Dynamic Sizing of Cloud-Native Telco Data Centers With Digital Twin and Reinforcement Learning
Open Access
- 1 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 91462-91479
Abstract
Telco edge data centers (DCs) accommodate applications whose load fluctuates considerably during a day. This variability mandates swift and responsive resource adjustments to mitigate the risk of incurring unnecessary costs during off-peak periods, where a significant fraction of nodes may be under-utilized. Tackling this challenge is integral to optimizing operational efficiency and cost-effectiveness of telco edge DCs. To this end, this article aims to address the Dynamic Data Center Sizing (DDS) problem, which boils down to optimizing the number of active nodes as per current resource demand. The proposed DDS solution consists of two core modules, namely a forecasting module, which predicts resource demands, and a decision-making module, which acts upon predicted demands. The decision-making of DDS is implemented via the filtering and the rank-drain-observe (RDO) algorithms. Filtering is based on integer linear programming, and it computes the theoretically optimal state of the DC based on predicted resource demands. RDO is a heuristic that strives to realize the optimal DC state in an iterative and robust fashion. To expedite RDO in large-scale clusters, we further devise a Reinforcement Learning (RL)-enabled DDS variant (i.e., RL-DDS), in which RDO integrates an RL agent that computes optimized batches of nodes for concurrent deactivation. We propose an innovative solution based on the notion of Digital Twin to train the RL agent in emulation mode. DDS and RL-DDS are evaluated upon real-life testbeds resembling actual DCs. Results demonstrate significant cost reduction, ranging from 7% in conservative and relatively static scenarios, up to 38% in highly dynamic settings.Keywords
Funding Information
- European Union-NextGenerationEU Program under the National Recovery and Resilience Plan “Greece 2.0” Framework through the ARCADIA Project (T2EDK-02097)
This publication has 17 references indexed in Scilit:
- Accurate workload prediction for edge data centers: Savitzky-Golay filter, CNN and BiLSTM with attention mechanismApplied Intelligence, 2022
- Benchmarking Kubernetes Container-Networking for Telco Usecases2021
- Multi-Cloud Connectivity for Kubernetes in 5G NetworksIEEE Communications Magazine, 2021
- AI-Driven Zero Touch Network and Service Management in 5G and Beyond: Challenges and Research DirectionsIEEE Network, 2020
- Improving Resource Utilization in Data Centers using an LSTM-based Prediction Model2019
- Adaptive Prediction Models for Data Center Resources Utilization EstimationIEEE Transactions on Network and Service Management, 2019
- A Survey on Mobile Edge Computing: The Communication PerspectiveIEEE Communications Surveys & Tutorials, 2017
- Energy-Efficient Resource Allocation and Provisioning Framework for Cloud Data CentersIEEE Transactions on Network and Service Management, 2015
- Dynamic Right-Sizing for Power-Proportional Data CentersIEEE/ACM Transactions on Networking, 2012
- Energy-aware resource allocation heuristics for efficient management of data centers for Cloud computingFuture Generation Computer Systems, 2012