2025· Proceedings of the 1st International Conference on Interdisciplinary Research in Science, Engineering, and Technology· 0 citations· 16 references
TL;DR
An energy-and fairness-aware task offloading (EFATO) scheme through a GA to achieve the optimal task scheduling and loading within multiple edge servers and a novel fitness function is proposed that combines energy cost, computational delay and fairness index.
Abstract
: The rapid growth of low-latency, computation-heavy mobile applications have led to Mobile Edge Computing (MEC) as a promising paradigm that shortens the latency and reduces the energy consumption by placing cloud services close to the end-users. Nevertheless, promoting tradeoffs among energy efficiency (EE), computational fairness and latency minimization is still a challenging issue compared to in multi-server MEC systems. To this end, this paper introduces an energy-and fairness-aware task offloading (EFATO) scheme through a GA to achieve the optimal task scheduling and loading within multiple edge servers. The GA based model of the paper refers a multi-objective optimization problem that minimizes total energy consumption and end-to-end latency involving fair treatment between mobile users. To guarantee fair resource utilization, a novel fitness function is proposed that combines energy cost, computational delay and fairness index. Simulation results show that our EFATO model can outperform the existing methods on energy savings, completion time of task and the fairness index. The proposed scheme also achieves better scalability and faster convergence, which can be used in dynamic MEC for real time applications. In general, the combination of GA-based optimization with fairness constraints can result in fair and sustainable edge computing resource management.
This work aims to design an efficient framework by incorporating a novel hybrid metaheuristic algorithm that combines Draco Lizard Optimization (DLO) and Sand Cat Optimization (SCO) for optimal task offloading and resource allocation for IoT applications.
Cloud computing has transformed the delivery of modern applications and services by providing scalable, flexible, and cost-effective access to computing resources. One of the most critical challenges in cloud environments is the efficient distribution of dynamic workloads across heterogeneous resources, commonly addressed through load balancing and task scheduling techniques. Efficient scheduling plays a vital role in maximizing resource utilization, minimizing response time, and maintaining acceptable Quality of Service (QoS), particularly under dynamic and large-scale workloads. Despite the progress achieved by traditional heuristics such as Min-Min and metaheuristic approaches like the Improved Sparrow Search Algorithm (ISSA), challenges related to scalability, adaptability, and computational overhead remain. Metaheuristic-based approaches often involve iterative optimization processes that may limit their efficiency in real-time scheduling scenarios. In this paper, we propose a lightweight Stochastic Predictive Energy-Aware Scheduling (SPES) algorithm that integrates predictive execution estimation, multi-resource awareness, and stochastic decision-making. Unlike deterministic scheduling strategies, SPES employs a Top K candidate selection mechanism combined with probabilistic weighting and epsilon-greedy exploration to enhance adaptability and avoid suboptimal resource allocation. The proposed method considers CPU, memory, and I/O demands to achieve balanced utilization across heterogeneous hosts while implicitly addressing energy efficiency through utilization-based modeling. The proposed algorithm is implemented and evaluated using the CloudSim 5.0 simulation framework under heterogeneous multi-region cloud environments with varying workload sizes. Experimental results demonstrate that SPES consistently outperforms ISSA and achieves makespan reductions of up to 23.8% while improving scalability, resource utilization, and scheduling efficiency under dynamic cloud workloads. These results indicate that SPES provides an effective lightweight scheduling solution for large-scale and energy-aware cloud computing environments and supports green computing objectives through improved resource efficiency.
M. Yacoub, A. Raouf, Walaa K. Gad et al.· Electronics· 0 citations
Optimal placement of services is a major challenge in the context of fog computing due to the resource-constrained and heterogeneous nature of nodes. Services must be placed optimally without overloading the nodes to fulfill the increasing demand of Internet of Things (IoT) applications. Energy consumption should also be minimized, along with the provision of Quality of Service (QoS). Typical problems of existing metaheuristic approaches, such as premature convergence, limited exploration capability, and high computational cost, result in suboptimal service placement. To solve this problem, we propose a QoS-aware and energy-efficient metaheuristic optimization-based service placement strategy for an integrated IoT and fog computing environment to improve QoS. In this metaheuristic optimization-based strategy, Differential Evolution (DE) is integrated with JAYA-based exploitation, which explores the search space, which in turn accelerates convergence toward optimum service placement in fog computing environments. This proposed strategy accounts for both communication and computational energy consumption when placing service modules, thereby enhancing execution efficiency and optimizing service delay and network usage in constrained fog computing settings. The experimental results demonstrate that the developed hybrid algorithm reduces energy consumption by 3.09% compared to the existing baseline approaches, while optimizing delay and minimizing network usage. Additionally, the proposed approach has been found to minimize network usage significantly compared with baselines.
Pallavi Mettupalli Venkata, Thatikonda Supraja, Priyanka Chawla et al.· Journal of Supercomputing· 0 citations
An adaptive Beta-policy and delayed-update multi-agent soft actor-critic method, abbreviated as ABDMASAC, which uses a Beta policy to model bounded actions and achieves a better overall trade-off than the selected MASAC-backbone and on-policy MARL baselines under the considered simulation settings.
Zheng Yao, Jie Liu, Changjun Deng et al.· Computers, Materials & C...· 0 citations
A distributed Multi-stage Adaptive Deferred Acceptance (MA-DA) algorithm is proposed that enables a stable and Pareto-optimal assignment of tasks to edge computing nodes (ECNs) and determines a reasonable task execution sequence and ensures the prioritized completion of delay-sensitive tasks.
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.