Fog computing is a promising computing paradigm in which IoT data can be processed near the edge to support time-sensitive applications. However, the availability of the resources in the computation device is not stable since they may not be exclusively dedicated to the processing in the Fog environment. This, combined with dynamic user behaviour, can affect the execution of applications. To address dynamic changes in user behaviour in a resource limited Fog device, this paper proposes a Multi-Criteria-based resource allocation policy with resource reservation in order to minimise overall delay, processing time and SLA violation which considers Fog computing-related characteristics, such as device heterogeneity, resource constraint and mobility, as well as dynamic changes in user requirements. We employ multiple objective functions to find appropriate resources for execution of time-sensitive tasks in the Fog environment. Experimental results show that our proposed policy performs better than the existing one, reducing the total delay by 51%. The proposed algorithm also reduces processing time and SLA violation which is beneficial to run time-sensitive applications in the Fog environment.
View on arXiv