On Effects of Applying Predictive Caching for State Machines

State machines are frequently used in software development, in many different contexts, ranging from modeling control software to distributed applications that operate in cloud environments. We have implemented and experimented on basic execution path-based predictive caching approaches for state machines to show that due to the limited number of paths that can be taken during a state machine run better pre-fetching can be achieved for state machine caches. We have applied our predictive approaches over least frequently used (LFU) and least recently used (LRU) replacement on two different state machine instances run with real-world execution traces.