Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI-Ready Energy Modelling for Next Generation RAN

Kishan Sthankiya, Keith Briggs, Mona Jaber, Richard G. Clegg

TL;DR

Extensions to the system-level discrete-event AIMM (AI-enabled Massive MIMO) Simulator are presented, generating realistic figures for throughput and energy efficiency (EE) towards digital twin network modelling, and investigating the trade-off between maximising either EE or spectrum efficiency (SE).

Abstract

Recent sustainability drives place energy-consumption metrics in centre-stage for the design of future radio access networks (RAN). At the same time, optimising the trade-off between performance and system energy usage by machine-learning (ML) is an approach that requires large amounts of granular RAN data to train models, and to adapt in near realtime. In this paper, we present extensions to the system-level discrete-event AIMM (AI-enabled Massive MIMO) Simulator, generating realistic figures for throughput and energy efficiency (EE) towards digital twin network modelling. We further investigate the trade-off between maximising either EE or spectrum efficiency (SE). To this end, we have run extensive simulations of a typical macrocell network deployment under various transmit power-reduction scenarios with a range of difference of 43 dBm. Our results demonstrate that the EE and SE objectives often require different power settings in different scenarios. Importantly, low mean user CPU execution times of 2.17 $\pm$ 0.05 seconds (2~s.d.) demonstrate that the AIMM Simulator is a powerful tool for quick prototyping of scalable system models which can interface with ML frameworks, and thus support future research in energy-efficient next generation networks.

AI-Ready Energy Modelling for Next Generation RAN

TL;DR

Extensions to the system-level discrete-event AIMM (AI-enabled Massive MIMO) Simulator are presented, generating realistic figures for throughput and energy efficiency (EE) towards digital twin network modelling, and investigating the trade-off between maximising either EE or spectrum efficiency (SE).

Abstract

Recent sustainability drives place energy-consumption metrics in centre-stage for the design of future radio access networks (RAN). At the same time, optimising the trade-off between performance and system energy usage by machine-learning (ML) is an approach that requires large amounts of granular RAN data to train models, and to adapt in near realtime. In this paper, we present extensions to the system-level discrete-event AIMM (AI-enabled Massive MIMO) Simulator, generating realistic figures for throughput and energy efficiency (EE) towards digital twin network modelling. We further investigate the trade-off between maximising either EE or spectrum efficiency (SE). To this end, we have run extensive simulations of a typical macrocell network deployment under various transmit power-reduction scenarios with a range of difference of 43 dBm. Our results demonstrate that the EE and SE objectives often require different power settings in different scenarios. Importantly, low mean user CPU execution times of 2.17 0.05 seconds (2~s.d.) demonstrate that the AIMM Simulator is a powerful tool for quick prototyping of scalable system models which can interface with ML frameworks, and thus support future research in energy-efficient next generation networks.

Paper Structure

This paper contains 12 sections, 1 equation, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Methods
  4. AIMM Simulator
  5. Extension Implementing Power Consumption Model for Base Stations
  6. System Model
  7. Experiment Setup
  8. Results and Discussion
  9. Impact on throughput and power consumption
  10. Energy and Spectrum Efficiency
  11. Lessons learnt for future network design
  12. Conclusions

Figures (3)

  • Figure 1: AIMM Simulator Block Diagram AIMM_Simulator
  • Figure 2: Topology of our system with nineteen BSs in a regular grid and UEs deployed over this grid.
  • Figure 3: Comparison of Mean Network Throughput (a), Mean Network Power Consumption (b), Mean Network Energy Efficiency (c) and Mean Network Spectral Efficiency (d). Each subplot $x$-axis represents the $P^\text{Tx}_j \ \forall$ Kv , ranging from sleep mode ($-\text{inf}$ dBm) to 43 dBm. All plots illustrate the effect of reducing transmit power of BSs in (Kv), and the impact that has on the network mean (i.e., across all cells).