An epistemic event‐based correlation approach for managing pervasive networks

Existing pervasive applications are based on time series data that possess the form of time‐ordered series of events. Such applications also embody the need to handle large volumes of unexpected events, often modified on‐the‐fly, containing conflicting information, and dealing with rapidly changing contexts while producing results with low latency. Correlating events across contextual dimensions holds the key to expanding the capabilities and improving the performance of these applications. In this paper we analyze complex‐event semantic correlation that examines epistemic uncertainty in computer networks by using Dempster–Shafer theory to support a high‐volume, event‐based, in‐network and non‐deterministic pervasive network management. We consider imprecision and uncertainty when an event is detected and associate a belief parameter with the semantics and the detection of composite events. The approach taps into in‐network processing capabilities of pervasive computer networks and can withstand missing or conflicting information gathered from multiple participating entities. In the end, we establish that a lightweight, distributed, large‐volume, event‐based technique which exploits epistemic uncertainty to correlate events along contextual dimensions provides a successful technique for enabling management of large‐scale and pervasive contemporary and future computer networks. Copyright © 2011 John Wiley & Sons, Ltd.