Jul 2026· 2026 6th International Conference on Inventive Computation and Information Technologies (ICICIT)· pp. 1791-1796· 0 citations· 15 references
Abstract
Due to the rapid proliferation of Industrial Internet of Things (IIoT) systems within smart industries, scalable, energy-efficient, and sustainable edge intelligence solutions are in demand. Despite the fact that Federated Learning (FL) allows collaborative training without raw data sharing, traditional FL methods have high communication overhead, huge model sizes, and require a lot of energy, which restricts their implementation in resource-constrained industrial settings. To address these issues, the present paper introduces a Green Federated Learning framework, GFed-AMP, a sustainable IIoT edge intelligent framework that includes Adaptive Model Pruning.The suggested framework incorporates the dynamic magnitude-based pruning of local updates to eliminate redundant parameters and lessen the computational complexity. A strategy of energy-conscious client selection assigns priority to the devices with larger residual energy and with lower carbon intensity, to make sure that participation is environmentally conscious. It has real-time energy and carbon monitoring modules that can be used to gauge power consumption and environmental effects during federated training. Moreover, a sparse-awares aggregation mechanism is an effective method which optimally manages pruned model updates and ensures stable convergence. Experimental assessment of industrial anomaly detection data sets shows that GFed-AMP can achieve up to 40% model reduction, 35% communication overhead reduction, and 30% overall energy reduction in comparison with traditional FedAvg. Notably, the decline in the accuracy of predictions is less than 1.5%, which proves robustness and stability of learning. Better scalability, bandwidth, and lower carbon emission are proven by statistical comparisons. All in all, the overall experience with GFed-AMP’s trade-off between accuracy, communication efficiency, and environmental sustainability is a viable green AI solution to Industry 4.0 deployments.
The Federated Green Anaconda Optimizer (FedGAO), an innovative FL framework inspired by the behavioral patterns of the Green Anaconda Optimizer (GAO), is proposed, demonstrating superior performance in terms of accuracy, convergence speed, and resource efficiency.
Elahe Eslami, S. A. Shahzadeh Fazeli, J. Abouei et al.· Cluster Computing· 0 citations
This study establishes a viable pathway toward integrating federated learning and green AI principles for the sustainable, intelligent operation of future 6G WSNs and introduces an adaptive client selection mechanism that prioritizes nodes with higher residual energy and better local model quality to participate in each training round, further enhancing sustainability.
Hongyuan Wang, Shi-Kai He, Yiping Jiang et al.· International Journal of Com...· 0 citations
The rapid growth of large-scale interconnected systems, such as smart cities, industrial automation, and environmental monitoring, demands intelligent decision-making frameworks that are resilient, scalable, and resource-efficient. Traditional centralized intelligence approaches suffer from communication bottlenecks, high energy demands, and vulnerability to single points of failure, making them unsuitable for realworld deployment. This work introduces an event-triggered decentralized intelligence framework with energy-aware federated learning designed to address these challenges. In the proposed system, distributed nodes collaborate by exchanging model updates only when significant events or anomalies occur, rather than relying on continuous communication. This event-driven strategy substantially reduces bandwidth consumption while enabling timely adaptation to dynamic environments. To further enhance sustainability, the framework integrates energy-aware scheduling, allowing devices with limited power resources to contribute adaptively based on their energy profiles. A multilayer coordination mechanism ensures local autonomy and global consensus without centralized control. Experimental evaluations on representative real-world datasets demonstrate that the proposed method achieves competitive accuracy compared to conventional federated learning while reducing communication overhead by more than 40% and extending device lifetime in energy-constrained settings. Additionally, the framework incorporates Byzantine-resilient aggregation and is analyzed under communication latency and varying network topology conditions.
M. Kishore, N. Velmurugan· 2026 7th International Confe...· 0 citations
The global energy sector is in the process of making a dual transition towards decarbonization and digitalization. This paper discusses how the fundamental digital technologies, Internet of Things (IoT), Artificial Intelligence (AI), machine learning, digital twins, edge computing, and blockchain facilitate environmental objectives in the energy sector by enhancing efficiency, integrating variable renewables, lowering emissions, and enhancing system resilience. Studies are reviewed to evaluate five pillars of applications, (i) integration of renewable energy through high‑fidelity forecasting, smart inverters, and AI‑aided dispatch, (ii) smart grids that employ ubiquitous sensing, automation, and edge intelligence for real‑time stability, demand response, and losses reduction, (iii) end‑use energy efficiency in buildings and industry through data‑driven controls and digital twin-based optimization, (iv) predictive maintenance of generation and network assets via condition monitoring and fault‑prediction models to reduce downtime and resource waste, and (v) emissions tracking and carbon management through IoT‑enabled monitoring, AI analytics, and blockchain‑backed certificates and markets. Observed benefits encompass double digit gains in energy efficiency, increased renewable penetration without reliability loss, quantifiable decreases in curtailment and peaking demand, and enhanced transparency in carbon accounting. Constrains such as cybersecurity, data privacy, interoperability, worker skills, and the energy profile of digital infrastructure are assessed with mitigation techniques such as privacy-preserving analytics, standard adoption, edge processing, and low-energy consensus mechanisms. Looking ahead, development in AI, IoT, digital-twin grids, 5G/6G‑facilitated edge coordination, sector coupling, and trusted decentralized markets will bring increasingly autonomous, adaptive, and verifiably low-carbon energy systems. Digitalization thereby presents itself as a catalyst and control layer for realizing scalable, equitable, and resilient decarbonization.
Sanjana Santra, B. Kumar· Environment, Social and Gove...· 1 citation
Non-technical losses (NTLs) are a major problem in modern smart grids, damaging revenue and operational functionality. This study proposes an integrated IoT-edge-cloud framework to improve fraud detection, analyze electricity usage patterns, and enhance data reliability in distributed smart grids. The approach extracts multiple features from smart meter data and uses a hybrid machine learning method that combines classification and clustering. To test the system’s robustness, the study included simulated fraud scenarios in difficult circumstances. Results show that the system achieved high detection accuracy (96.4%) and an AUC of 0.98. The framework also reduced false alarms by 86% compared to traditional rule-based methods, improving consistency and productivity. It supports near-real-time operation with response times around 125 ms and is scalable for larger smart grid environments. Behavioral segmentation further improved reliability by identifying differences in electricity consumption and reducing incorrect classifications. Overall, the study shows that combining data quality management, behavioral analysis, and distributed processing yields a more reliable and resilient solution for operational smart grid systems.
F. Otosi, Celestine A. Udie, F. Faithpraise· E3S Web of Conferences· 0 citations
This paper proposes a communication-efficient adaptive federated learning algorithm for heterogeneous defect classification tasks that achieves competitive classification accuracy while reducing single-round training time by up to 70%.
Shuo He, He-Yang Wei, Congxian Bi et al.· Electronics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
