Energy consumption-based services composition optimization for internet of things

Abstract

Internet of Things (IoT) services are directly deployed on resource-constrained smart devices. Smart devices are characteristic by spatial and temporal constraints and energy limitations. A single IoT service cannot meet the complex requirements of users, so multiple IoT services need to be combined to provide services to users. As more and more smart devices are deployed in IoT, how to select IoT services with lower energy consumption and better quality of service (QoS) for service composition becomes a challenging problem. Combined with the characteristics that the data information of IoT is closely related to geographical location, the GeoHash algorithm is used to locally screen services based on geographical location, so as to narrow the range of candidate services. For smart devices with energy constraints, this paper proposes a combined optimization model. The model considers not only the transmission energy consumption and switching energy consumption, but also the execution energy consumption when the device provides services. In order to balance QoS attributes and energy consumption, the composition problem is regarded as a multi-objective optimization problem and solved using a genetic algorithm (GA). The simulation results show that service composition scheme selected by this service composition optimization model has lower energy consumption and higher service quality.

Skyline-Enhanced Deep Reinforcement Learning Approach for Energy-Efficient and QoS-Guaranteed Multi-Cloud Service Composition

“…Finally, a genetic algorithm is used to solve the service composition problem under a multi-cloud environment. Xiao et al [31] proposed a combinatorial optimization model that not only considers the transmission and switching energy consumption but also takes into account the execution energy consumption when the device provides services. To balance the QoS attributes and energy consumption, the composition problem is treated as a multi-objective optimization problem and solved using a genetic algorithm.…”