Study on Optimal Allocation of Inference Nodes for Distributed Inference in Smart Environment

Under traditional rule-based reasoning in a smart environment, the inference engine deployed in gateway collects context data from various sensors to match the rules, which undertakes whole reasoning work. The current research uses the Rete algorithm to construct an inference network by rules and then allocate the Rete inference nodes to Smart Nodes for collaborative reasoning based on fog computing, afterwards, the allocation mechanism becomes crucial. This paper utilizes the regularity of rules triggered under the influence of activities to design an algorithm CoA(Clustering of Activity), which clusters activities and respectively constructs the inference networks. Subsequently, calculate the shortest path between Smart Nodes and substitute the results into AAoRN(Allocation Algorithm of Rete inference nodes), which is proposed to overcome hierarchical delay for optimally allocating each inference node. Theoretical analysis and experimental results show that the proposed mechanism efficiently utilizes the resources and has achieved outstanding real-time performance.