Traffic-profile and machine learning based regional data center design and operation for 5G network

Paul, Udita; Liu, Jiamo; Troia, Sebastian; Falowo, Olabisi E.; Maier, Guido

doi:10.1109/jcn.2019.000055

Cited by 26 publications

(14 citation statements)

References 42 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, it is difficult to obtain such kind of public data sets. In this work, we aim to develop a data-driven BS sleeping strategy based on public data with limited general cellular networks [39], e.g., overall traffic and BSs's number, therefore, we define a cellular energy saving problem to seek the optimal BSs' number in an area.…”

Section: The Optimal Bs Sleeping Strategymentioning

confidence: 99%

A Data-driven Base Station Sleeping Strategy Based on Traffic Prediction

Lin¹,

Chen²,

Zheng³

et al. 2024

IEEE Trans. Netw. Sci. Eng.

View full text Add to dashboard Cite

Due to the rapidly increasing number of deployed base stations (BSs) in current cellular networks, energy consumption has emerged as a great challenge in network operation. In this paper, we propose a novel data-driven intelligent BS sleeping mechanism based on a wireless traffic prediction model that measures the BSs' capacity in different regions. Firstly, a spatial-temporal traffic prediction model is proposed, where a multi-graph convolutional network (MGCN) is developed to capture spatial features, and a multi-channel long short-term memory (LSTM) involving short-term, daily, and weekly periodic data is used to capture temporal features. Secondly, the capacities of macro-cell BSs (MBSs) and small-cell BSs (SBSs) with different environment characteristics are modeled, where both clustering and transfer learning algorithms are adopted to quantify the traffic supported by MBSs and SBSs. Finally, an optimal BS sleeping strategy is proposed to minimize the network power consumption. Experimental results show that the proposed MGCN-LSTM model outperforms the existing models in terms of traffic prediction, and the proposed BS sleeping strategy using an approximated non-linear model of capacity function achieves a near-optimal energy-saving performance with relatively low complexity.

show abstract

Section: The Optimal Bs Sleeping Strategymentioning

confidence: 99%

A Data-driven Base Station Sleeping Strategy Based on Traffic Prediction

Lin¹,

Chen²,

Zheng³

et al. 2024

IEEE Trans. Netw. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…The application of ML/AI algorithms to cellular networks is gaining momentum as a promising and effective way to design and deploy solutions capable of predicting, controlling, and automating the network behavior under dynamic conditions. Relevant examples include the application of Deep Learning and Deep Reinforcement Learning (DRL) to predict the network load [9,14,23], classify traffic [15,24,25], perform beam alignment [16,17], allocate radio resources [3,4,26], and deploy service-tailored network slices [5][6][7][8][9][10]27]. It is clear that ML/AI techniques will play a key role in the transition to intelligent networks, especially in the O-RAN ecosystem [28].…”

Section: Related Workmentioning

confidence: 99%

“…The O-RAN architecture makes it possible to bring automation and intelligence to the network through Machine Learning (ML) and Artificial Intelligence (AI), which will leverage the enormous amount of data generated by the RAN-and exposed through the O-RAN interfaces-to analyze the current network conditions, forecast future traffic profiles and demand, and implement closed-loop network control strategies to optimize the RAN performance. For this reason, how to design, train and deploy reliable and effective data-driven solutions has recently received increasing interest from academia and industry alike, with applications ranging from controlling RAN resource and transmission policies [3][4][5][6][7][8][9][10][11][12][13], to forecasting and classifying traffic and Key Performance Indicators (KPIs) [14][15][16][17][18], thus highlighting how these approaches will be foundational to the Open RAN paradigm. However, how to deploy and manage, i.e., orchestrate, intelligence into softwarized cellular networks is by no means a solved problem for the following reasons:…”

Section: Introductionmentioning

confidence: 99%

OrchestRAN: Network Automation through Orchestrated Intelligence in the Open RAN

Bonati¹,

Polese²,

Melodia³

2022

Preprint

View full text Add to dashboard Cite

The next generation of cellular networks will be characterized by softwarized, open, and disaggregated architectures exposing analytics and control knobs to enable network intelligence via innovative data-driven algorithms. How to practically realize this vision, however, is largely an open problem. For a given network optimization/automation objective, it is currently unknown how to select which data-driven models should be deployed and where, which parameters to control, and how to feed them appropriate inputs. In this paper, we take a decisive step forward by presenting and prototyping OrchestRAN, a novel orchestration framework for next generation systems that embraces and builds upon the Open Radio Access Network (RAN) paradigm to provide a practical solution to these challenges. OrchestRAN has been designed to execute in the non-Real-time (RT) RAN Intelligent Controller (RIC) and allows Network Operators (NOs) to specify high-level control/inference objectives (i.e., adapt scheduling, and forecast capacity in near-RT, e.g., for a set of base stations in Downtown New York). OrchestRAN automatically computes the optimal set of data-driven algorithms and their execution location (e.g., in the cloud, or at the edge) to achieve intents specified by the NOs while meeting the desired timing requirements and avoiding conflicts between different data-driven algorithms controlling the same parameters set. We show that the intelligence orchestration problem in Open RAN is NP-hard, and design low-complexity solutions to support real-world applications. We prototype Orches-tRAN and test it at scale on Colosseum, the world's largest wireless network emulator with hardware in the loop. Our experimental results on a network with 7 base stations and 42 users demonstrate that OrchestRAN is able to instantiate data-driven services on demand with minimal control overhead and latency.

show abstract

“…In [ 71 ], the authors combine some of the technologies mentioned with SDN and identify different traffic profiles.…”

Section: Use Of Sdn In Iiotmentioning

confidence: 99%

Software-Defined Networking Solutions, Architecture and Controllers for the Industrial Internet of Things: A Review

Urrea

Benítez

2021

Sensors

View full text Add to dashboard Cite

The use of Software-Defined Networking (SDN) in the communications of the Industrial Internet of Things (IIoT) demands more comprehensive solutions than those developed to date. The lack of an SDN solution applicable in diverse IIoT scenarios is the problem addressed in this article. The main cause of this problem is the lack of integration of a set of aspects that should be considered in a comprehensive SDN solution. To contribute to the solution of this problem, a review of the literature is conducted in this article, identifying the main requirements for industrial networks nowadays as well as their solutions through SDN. This review indicates that aspects such as security, independence of the network technology used, and network centralized management can be tackled using SDN. All the advantages of this technology can be obtained through the implementation of the same solution, considering a set of aspects proposed by the authors for the implementation of SDNs in IIoT networks. Additionally, after analyzing the main features and advantages of several architectures proposed in the literature, an architecture with distributed network control is proposed for all SDN network scenarios in IIoT. This architecture can be adapted through the inclusion of other necessary elements in specific scenarios. The distributed network control feature is relevant here, as it prevents a single fault-point for an entire industrial network, in exchange for adding some complexity to the network. Finally, the first ideas for the selection of an SDN controller suitable for IIoT scenarios are included, as this is the core element in the proposed architecture. The initial proposal includes the identification of six controllers, which correspond to different types of control planes, and ten characteristics are defined for selecting the most suitable controller through the Analytic Hierarchy Process (AHP) method. The analysis and proposal of different fundamental aspects for the implementation of SDNs in IIoT in this article contribute to the development of a comprehensive solution that is not focused on the characteristics of a specific scenario and would, therefore, be applicable in limited situations.

show abstract

Traffic-profile and machine learning based regional data center design and operation for 5G network

Cited by 26 publications

References 42 publications

A Data-driven Base Station Sleeping Strategy Based on Traffic Prediction

A Data-driven Base Station Sleeping Strategy Based on Traffic Prediction

OrchestRAN: Network Automation through Orchestrated Intelligence in the Open RAN

Software-Defined Networking Solutions, Architecture and Controllers for the Industrial Internet of Things: A Review

Contact Info

Product

Resources

About