{"ID":2891854,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16668","arxiv_id":"2507.16668","title":"FOGNITE: Federated Learning-Enhanced Fog-Cloud Architecture","abstract":"Modern smart grids demand fast, intelligent, and energy-aware computing at the edge to manage real time fluctuations and ensure reliable operation. This paper introduces FOGNITE Fog-based Grid In intelligence with Neural Integration and Twin based Execution a next-generation fog cloud framework designed to enhance autonomy, resilience, and efficiency in distributed energy systems. FOGNITE combines three core components: federated learning, reinforcement learning, and digital twin validation. Each fog node trains a local CNN LSTM model on private energy consumption data, enabling predictive intelligence while preserving data privacy through federated aggregation. A reinforcement learning agent dynamically schedules tasks based on current system load and energy conditions, optimizing for performance under uncertainty. To prevent unsafe or inefficient decisions, a hierarchical digital twin layer simulates potential actions before deployment, significantly reducing execution errors and energy waste. We evaluate FOGNITE on a real world testbed of Raspberry Pi devices, showing up to a 93.7% improvement in load balancing accuracy and a 63.2% reduction in energy waste compared to conventional architectures. By shifting smart grid control from reactive correction to proactive optimization, FOGNITE represents a step toward more intelligent, adaptive, and sustainable energy infrastructures","short_abstract":"Modern smart grids demand fast, intelligent, and energy-aware computing at the edge to manage real time fluctuations and ensure reliable operation. This paper introduces FOGNITE Fog-based Grid In intelligence with Neural Integration and Twin based Execution a next-generation fog cloud framework designed to enhance auto...","url_abs":"https://arxiv.org/abs/2507.16668","url_pdf":"https://arxiv.org/pdf/2507.16668v1","authors":"[\"Somayeh Sobati-M\"]","published":"2025-07-22T15:01:16Z","proceeding":"cs.DC","tasks":"[\"cs.DC\"]","methods":"[\"Reinforcement Learning\",\"Convolutional Neural Network\"]","has_code":false}