Adaptive Behavioral Model Learning for Software Product Lines

TL;DR

This paper introduces an adaptive model learning approach for software product lines that reuses learned models to improve efficiency, significantly reducing learning costs for complex SPLs.

Contribution

It presents the $ ext{PL}^*$ method, an adaptive extension of the $L^*$ algorithm, leveraging model reuse across products in an SPL to enhance learning efficiency.

Findings

The $ ext{PL}^*$ method reduces learning costs compared to non-adaptive methods.

Order of product learning impacts the efficiency of the adaptive approach.

A heuristic for product learning order further improves cost reduction.

Abstract

Behavioral models enable the analysis of the functionality of software product lines (SPL), e.g., model checking and model-based testing. Model learning aims at constructing behavioral models for software systems in some form of a finite state machine. Due to the commonalities among the products of an SPL, it is possible to reuse the previously learned models during the model learning process. In this paper, an adaptive approach (the $\text{PL}^*$ method) for learning the product models of an SPL is presented based on the well-known $L^*$ algorithm. In this method, after model learning of each product, the sequences in the final observation table are stored in a repository which will be used to initialize the observation table of the remaining products to be learned. The proposed algorithm is evaluated on two open-source SPLs and the total learning cost is measured in terms of the number of rounds, the total number of resets and input symbols. The results show that for complex SPLs, the total learning cost for the $\text{PL}^*$ method is significantly lower than that of the non-adaptive learning method in terms of all three metrics. Furthermore, it is observed that the order in which the products are learned affects the efficiency of the $\text{PL}^*$ method. Based on this observation, we introduced a heuristic to determine an ordering which reduces the total cost of adaptive learning in both case studies.