Davide Yi Xian Hu

Davide Yi Xian Hu

Ph.D. Student, Politecnico di Milano. Swag Master.

Publications

 Google Scholar    ResearchGate   ORCID   dblp   Scopus   Semantic Scholar

NEPTUNE: Network-and GPU-Aware Management of Serverless Functions at the Edge

Published in 17th Symposium on Software Engineering for Adaptive and Self-Managing Systems, SEAMS 2022, 2022

Abstract: Nowadays a wide range of applications is constrained by low-latency requirements that cloud infrastructures cannot meet. Multi-Access Edge Computing (MEC) has been proposed as the reference architecture for executing applications closer to users and reducing latency, but new challenges arise: edge nodes are resource-constrained, the workload can vary significantly since users are nomadic, and task complexity is increasing (e.g., machine learning inference). To overcome these problems, the paper presents NEPTUNE, a serverless-based framework for managing complex MEC solutions. NEPTUNE i) places functions on edge nodes according to user locations, ii) avoids the saturation of single nodes, iii) exploits GPUs when available, and iv) allocates resources (CPU cores) dynamically to meet foreseen execution times. A prototype, built on top of K3S, was used to evaluate NEPTUNE on a set of experiments that demonstrate a significant reduction in terms of response time, network overhead, and resource consumption compared to three well-known approaches. © 2022 ACM. keywords: Complex networks; Control theory; Graphics processing unit; Program processors; Cloud infrastructures; Dynamic resource allocations; Edge computing; Edge nodes; Gpu; Low latency; Multiaccess; Placement; Reference architecture; Serverless; Edge computing pages: 144-155

Recommended citation: Baresi L., Hu D.Y.X., Quattrocchi G., Terracciano L. (2022). "NEPTUNE: Network-and GPU-Aware Management of Serverless Functions at the Edge." 17th Symposium on Software Engineering for Adaptive and Self-Managing Systems, SEAMS 2022. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85134186377&doi=10.1145%2f3524844.3528051&partnerID=40&md5=a4a2540c15be832fff1dcf445335b871

KOSMOS: Vertical and Horizontal Resource Autoscaling for Kubernetes

Published in 19th International Conference on Service-Oriented Computing, ICSOC 2021, 2021

Abstract: Cloud applications are increasingly executed onto lightweight containers that can be efficiently managed to cope with highly varying and unpredictable workloads. Kubernetes, the most popular container orchestrator, provides means to automatically scale containerized applications to keep their response time under control. Kubernetes provisions resources using two main components: i) Horizontal Pod Autoscaler (HPA), which controls the amount of containers running for an application, and ii) Vertical Pod Autoscaler (VPA), which oversees the resource allocation of existing containers. These two components have several limitations: they must control different metrics, they use simple threshold-based rules, and the reconfiguration of existing containers requires stopping and restarting them. To overcome these limitations this paper presents KOSMOS, a novel autoscaling solution for Kubernetes. Containers are individually controlled by control-theoretical planners that manage container resources on-the-fly (vertical scaling). A dedicated component is in charge of handling resource contention scenarios among containers deployed in the same node (a physical or virtual machine). Finally, at the cluster-level a heuristic-based controller is in charge of the horizontal scaling of each application. © 2021, Springer Nature Switzerland AG. keywords: Autoscaling; Cloud applications; Horizontal scaling; Kubernetes; Resource contention; Resource provisioning; Simple++; Two-component; Vertical scaling; Containers pages: 821-829

Recommended citation: Baresi L., Hu D.Y.X., Quattrocchi G., Terracciano L. (2021). "KOSMOS: Vertical and Horizontal Resource Autoscaling for Kubernetes." 19th International Conference on Service-Oriented Computing, ICSOC 2021. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85120525473&doi=10.1007%2f978-3-030-91431-8_59&partnerID=40&md5=c7ae46c26ef35f9c8d7b0a5a43e67cf8

Multi-Objective Blended Ensemble for Highly Imbalanced Sequence Aware Tweet Engagement Prediction

Published in 2020 ACM Recommender Systems Challenge Workshop, RecSysChallenge 2020, held at 14th ACM Conference on Recommender Systems, ACM RecSys 2020, 2020

Abstract: In this paper we provide a description of the methods we used as team BanaNeverAlone for the ACM RecSys Challenge 2020, organized by Twitter. The challenge addresses the problem of user engagement prediction: the goal is to predict the probability of a user engagement (Like, Reply, Retweet or Retweet with comment), based on a series of past interactions on the Twitter platform. Our proposed solution relies on several features that we extracted from the original dataset, as well as on consolidated models, such as gradient boosting for decision trees and neural networks. The ensemble model, built using blending, and a multi-objective optimization allowed our team to rank in position 4. © 2020 ACM. keywords: Blending; Decision trees; Multiobjective optimization; Recommender systems; Social networking (online); Ensemble modeling; Gradient boosting; Multi objective; User engagement; Forecasting pages: 29-33

Recommended citation: Felicioni N., Donati A., Conterio L., Bartoccioni L., Hu D.Y.X., Bernardis C., Ferrari Dacrema M. (2020). "Multi-Objective Blended Ensemble for Highly Imbalanced Sequence Aware Tweet Engagement Prediction." 2020 ACM Recommender Systems Challenge Workshop, RecSysChallenge 2020, held at 14th ACM Conference on Recommender Systems, ACM RecSys 2020. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85092744154&doi=10.1145%2f3415959.3415998&partnerID=40&md5=3269bb23c4590d2992deb922beb21eed