CTL-Based Adaptive Service Composition in Edge Networks

Abstract

With the recent adoption of edge computing, <i>I</i> nternet of <i>T</i> hings ( <i>IoT</i> ) devices collaborate at the network edge to facilitate edge-native applications. In this setting, <i>IoT</i> devices are typically encapsulated as <i>IoT</i> services to encode their functionalities, and their collaboration is achieved through <i>IoT</i> service composition. Due to the continuous resource occupancy, release, and consumption of <i>IoT</i> devices at runtime, a composition, which is functionally compatible and non-functionally optimal at this moment, may not hold in the forthcoming time durations, when certain <i>IoT</i> services may significantly downgrade in their <i>Q</i> uality-of- <i>S</i> ervices ( <i>QoS</i> ). To guarantee the compatibility of compositions with <i>QoS</i> variations, this article proposes an adaptive composition mechanism leveraging <i>C</i> omputation <i>T</i> ree <i>L</i> ogic ( <i>CTL</i> ) specifications. Specifically, we formalize the composition as a temporal task, and convert it to <i>CTL</i> formulae with the abstractions of required functionalities and composite structures. Functional compatibility is formally interpreted by <i>CTL</i> semantics during the execution of compositions. Besides, we construct a <i>QoS</i> <i>D</i> ependency <i>G</i> raph ( <i>QoSDG</i> ) to capture <i>QoS</i> variations, and achieve adaptive composition with dynamic <i>QoS</i> satisfactions. Extensive experiments are conducted upon publicly-available datasets, and comparison results demonstrate that our technique outperforms the state-of-the-art counterparts in heterogenous scenarios with higher <i>QoS</i> dependencies ranging from 0.3 <inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> to 27.8 <inline-formula><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> .