Microservice architecture can be modeled as a network of microservices making calls to each other, commonly known as the service dependency graph. Network Science can provide methods to study such networks. In particular, temporal network analysis is a branch of Network Science that analyzes networks evolving with time. In microservice systems, temporal networks can arise if we examine the architecture of the system across releases or monitor a deployed system using tracing.

In this research summary paper, I discuss the challenges in obtaining temporal networks from microservice systems and analyzing them with the temporal network methods. In particular, the most complete temporal network that we could obtain contains 7 time instances and 42 microservices, which limits the potential analysis that could be applied.

Alexander Bakhtin is a Doctoral Researcher at the University of Oulu, Finland. He works in the unit of Empirical Software Engineering in Software, Systems, and Services at the Information Technology and Electrical Engineering Faculty. Previously, he received his Bachelor’s Degree in Science and Technology (Mathematics) and Master’s Degree in Computing Sciences (Machine Learning) from Tampere University, Finland, in 2021 and 2022, respectively. During that time, he also worked in the units of Cloud Engineering, Audio Processing, and Financial Data analysis, where he gained experience in applying mathematical and machine learning methods to a diverse range of problems.

His current research interests include applying Static and Temporal Network Methods to networks encountered in the field of Software Engineering, such as networks of microservice architecture or developer collaboration. His work has been featured in IEEE SOSE, IEEE SCC, ACM SAC, ECSA, MSR, and ICSA conferences. He also served as Student Volunteer chair during the SANER 2024 conference in Rovaniemi, Finland.