TY - GEN

T1 - A Deep Reinforcement Learning Approach to Configuration Sampling Problem

AU - Abolfazli, Amir

AU - Spiegelberg, Jakob

AU - Palmer, Gregory

AU - Anand, Avishek

N1 - Funding Information: The authors gratefully acknowledge that the proposed research is a result of the research project QuBRA granted by the BMBF via funding code 13N16052.

PY - 2023

Y1 - 2023

N2 - Configurable software systems have become increasingly popular as they enable customized software variants. The main challenge in dealing with configuration problems is that the number of possible configurations grows exponentially as the number of features increases. Therefore, algorithms for testing customized software have to deal with the challenge of tractably finding potentially faulty configurations given exponentially large configurations. To overcome this problem, prior works focused on sampling strategies to significantly reduce the number of generated configurations, guaranteeing a high t-wise coverage. In this work, we address the configuration sampling problem by proposing a deep reinforcement learning (DRL) based sampler that efficiently finds the trade-off between exploration and exploitation, allowing for the efficient identification of a minimal subset of configurations that covers all t-wise feature interactions while minimizing redundancy. We also present the CS-Gym, an environment for the configuration sampling. We benchmark our results against heuristic-based sampling methods on eight different feature models of software product lines and show that our method outperforms all sampling methods in terms of sample size. Our findings indicate that the achieved improvement has major implications for cost reduction, as the reduction in sample size results in fewer configurations that need to be tested.

AB - Configurable software systems have become increasingly popular as they enable customized software variants. The main challenge in dealing with configuration problems is that the number of possible configurations grows exponentially as the number of features increases. Therefore, algorithms for testing customized software have to deal with the challenge of tractably finding potentially faulty configurations given exponentially large configurations. To overcome this problem, prior works focused on sampling strategies to significantly reduce the number of generated configurations, guaranteeing a high t-wise coverage. In this work, we address the configuration sampling problem by proposing a deep reinforcement learning (DRL) based sampler that efficiently finds the trade-off between exploration and exploitation, allowing for the efficient identification of a minimal subset of configurations that covers all t-wise feature interactions while minimizing redundancy. We also present the CS-Gym, an environment for the configuration sampling. We benchmark our results against heuristic-based sampling methods on eight different feature models of software product lines and show that our method outperforms all sampling methods in terms of sample size. Our findings indicate that the achieved improvement has major implications for cost reduction, as the reduction in sample size results in fewer configurations that need to be tested.

KW - configuration sampling

KW - reinforcement learning

KW - software testing

UR - http://www.scopus.com/inward/record.url?scp=85185398160&partnerID=8YFLogxK

U2 - 10.1109/ICDM58522.2023.00009

DO - 10.1109/ICDM58522.2023.00009

M3 - Conference contribution

AN - SCOPUS:85185398160

SN - 979-8-3503-0789-4

SP - 1

EP - 10

BT - 2023 IEEE International Conference on Data Mining

A2 - Chen, Guihai

A2 - Khan, Latifur

A2 - Gao, Xiaofeng

A2 - Qiu, Meikang

A2 - Pedrycz, Witold

A2 - Wu, Xindong

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 23rd IEEE International Conference on Data Mining, ICDM 2023

Y2 - 1 December 2023 through 4 December 2023

ER -