A Systematic Review of Resource Allocation Strategies in Cloud-Assisted Wireless Sensor Networks

This systematic examination consolidates the body of work regarding resource distribution methodologies in cloud-assisted Wireless Sensor Networks (WSNs), accentuating their progression, theoretical underpinnings, contemporary trends, applications, and deficiencies. The principal contribution is a thorough categorization of methodologies into optimization-centric, game theory-centric, and machine learning-centric approaches, with meticulous comparisons via tables and diagrams to assess their efficacy in terms of energy efficiency, scalability, latency, and security. Significant findings encompass the preeminence of hybrid machine learning models in dynamic contexts, attaining up to ۳۰% enhanced energy efficiency in recent investigations, whilst pinpointing inadequately explored domains such as real-world empirical validation and privacy integration. This review furnishes a strategic framework for forthcoming research, underscoring the necessity for interdisciplinary solutions to reconcile efficiency and security within IoT ecosystems.

کلیدواژه ها:

Cloud-assisted WSNs ، Edge-cloud architectures ، Energy efficiency ، Machine learning ، Resource allocation ، Sensing-as-a-Service