Mingming Liu

Graph Neural Networks for Micro Service Based Cloud Application

Recently, there has been a significant shift towards the adoption of microservice architectures for cloud-based applications. The key idea of these architectures is to allow a group of small, independent, and scalable functional units working together to achieve common goals through efficient communication protocols and mechanisms facilitated in cloud networks. As applications increasingly adopt the microservice architectures, it becomes practically important to have intelligent resource provisioning algorithms in place. The primary objective of these intelligent algorithms is to dynamically allocate cloud resources such as CPU, memory to different microservices as their demands change over time, which can help improve efficiency and reduce operational costs.

The design of an intelligent resource provisioning algorithm often considers various factors including the workload pattern of each microservice, the available resources in the cloud environment, and the service level agreements (SLAs) that the applications must meet. Machine learning algorithms have become increasingly popular in recent years for designing these algorithms for microservice-based applications. By analyzing historical data available on cloud-based monitoring platforms, these algorithms are capable of forecasting future resource requirements and performance of applications to the next level

In this talk, I will present some recent advances in using machine learning techniques for the design of these algorithms, starting from basic rule-based methods to recent graph-based learning methods.

back to overview

Watch Recording
Speaker Image


Dr Mingming Liu is working as an assistant professor in the school of electronic engineering at Dublin City University (DCU) and is also affiliated with the SFI Insight Centre for Data Analytics as a Funded Investigator. He received his B. Eng. in Electronic Engineering at NUI Maynooth in 2011 and his PhD in Control Engineering and Decision Science from the Hamilton Institute at the same university in 2015. He has several years of experience in machine learning, system control and applied optimization with strong links to IoT in the context of smart grid, intelligent transportation, smart cities, and cloud computing. Prior to DCU, he was employed at IBM Ireland Lab working as a data scientist, applied researcher and project lead, where he had been involved in several EU H2020 projects, including Chariot, VI-DAS, ICONET, COPKIT and 5G-Solutions. He was the work package lead for VI-DAS and 5G-Solutions at IBM. Before IBM, he worked at University College Dublin as a (senior) postdoctoral researcher with a focus on both EU and Science Foundation Ireland (SFI) funded projects, including Green Transportation and Networks (SFI) and Enable-S3 (EU H2020). He is an IEEE Senior member and has published over 50 papers to date, including several top journals in his research fields, such as “IEEE Transactions on Smart Grids”, “IEEE Transactions on Intelligent Transportation Systems”, “IEEE Transactions on Automation Science and Engineering”, "IEEE Transactions on Transportation Electrification", "IEEE System Journal", "Scientific Reports" and “Automatica”. Since 2018, he has secured more than 1.2 million euros from various resources (Huawei, National and EU) for his research as the independent PI. In addition, he is the management committee member in Ireland for the EU COST Actions CA19126 and CA20138 and CA21131.