Jul 2026· International Journal of Swarm Intelligence Research· 0 citations
TL;DR
A three-tier “device–edge–cloud” federated edge collaborative scheduling framework FedAOT is proposed, integrating an improved Artificial Bee Colony algorithm with Optimal Transport for adaptive aggregation optimization.
Abstract
The rapid development of multi-entity distributed energy systems has underscored the importance of source–grid–load–storage coordinated scheduling in improving renewable energy utilization and reducing operating costs. However, traditional centralized scheduling faces privacy risks, computational bottlenecks, and high latency, making it unsuitable for real-time distributed energy management. To address these challenges, this paper proposes a three-tier “device–edge–cloud” federated edge collaborative scheduling framework FedAOT, integrating an improved Artificial Bee Colony (ABC) algorithm with Optimal Transport (OT) for adaptive aggregation optimization. Specifically, an enhanced ABC is proposed to optimize the aggregation weight vector each round, while OT theory constructs optimal mapping relationships among client models, minimizing parameter distribution discrepancies. Simulation results demonstrate that the proposed method dynamically adapts to variations in data distribution and model quality, significantly improving global model accuracy and convergence speed.
As large-scale electric vehicle clusters become increasingly integrated into grid-wide collaborative scheduling, the cross-domain flow of massive user data introduces serious privacy risks. To address these challenges, this study proposed a distributed data privacy protection framework tailored for multiscale collaborative optimization of electric vehicle clusters. The framework mitigated single-point failures and trust issues commonly found in centralized scheduling systems. The proposed approach combined hierarchical federated learning with adaptive differential privacy to establish a three-tier collaborative architecture—vehicle, station, and cloud. At the charging station level, local models were trained with perturbed gradients, where an adaptive noise injection mechanism enforced (ε,δ)-differential privacy. At the cloud level, a multitimescale optimization model was employed: in the day-ahead stage, the globally aggregated hierarchical-federated-learning model predicted the schedulable capacity of electric vehicle clusters.
Haiyan Cao, Jianlin Qiu, Xiaodan Cai et al.· International Journal of Inf...· 0 citations
A DNs cooperative optimization method based on resource aggregation and RL is proposed, which demonstrates the effectiveness and superiority of the proposed method in ensuring the secure operation of DNs.
It is demonstrated that lightweight aggregation strategies can substantially improve empirical safety in federated reinforcement learning while preserving standard communication protocols.
Rapid growth of cloud platforms and large-scale data centers has placed extreme pressure on global power grids and has heavily amplified carbon footprints globally. This literature review delivers a step by evaluation of energy-conservation strategy for green computing, organized across five complementary domains: (1) containerized workload management lever-aging Kubernetes combined with nature-inspired solvers such as Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Dynamic Voltage and Frequency Scaling (DVFS); (2) data-driven energy forecasting using Long Short-Term Memory (LSTM), Transformer, and ensemble neural architectures; (3) thermodynamic optimization of cooling subsystems via metaheuristic search, multi-agent reinforcement learning, and intelligent thermal control; (4) power management at edge data centers through demand aggregation, workload migration, and online Lyapunov-based decision-making; and (5) clean energy sourcing via combined photovoltaic–wind–hydrogen storage topologies. The contribution of this review is synthesized from ten IEEE papers the survey identifies recurring methodological patterns, outstanding technical constraints, and pathways aiming for a cohesive structure for sustainability, autonomously managed infrastructure, self-managing cloud and cloud frameworks. Our comprehensive literature review indicates a lack of research combining high fidelity energy modelling with adaptive control within a single closed - loop framework. To mitigate this limitation, we propose a hybrid architecture combining an LSTM network for multi horizon energy demand forecasting with a Deep Reinforcement Learning agent for real time resource optimization. Overall, the examined works report energy reductions of 9.2% to 45%, quantifiable Power Usage Effectiveness (PUE) improvements, and significant CO2 cuts, validating the impactful potential of algorithmic and systems level innovations for environmental sustainability.
Chandana H M, Ramesh B· International Research Journ...· 0 citations
Integrating distributed energy resources (DERs) via Virtual Power Plants (VPPs) faces challenges like renewable intermittency, communication scheduling uncertainties, and high data collection costs. While existing studies often overlook practical implementation efficiency, this paper proposes a VPP scheduling framework integrated with communication optimization. First, a communication-scheduling model is established to quantify the impact of network uncertainties on revenue. Second, an equipment pre-allocation strategy based on historical data clustering is presented to lower trial-and-error costs and algorithm complexity. Finally, a global optimization algorithm achieves time-segmented collaborative optimization of equipment access, reducing network switching frequency while balancing packet loss, transmission delay, and operational revenue. Simulation results demonstrate that the proposed strategy reduces VPP scheduling revenue loss by approximately 23.6% compared with the traditional greedy algorithm. Furthermore, when evaluated against classic metaheuristic baseline algorithms such as PSO under identical forecasting conditions, Network-Aware FA (NAFA) effectively escapes local optima and achieves the lowest revenue loss, strongly validating the economic efficiency, algorithmic superiority and scheduling reliability of the proposed framework.
Simulation results show that the proposed MARL-BA-ABC framework outperforms Low-Energy Adaptive Clustering Hierarchy (LEACH), Hybrid Energy-Efficient Distributed Clustering (HEED), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Bat Algorithm (BA), and Artificial Bee Colony (ABC), achieving a First Node Death of 2200 rounds.
H. S. Mohammed, Poria Pirozmand, S. Memon et al.· Italian National Conference...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
