E2DLB: An Energy Efficient Deadline Aware Load Balancing Algorithm for Fog and Edge Computing

Abstract

As demand for low-latency, energy-efficient processing in IoT applications grows, fog and edge computing have become vital. However, many traditional load-balancing algorithms fail to account for both energy consumption and deadline constraints, which degrades their performance in time-sensitive environments. To address this, we introduce the E2DLB (Energy Efficient Deadline Aware Load Balancing) algorithm. E2DLB distributes tasks across computing nodes to minimize energy use while meeting deadlines. It uses a multilayer architecture that includes smart task classification, deadline-based prioritization, and dynamic offloading to optimize resource use. The algorithm also employs a multi-criteria decision approach to balance energy efficiency and deadlines when evaluating a batch of IoT tasks with varying sizes, needs, and time limits. To prevent overloads and reduce delays, E2DLB uses adaptive thresholds and continuously monitors node statuses. Simulation results show that E2DLB outperforms existing load-balancing solutions in energy savings and deadline compliance. Specifically, it decreases energy consumption by an average of 13% compared to BALBA, over 20% compared to DCLB, and up to 26.88% compared to REAL. This work enhances the sustainability of edge computing by addressing the trade-off between energy efficiency and service quality in real-time distributed systems.