GTMicro—microservice identification approach based on deep NLP transformer model for greenfield developments

• Published in: International journal of information technology (Singapore. Online) 2024, Vol.16 (5), p.2751-2761
• Main Authors: Bajaj, Deepali, Bharti, Urmil, Gupta, Isha, Gupta, Priya, Yadav, Asha
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Computer Imaging; Computer Science; Image Processing and Computer Vision; Machine Learning; Original Research; Pattern Recognition and Graphics; Software Engineering; Vision
• ISSN: 2511-2104; 2511-2112
• DOI: 10.1007/s41870-024-01766-5

Microservice architecture (MSA) has become a new style to modernize monolithic systems. MSA comprises small, independent, and autonomous services that communicate using lightweight network protocols. Recently few studies have proposed microservice identification techniques to embrace the designing of microservices. However, majority of the existing approaches are applicable to brownfield applications where monolithic application already exists. In this paper, we introduce a novel Greenfield Transformer-based Microservice identification approach—GTMicro to identify the bounded context as microservices for greenfield applications. GTMicro makes use of Bidirectional Encoder Representations from Transformers (BERT) which is a deep Learning model. BERT is used to compute the semantic textual similarity between use cases of the application and group them semantically. We validated GTMicro on two sample benchmark monolithic Java applications and migrated them toward microservices-based architecture. We mapped GTMicro to the state-of-the-art software quality assessment metrics and have presented the gains achieved through our results.