Generating Feasible Transition Paths for Testing from an Extended Finite State Machine (EFSM) with the Counter Problem

Abstract

The extended finite state machine (EFSM) is a powerful approach for modeling state-based systems. However, testing from EFSMs is complicated by the existence of infeasible paths. One important problem is the existence of a transition with a guard that references a counter variable whose value depends on previous transitions. The presence of such transitions in paths often leads to infeasible paths. This paper proposes a novel approach to bypass the counter problem. The proposed approach is evaluated by being used in a genetic algorithm to guide the search for feasible transition paths (FTPs). I.

An integrated search-based approach for automatic testing from extended finite state machine (EFSM) models

“…It appears to be difficult to identify such cases using static data flow dependencies formulated as penalty values. The counter problem requires additional analysis and an initial approach to overcome the counter problem was introduced in [40]. Table 5 summarises the results achieved with the random approach.…”

Modeling and Testing of Network Protocols with Parallel State Machines

“…These studies can be broadly separated into two categories: reachability analysis [1], [2] and heuristic methods [3]- [8]. Lee et al [1], [2] presented an approach to convert a class of EFSMs into equivalent FSMs based on the assumption that input variables have finite domains.…”

“…El-Fakih et al studied EFSM test generation with user defined faults [5]. Kalaji et al [6]- [8] applied Genetic Algorithm on feasible paths generation. Although these heuristic methods cannot ensure executability of test sequences generated, the state explosion can be avoid.…”

“…Among so many formal methods, the models with single component, such as FSM (Finite State Machine) and EFSM (Extended FSM), are widely accepted for testing [1]- [8]. But they can only be used to model the protocol with single component.…”

Monadic Sequence Testing and Explicit Test-Refinements

“…In settings for the latter, underlying set-theories need either to be typed or axiomatised in a system like ZFC [11]. Applications based on automated reasoning over these formalisations turn out to be so difficult that successful tool implementations exist only for particular special-cases such as symbolic regular expression representations [17,27]. In our view, it is not a coincidence that implementations of symbolic versions of test-systems like TGV (e. g., STG [16]) or SIOCO [12] remained in a prototypical stage.…”