Jul 2026· Annual Conference on Genetic and Evolutionary Computation· pp. 1267-1275· 0 citations· 30 references
Computer Science
TL;DR
This paper introduces the Committee-Based Active Learning Surrogate-Assisted Particle Swarm Optimization (QBC-SA-PSO) framework, which combines multiple surrogate models with a Query by Committee (QBC) strategy to intelligently approximate fitness evaluations.
Abstract
Efficient real-time resource allocation for electric vehicle (EV) charging in Fog computing environments demands fast and intelligent decision-making under strict quality-of-service constraints. Traditional metaheuristics like genetic algorithms and differential evolution yield high-quality solutions but incur prohibitive computational costs, limiting their applicability in real-time systems. This paper introduces the Committee-Based Active Learning Surrogate-Assisted Particle Swarm Optimization (QBC-SA-PSO) framework, which combines multiple surrogate models with a Query by Committee (QBC) strategy to intelligently approximate fitness evaluations. By balancing exploration and exploitation, the framework drastically reduces the need for expensive exact simulations while maintaining near-optimal solution quality. Experimental validation on EV charging datasets demonstrates that PSO-SA-QBC converges within only 33 iterations, achieving a 66% reduction compared to traditional simulation techniques replaced with exact fitness evaluations, while preserving over 99% solution quality.
Aiming to address the problems of interest conflict between charging stations and electric vehicle (EV) owners, as well as severe load fluctuations caused by disorderly EV charging, this paper proposes a multi-objective optimal scheduling model based on an improved NSGA-III algorithm (TSM-NSGA-III). The model utilizes dynamic electricity price as a decision variable instead of a fixed time-of-use price, with optimization objectives set to maximize charging station profit, maximize EV owner satisfaction, and minimize the load peak-valley difference rate. The TSM-NSGA-III algorithm enhances the original NSGA-III through three key improvements: (1) chaotic reverse learning to improve initial population quality, (2) the sparrow search algorithm to avoid local optima, and (3) Manhattan distance to preserve population diversity and discover potential optimal solutions. Experimental results demonstrate that the proposed method achieves a 26% faster convergence and a 9.9% higher average solution quality compared to NSGA-III. Furthermore, it obtains superior Pareto frontiers with significantly better performance in both charging station revenue and user satisfaction, effectively overcoming the algorithm’s tendencies toward premature convergence and neglect of diverse optimal solutions.
Yun Wu, Ziyi Wang, Yan Du et al.· Journal of Advanced Computat...· 0 citations
The rapid transition toward sustainable electrified transportation has led to the urgent deployment of electric vehicle (EV) fleets in urban logistics, where limited battery capacity and the need for en-route charging introduce new challenges for EV routing optimization. The final route, travel time, and operational cost are directly affected by the inclusion of charging stations in the routing objective. Unlike conventional vehicle routing problems (VRPs), the electric VRP (EVRP) requires energy feasibility constraints to be tightly integrated with routing decisions. In this study, we introduce a scalable, simulation-based EVRP framework that explicitly incorporates charging-station insertion into a metaheuristic optimization solver. A particle swarm optimization (PSO) approach is adopted to address the combinatorial complexity of large-scale instances, while feasibility is enforced through state-of-charge tracking and adaptive charging decisions. The proposed framework is evaluated and compared with a heuristic baseline algorithm (BR-TSP) under multiple simulation scenarios. Results demonstrate that the proposed approach is fully feasible across all tested scenarios, significantly outperforms classical exact solvers in scalability, and highlights the critical role of explicit charging integration in realistic EV fleet operations. The findings reveal practical strategies for energy-aware routing in large-scale electric mobility applications.
Khaled Bouhadef, José Almeida, Jo˜ao Soares et al.· Proceedings of the Genetic a...· 0 citations
This paper proposes a coordinated energy management framework for plug-in electric vehicle (EV) charging and discharging that minimizes operational cost while preserving grid stability under uncertain user behavior. The uncertainty of charging demand is represented through stochastic initial state-of-charge (SOC) levels, which capture the variability of EV energy requirements upon arrival. Based on this uncertainty representation, an optimization model incorporating battery dynamics, time-of-use (TOU) pricing, vehicle-to-grid capability, mobility constraints, and peak demand limits is formulated. To solve the resulting nonlinear optimization problem, the Grey Wolf Optimization (GWO) algorithm is employed and benchmarked against Genetic Algorithm (GA), Non-dominated Sorting Genetic Algorithm-II (NSGA-II), and Particle Swarm Optimization (PSO) Algorithm. Simulation studies conducted on a fleet of EVs over a 24-hour scheduling horizon demonstrate that the proposed framework maintains SOC within the safe operating range while ensuring that all vehicles satisfy the departure SOC target.
D. C. Huynh, Loc D. Ho, M. Dunnigan· 2026 6th International Confe...· 0 citations
The proposed RSO–SFO framework integrates both strategies within a unified fitness function designed to minimize deployment cost while ensuring efficient allocation of fog resources, confirming the effectiveness and robustness of the proposed hybrid strategy for optimal service placement in fog-based IoT environments.
H. Merouani, S. Bendib, H. Moumen et al.· Revista Internacional de Mét...· 0 citations
Resource allocation in the cloud-edges is extremely important to reduce the time of execution, energy usage, and service-level agreement (SLA) breaches when experiencing dynamic workloads. In this paper, the author has proposed an elite co-evolution hybrid optimization model, Hybrid Hierarchical Optimization for Cloud Allocation (H2O-Cloud), which combines Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) using periodic elite migration and adaptive multi-objective evaluation. The suggested approach is also optimal in terms of makespan, SLA violation rate, energy consumption, and resource usage. Real world Azure LLM Inference Trace datasets (both code-generation, conversational AI) were used to run experiments. The analysis took into account scalable loads of 300 to 1200 tasks on heterogeneous cloud virtual machines, edge-only and hybrid edge-cloud infrastructure. Measurements confirm that H2O-Cloud is drastically more efficient than traditional FCFS scheduling with the maximum makespan decrease of 39.7% and throughput enhancement of 65.8% and SLA violation decrease of 17.1% when using the cloud only (900-task workload). The proposed approach results in an 8.0 percent reduction in makespan and a better resource utilization than PSO. Moreover, H2O-Cloud remains competitive in terms of energy efficiency and also shows better scalability to a larger amount of tasks. The strength of the proposed approach is statistically verified with the help of paired tests. This hybrid co-evolution mechanism contributes to both global exploration and local refinement at the same time, which allows the stable convergence and best load balancing on heterogeneous resources. The framework also exhibits high flexibility in edge-cloud hybrid systems, which minimizes SLA breaches and balances the energy usage. The experimental results confirm H2O-Cloud as a strong, scalable and SLA conscious resource provision strategy to next-generation AI-driven cloud computing systems.
D.Bhuvaneswari, S.Jeevitha, Prashant Sangulagi et al.· 2026 6th International Confe...· 0 citations
This paper proposes a QoS-aware and energy-efficient metaheuristic optimization-based service placement strategy for an integrated IoT and fog computing environment to improve QoS and demonstrates that the developed hybrid algorithm reduces energy consumption by 3.09% and minimize network usage significantly compared with baselines.
Pallavi Mettupalli Venkata, Thatikonda Supraja, Priyanka Chawla et al.· Journal of Supercomputing· 0 citations
