Data-driven Energy Efficiency Modelling in Large-scale Networks: An Expert Knowledge and ML-based Approach

TL;DR

SRCON introduces a data-driven, mixed ML and expert framework to model network energy efficiency under carrier shutdown in large-scale 4G/5G deployments. By decomposing the problem into ML-based energy and UE rate models plus an expert ABM that captures stochastic shutdown and handover dynamics, SRCON achieves statistically indistinguishable network behavior without drive testing or ray-tracing. Empirical results on real metropolitan data show SRCON outperforms a leading operator baseline by substantial margins in energy consumption, UE throughput, and related KPIs, while offering robust generalization through a white-box ABM guiding ML inputs. The framework enables practical optimization of energy-saving policies with scalable data requirements, supporting future real-time or near-real-time extensions.

Abstract

The energy consumption of mobile networks poses a critical challenge. Mitigating this concern necessitates the deployment and optimization of network energy-saving solutions, such as carrier shutdown, to dynamically manage network resources. Traditional optimization approaches encounter complexity due to factors like the large number of cells, stochastic traffic, channel variations, and intricate trade-offs. This paper introduces the simulated reality of communication networks (SRCON) framework, a novel, data-driven modeling paradigm that harnesses live network data and employs a blend of machine learning (ML)- and expert-based models. These mix of models accurately characterizes the functioning of network components, and predicts network energy efficiency and user equipment (UE) quality of service for any energy carrier shutdown configuration in a specific network. Distinguishing itself from existing methods, SRCON eliminates the reliance on expensive expert knowledge, drive testing, or incomplete maps for predicting network performance. This paper details the pipeline employed by SRCON to decompose the large network energy efficiency modeling problem into ML and expert-based submodels. It demonstrates how, by embracing stochasticity, and carefully crafting the relationship between such submodels, the overall computational complexity can be reduced and prediction accuracy enhanced. Results derived from real network data underscore the paradigm shift introduced by SRCON, showcasing significant gains over a state-of-the art method used by a operator for network energy efficiency modeling. The reliability of this local, data-driven modeling of the network proves to be a key asset for network energy-saving optimization.

Figures (13)

• Figure 1: SRCON framework for network energy efficiency.
• Figure 2: Energy consumption SHAP analysis performed on the most important numerical features in the collected measurements data.
• Figure 3: Structure of our proposed ANN, highlighting the selected input variables, the organization and interconnection of the two hidden layers, and the configuration of the two output neurons which represent the mean and standard deviation of the power consumption estimates.
• Figure 4: True and estimated normalized energy consumption vs DL PRB load for multiple BSs of a given type.
• Figure 5: Example of UE rate SHAP analysis performed on the most important numerical features in the collected measurements data in a given cell.

Theorems & Definitions (7)

• Remark 1
• Remark 2
• Definition 1
• Definition 2
• Definition 3
• Definition 4
• Definition 5