Dataflow networks for event stream processing

We present a design of a new class of dataflow-like networks suitable for detecting complex conditions in systems in which parameters change rapidly. Such networks are helpful for detecting conditions that signal threats or opportunities in areas such as logistics, finance, and public health. Examples of such applications are detection of money laundering, epidemics, and unauthorized intrusion into systems. We call these networks ∆-dataflow networks because nodes in the network propagate only changes in data values. Streams of events are fed to entry points in the network asynchronously and events that signal complex conditions are output at exit points. The networks are asynchronous and nondeterministic because events appear at inputs at arbitrary times. The design of ∆-dataflow networks is presented in a notation suitable for implementation in asynchronous VLSI.