Development of an Enhanced Multi-Objective Algorithm for Optimal Quality-aware Web Service Composition in the Internet of Things
Subject Areas : مهندسی برق و کامپیوتر
Narges Zahiri
1
,
Fereshte Dehghani
2
,
Salman Goli
3
1 - Computer Engineering Department, Faculty of Electrical And Computer Engineering, University of Kashan, Kashan, Isfahan
2 - Computer Engineering Department, Faculty of Electrical And Computer Engineering, University of Kashan, Kashan, Isfahan
3 - Computer Engineering Department, Faculty of Electrical And Computer Engineering, University of Kashan, Kashan, Isfahan
Keywords: Evolutionary Algorithm, Internet of Things, multi-objective optimization, optimal web service composition and selection, quality-aware web services,
Abstract :
The emergence of the Internet of Things (IoT) has intensified the focus on web service composition and the fulfillment of increasingly complex and diverse user requirements. IoT-based systems often encounter numerous service candidates with varying qualitative attributes, presenting a significant challenge in selecting an optimal combination. This problem, categorized as NP-hard, requires efficient approaches for resolution. This study proposes a near-optimal solution for web service composition in IoT environments by leveraging the NSGA-III multi-objective metaheuristic algorithm to identify the optimal Pareto front. To further enhance the quality and diversity of the solutions, an improved algorithm integrating NSGA-III with a novel fitness function is introduced. The proposed approach optimizes service composition using nine quality parameters, which are subsequently streamlined into three principal objectives for better computational efficiency. Experimental evaluations demonstrate that the proposed method outperforms the baseline NSGA-III algorithm in terms of the average performance of two out of three objectives. Additionally, the approach achieves an average of 11% higher coverage based on performance indices and exhibits superior solution distribution and dispersion compared to alternative algorithms.