiming to optimize the net operation cost in the smart grid, after all active customers participation in ancillary service programs. The proposed framework has been verified on a modified IEEE 57-bus radial distribution system based on real-world household data. The results show that the SMTA algorithm significantly improves load disaggregation accuracy. Furthermore, the proposed framework in comparison to basic energy management. reduces the net operation costs by up to 26.9%, highlighting the substantial economic benefits of integrating NILM into smart grid operations.

Transformer models, which have gained prominence in recent years, serve as the backbone for a wide range of deep learning applications, from natural language processing to computer vision. These models have become indispensable for various inference tasks, but their implementation often faces challenges related to GPU utilization and system throughput. Current GPU-based inference frameworks typically treat each model individually, leading to suboptimal resource management and reduced performance. In response to these limitations, we introduce ITIF: Integrated Transformers Inference Framework for multi-tenants with a shared backbone. By allowing multiple tenants to share a single backbone Transformer model on a single GPU, ITIF consolidates operators from diverse multi-tenant inference models, which in turn optimizes GPU utilization and system throughput. Our proposed framework, ITIF, represents a significant step towards improving the efficiency of deep learning, particularly for large-scale cloud providers hosting numerous models with a shared backbone. In our experiments, ITIF improved performance by up to 2.40 × compared with the baselines.

Federated learning (FL) offers innovative solutions for training complex neural networks on large-scale data without directly accessing participants’ raw data. Owing to its inherent privacy-preserving nature, FL has seen widespread deployment in real-world applications, particularly in social computing. While promising, existing performance evaluations are often one-dimensional and industrial-centric, failing to reflect the human-centered requirements of social computing scenarios. Consequently, how to comprehensively evaluate an FL algorithm and identify the most suitable candidate for social computing remains an open challenge. To mitigate the research gap, we introduce the federated learning social computing performance evaluation (FedSCOPE) framework in this study. FedSCOPE comprises five compulsory components—learning performance, reliability, fairness, robustness, and privacy preservation—that reflect the primary needs of participants in social computing FL systems, and includes an optional personalization component when required. Each component is weighted by an importance factor, and their integration yields a single FedSCOPE index that provides a holistic assessment of an FL algorithm. Three representative case studies in social computing were conducted to evaluate the effectiveness of the proposed FedSCOPE. PriHFLRw, FedAvgRw, and FLTrust achieved FedSCOPE scores of 98.7, 87.5, and 87.73, respectively, and were recommended as suitable algorithms for delivering smart services in the simulated scenarios. We hope this work can offer practical insights and guide the evaluation of FL algorithms in real-world applications.