AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
TL;DR
A novel method for the Search and Optimization of IoT Service Composition towards QoS and Energy balance (SOISC-QE) is proposed and an enhanced Dung Beetle Optimization (DBO) is designed by integrating two complementary mechanisms.
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.
Timely, context-aware service recommendations are most significant for maximizing system efficiency and resource utilization in fog-enabled Internet of Things (IoT) for smart agriculture. Classical Grey Wolf Optimization (GWO) algorithms are prone to premature convergence and lack robustness for multi-objective and dynamic environments. This study presents an Enhanced Grey Wolf Optimization (EGWO) algorithm that incorporates adaptive weighting and nonlinear exploration-exploitation control. The EGWO algorithm uses a dynamic alpha-beta-delta hierarchy for weighting and a cosine-based decay for the control parameter, ensuring better convergence and global search efficiency. In the fog-based service recommendation environment, EGWO optimizes multiple conflicting objectives, including latency, energy consumption, trust, and service utility. A comparison is made between standard GWO, PSO, and DE using a simulated agricultural fog-IoT network. The results demonstrate that EGWO achieves faster convergence speed, higher recommendation quality, and uniform behavior across all test scenarios. The method is suitable for practical application in real-time agricultural use cases, ensuring guaranteed optimal service allocation and improved decision support at the network's edge.
The increasing complexity of Internet of Things (IoT) environments requires adaptive mechanisms for efficient service allocation across distributed infrastructures. Existing approaches are often focused on specific optimization algorithms or isolated Quality of Service (QoS) parameters, lacking a unified framework for decision-making across IoT, Fog/Edge, and Cloud layers. This paper proposes a modular QoS-aware decision-making framework that integrates QoS profiles, key performance indicators (KPIs), utility functions, and multi-criteria decision-making mechanisms to support both static and dynamic service allocation. The framework considers service execution latency, energy consumption, network throughput, and network coverage as decision criteria and enables adaptive balancing of conflicting QoS requirements. Its applicability is demonstrated through a smart transportation use case involving multiple service allocation scenarios across CRU, Fog, and Cloud infrastructures. The results confirm that different allocation strategies exhibit distinct QoS trade-offs and demonstrate the suitability of the proposed framework for adaptive and resource-efficient service allocation in layered IoT architectures.
Internet of Things (IoT) involves a large number of interconnected sensor nodes, which sense, communicate, and become active in data processing in resource-constrained settings. This paper proposes a hybrid grey wolf optimization and squirrel search algorithm (GWO-SSA) for optimal cluster head (CH) selection in an IoT network to enhance energy efficiency, reduce delay, and prolong network lifetime. The proposed model integrates SSA into GWO to enhance exploration and exploitation balance, enabling efficient selection of CHs based on temperature, delay, energy, load, and cost function. Experimental results demonstrate that GWO-SSA significantly outperforms existing methods such as GA, ACO, PSO, IPSO, GWO, SSA, and BCO. The proposed approach reduces temperature by 11.93 % and delay by 32.82 % compared to GA, while achieving an energy efficiency improvement of 22.61%. Additionally, the number of alive nodes increased by 21.27%, indicating a substantial enhancement in network lifetime. Load handling capability is improved by 12.70 %, and the cost function is reduced by 15.35 %, confirming effective optimized performance. The GWO-SSA approach provides a robust, scalable, and energy-efficient cluster solution for an IoT environment. The significant improvements across multiple performance metrics validate the effectiveness of the hybrid approach, making it suitable for real-time and large-scale sensor network applications.
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.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.