A Multi-Strategy Multi-Objective Hierarchical Approach for Energy Management in 5G Networks

Peesapati, S. Krishna Gowtam; Olsson, Magnus; Andersson, Sören

doi:10.1109/globecom48099.2022.10001149

Cited by 4 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we implemented and evaluated the energy performance of the TowerCo's RANaaS RAN-sharing scenario seen in Figure 8. We used the AI system proposed in [22] to assist each MNO in adapting their logical RAN resources. Following this, we looked at the energy savings' probability under three scenarios and studied the impact of the operator's requirements over 24 h. This analysis considered the energy-saving features activated under different scenarios and the extent to which the operator's decisions overlapped.…”

Section: Implementation Results and Analysismentioning

confidence: 99%

“…In [20], we extended the analytical methodology developed in [21] to propose a dynamic Q-learning-based resource adaptation algorithm to obtain higher energy savings under varying traffic loads. As an extension to [20], in [22], we mainly addressed the challenges associated with complex long-horizon problems by developing a hierarchical reinforcement learning solution wherein different optimization strategies were implemented as a hierarchy of reinforcement learning agents. It was not only to improve the network energy efficiency but also to learn the best way to optimize the network in any given scenario.…”

Section: Related Workmentioning

confidence: 99%

“…The performance evaluation of the optimization strategies implemented as hierarchical agents was carried out in [22]. In that evaluation, we measured the energy savings obtained by comparing it against the baseline scenario with all resources activated at each site, i.e., from an operator perspective, the maximum bandwidth of 10/20/100 MHz and the maximum antenna configuration, 4/4/64 on the three bands 700/2100/3500 MHz, respectively.…”

Section: Baselinementioning

confidence: 99%

See 2 more Smart Citations

AI-Assisted Multi-Operator RAN Sharing for Energy-Efficient Networks

Peesapati

Olsson

Andersson

et al. 2023

Telecom

View full text Add to dashboard Cite

Recent times have seen a significant rise in interest from mobile operators, vendors, and research projects toward achieving more energy-efficient and sustainable networks. Not surprisingly, it comes at a time when higher traffic demand and more stringent and diverse network requirements result in diminishing benefits for operators using complex AI-driven network optimization solutions. In this paper, we propose the idea of tower companies that facilitate radio access network (RAN) infrastructure sharing between operators and evaluate the additional energy savings obtained in this process. In particular, we focus on the RAN-as-a-Service (RANaaS) implementation, wherein each operator leases and controls an independent logical RAN instance running on the shared infrastructure. We show how an AI system can assist operators in optimizing their share of resources under multiple constraints. This paper aims to provide a vision, a quantitative and qualitative analysis of the RANaaS paradigm, and its benefits in terms of energy efficiency. Through simulations, we show the possibility to achieve up to 75 percent energy savings per operator over 24 h compared to the scenario where none of the energy-saving features are activated. This is an additional 55 percent energy savings from sharing the RAN infrastructure compared to the baseline scenario where the operators use independent hardware.

show abstract

Section: Implementation Results and Analysismentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Baselinementioning

confidence: 99%

See 1 more Smart Citation

AI-Assisted Multi-Operator RAN Sharing for Energy-Efficient Networks

Peesapati

Olsson

Andersson

et al. 2023

Telecom

View full text Add to dashboard Cite

show abstract

“…Hence, the current 3GPP NR architecture introduces the Network Data Analytics Function (NWDAF) and the Management Data Analytics Function (MDAF) [23]. Within reinforcement learning, the Q-model is used in [126], [112], [127] and [128]. In [128], the authors utilise the Q-model to adapt a base station's resources according to the traffic demand, by optimising the use of sleep modes.…”

Section: A Technology Improvementsmentioning

confidence: 99%

“…Results in [128] reports on up to 16% energy consumption savings. Authors in [127] use a framework for effective strategy selection and optimisation policies and obtains up to 20% energy savings in a high load scenario. The work in [126] utilises the Q-model to optimise the trade-off between QoS and energy efficiency.…”

Section: A Technology Improvementsmentioning

confidence: 99%

Toward Greener 5G and Beyond Radio Access Networks—A Survey

Larsen

Christiansen

Ruepp

et al. 2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Mobile network traffic is increasing and so is the energy consumption. The Radio Access Network (RAN) part is responsible for the largest share of the mobile network energy consumption, and thus; an important consideration when expanding mobile networks to meet traffic demands. This work analyses how the energy consumption of future mobile networks can be minimised by using the right RAN architecture, share the network with other operators and implementing the most efficient energy minimising technologies in the RAN. It is explored how the different approaches can be realised in real life networks as well as the research state of the art is highlighted. Furthermore, this work provides an overview of future research directions for 6G energy saving potentials. Different energy saving contributions are evaluated by a common methodology for more realistic comparison, based on the potential energy saving of the overall mobile network consumption. Results show that implementing selected technologies and architectures, the mobile network overall energy consumption can be reduced by approximately 30%, corresponding to almost half of the RAN energy consumption. Following this, a set of guidelines towards an energy optimised mobile network is provided, proposing changes to be made initially and in the longer run for brownfield network operators as well as a target network for greenfield network operators.

show abstract