Banca de DEFESA: THIAGO PEREIRA DA SILVA
Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
DISCENTE : THIAGO PEREIRA DA SILVA
DATA : 15/09/2023
HORA: 14:00
LOCAL: Google Meet
TÍTULO:
An Ensemble Online Learning-based Approach for VNF Scaling in the Edge
PALAVRAS-CHAVES:
Auto-scaling, Edge Computing, Online Machine Learning, Ensemble Learning, Virtual Network Functions, Autonomic Computing.
PÁGINAS: 125
RESUMO:
Edge Computing (EC) platforms have recently been proposed to manage emergencyapplications with high computational load and low response time requirements. EC plat-forms take advantage of the distributed nature of edge devices close to end-users and datasources, thus minimizing constraints such as bandwidth consumption, network congestion,response time, and operational costs imposed by cloud providers. To provide more agilityand flexibility for service provisioning while reducing deployment costs for infrastructureproviders, technologies such as Network Functions Virtualization (NFV) are frequentlyused in production environments at the network edge, promoting the decoupling of hard-ware and network functions using virtualization technologies. Network or even higherlayers functions are implemented as Virtual Network Functions (VNFs) software entities.The integration of EC and NFV paradigms, as proposed by ETSI MEC, enables the cre-ation of an ecosystem for 5G applications. Such integration allows the creation of VNFchains, representing end-to-end services for end-users and their deployment on edge nodes.A Service Function Chaining (SFC) comprises a set of VNFs chained together in a givenorder, where each VNF can be running on a different edge node. The main challengesin this environment concern the dynamic provisioning and deprovisioning of distributedresources to run the VNFs and meet application requirements while optimizing the costto the infrastructure provider. In this sense, scaling VNFs in this environment representscreating new containers or virtual machines and reallocating resources to them due to thevariation in the workload and dynamic nature of the EC environment. This work presentsa hybrid auto-scaling approach for the dynamic scaling of VNFs in the EC environment.Such an auto-scaling approach employs an online ensemble machine-learning technique
that consists of different online machine-learning models that predict the workload. The
architecture of such an auto-scaling approach follows the abstraction of the MAPE-K
(Monitor-Analyze-Plan-Execute over a shared Knowledge) control loop to dynamically
adjust the number of resources in response to workload changes. This approach is innova-
tive because it proactively predicts the workload to anticipate scaling actions and behaves
reactively when the prediction model does not meet the desired quality. In addition, the
proposal requires no prior knowledge of the data’s behavior, making it suitable for use
in different contexts. We also have developed an algorithm to scale the VNF instances in
the edge computing environment that uses a strategy to define how many resources to
allocate or deallocate to a VNF instance during a scaling action. Finally, we evaluated
the ensemble method and the proposed algorithm, comparing prediction performance and
the amount of scaling actions and SLA violations.
MEMBROS DA BANCA:
Presidente - 1213777 - THAIS VASCONCELOS BATISTA
Interno - 1678918 - NELIO ALESSANDRO AZEVEDO CACHO
Externo ao Programa - 2510306 - FREDERICO ARAUJO DA SILVA LOPES - UFRNExterna à Instituição - FLAVIA COIMBRA DELICATO - UFF
Externo à Instituição - PAULO DE FIGUEIREDO PIRES - UFF