Monolith to Microservices: Representing Application Software through Heterogeneous Graph Neural Network

Abstract

Traffic flow forecasting plays a vital role in the transportation domain. Existing studies usually manually construct correlation graphs and design sophisticated models for learning spatial and temporal features to predict future traffic states. However, manually constructed correlation graphs cannot accurately extract the complex patterns hidden in the traffic data. In addition, it is challenging for the prediction model to fit traffic data due to its irregularly-shaped distribution. To solve the above-mentioned problems, in this paper, we propose a novel learning-based method to learn a spatial-temporal correlation graph, which could make good use of the traffic flow data. Moreover, we propose First-Order Gradient Supervision (FOGS), a novel method for traffic flow forecasting. FOGS utilizes first-order gradients, rather than specific flows, to train prediction model, which effectively avoids the problem of fitting irregularly-shaped distributions. Comprehensive numerical evaluations on four real-world datasets reveal that the proposed methods achieve state-of-the-art performance and significantly outperform the benchmarks.

Migration of Monolithic Systems to Microservices using AI: A Systematic Mapping Study

“…Studies Percentage Static [Brito et al 2021, Kamimura et al 2018, Mathai et al 2022, Nitin et al 2022, Nunes et al 2019, Pigazzini et al 2019, Sellami et al 2022, Trabelsi et al 2022 36.4% Dynamic [Bajaj et al 2020, Jin et al 2021, Kalia et al 2021 [Eski andBuzluca 2018, Mazlami et al 2017] 9.1% Documentation (A&D) + Dynamic + Static [Li et al 2022] 4.5% Documentation based (A&D) [Gysel et al 2016] 4.5% By language support Although the majority of the reviewed techniques are designed to support a monolith developed in any programming language (65.2%), a subset of them (53.3%) currently support Java monoliths due to the fact those techniques rely on tools that are only available for the Java language, for instance Wala [Ren et al 2018] and Java Call Graph [Cao and Zhang 2022]. 21.7% of the studies migrate Java monoliths to microservices, thus becoming Java the most popular monolith language to develop migration techniques.…”

“…Percentage [Brito et al 2021, Kalia et al 2021, Liu et al 2022, Jin et al 2021, Eski and Buzluca 2018, Mazlami et al 2017, Matias et al 2020, Kamimura et al 2018, Nunes et al 2019, Pigazzini et al 2019, Sellami et al 2022, Trabelsi et al 2022, Nitin et al 2022, De Alwis et al 2018, Mathai et al 2022 Class Implementation 68.1% [Li et al 2022, Ren et al 2018…”

A Survey on Graph Neural Networks for Microservice-Based Cloud Applications

“…GNNs have many applications across multiple areas of research involving classification, regression, and clustering problems; for example, node classification, node embedding [ 18 ], graph classification, graph generation [ 50 , 51 , 52 ], node prediction, graph prediction tasks [ 53 ], and node clustering tasks [ 54 ]. In this paper, we mainly focus on the study of GNNs for microservice-based applications, including anomaly detection [ 30 , 31 , 32 , 33 , 34 , 55 ], resource scheduling [ 17 , 35 , 36 ], and refactoring monolith applications [ 37 , 38 , 56 ]. More specifically, we detail node and edge representations of the GNN approaches in Table 4 .…”

“…To further extend the Desai et al [ 37 ] approach, Mathai et al [ 38 ] further included application resources for recommending a microservice architecture. The refactoring monolith application problem was treated as a heterogeneous graph model with function nodes and resource nodes.…”

“…These attributes along with the naturally interconnected graph of the services in the microservice architecture make GNN an ideal method to handle the irregularity and dynamic resource needs of microservices. Currently, there are ongoing research efforts in applying GNNs to microservice-based applications on anomaly analysis [ 30 , 31 , 32 , 33 , 34 ], resource scheduling [ 17 , 35 , 36 ], and refactoring monolith applications [ 37 , 38 ].…”