Energy-Optimized Edge-Fog Computing With Fuzzy Based Iot Routing

The rapid expansion of the Internet of Things (IOT) has led to an unprecedented increase in data traffic, demanding real-time processing, low latency, and energy efficiency. Traditional cloud-centric architectures face significant challenges in managing massive IOT networks due to high power consumption, network congestion, and increased transmission delays. To address these issues, this research proposes an Energy-Optimized Edge-Fog Computing framework with Fuzzy-Based IOT Routing, designed to enhance energy efficiency, minimize traffic delays, and optimize data transmission across large-scale IOT networks. This novel approach integrates edge and fog computing to decentralize computational tasks, reducing reliance on distant cloud servers and enabling faster decision-making closer to IOT devices. The core innovation of this research lies in utilizing fuzzy logic-based intelligent routing that dynamically adjusts energy consumption, bandwidth allocation, and data priority across edge and fog layers. Unlike conventional deterministic routing methods, fuzzy logic provides a human-like reasoning mechanism to handle uncertainty, imprecise traffic conditions, and dynamic network variations. This enables Io T devices to make adaptive routing decisions, selecting the most energy-efficient paths while ensuring low end-to-end latency. Furthermore, the system incorporates machine learning (ML)-assisted predictive analytics, allowing IoT nodes to anticipate congestion patterns and preemptively reroute data traffic to optimize performance. In this framework, fog computing acts as an intermediary between edge devices and cloud infrastructure, reducing unnecessary long-distance data transmissions and significantly lowering energy consumption. The proposed model ensures that critical real-time applications, such as autonomous vehicles, healthcare monitoring, and industrial automation, benefit from low-latency data processing, while non-time-sensitive data can be scheduled for cloud offloading. The energy-aware task allocation mechanism efficiently distributes computational loads among edge and fog nodes, preventing resource exhaustion and extending network lifespan. A key aspect of this research is the integration of reinforcement learning with fuzzy logic-based decision-making, enabling IoT networks to self-optimize over time. The system continuously learns from historical data, adapting to network topology changes, varying traffic loads, and unpredictable IoT device behaviors. By leveraging fuzzy multi-criteria decision- making (FMCDM), the routing process balances energy efficiency, latency constraints, and quality of service (QoS) requirements dynamically, ensuring an optimized network operation.