Modelling the 5G Energy Consumption using Real-world Data: Energy Fingerprint is All You Need

2024-06-13

arXiv.org

AI Summary

The surging energy consumption of 5G base stations threatens network sustainability, while existing models fail to capture the coupled effects of individual base station heterogeneity and dynamic operational conditions. To address this, we propose a high-precision, real-world-oriented energy consumption prediction method. Our approach introduces base station identifiers (BSIDs) with embedding encoding to model each station’s unique “energy fingerprint,” and integrates a masked training strategy with attention mechanisms to jointly enhance generalization and prediction accuracy. Built upon a deep regression framework, the model combines learnable embeddings, self-attention modules, and a robust training paradigm. Evaluated on a real-world dataset, it reduces the mean absolute percentage error (MAPE) from 12.75% to 4.98%—a >60% improvement in accuracy—and secured second place in the ITU 5G Energy Consumption Modeling Challenge.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The introduction of fifth-generation (5G) radio technology has revolutionized communications, bringing unprecedented automation, capacity, connectivity, and ultra-fast, reliable communications. However, this technological leap comes with a substantial increase in energy consumption, presenting a significant challenge. To improve the energy efficiency of 5G networks, it is imperative to develop sophisticated models that accurately reflect the influence of base station (BS) attributes and operational conditions on energy usage.Importantly, addressing the complexity and interdependencies of these diverse features is particularly challenging, both in terms of data processing and model architecture design. This paper proposes a novel 5G base stations energy consumption modelling method by learning from a real-world dataset used in the ITU 5G Base Station Energy Consumption Modelling Challenge in which our model ranked second. Unlike existing methods that omit the Base Station Identifier (BSID) information and thus fail to capture the unique energy fingerprint in different base stations, we incorporate the BSID into the input features and encoding it with an embedding layer for precise representation. Additionally, we introduce a novel masked training method alongside an attention mechanism to further boost the model's generalization capabilities and accuracy. After evaluation, our method demonstrates significant improvements over existing models, reducing Mean Absolute Percentage Error (MAPE) from 12.75% to 4.98%, leading to a performance gain of more than 60%.

Problem

• Modeling 5G base station energy consumption accurately
• Reducing high energy usage in 5G networks sustainably
• Capturing unique energy patterns across different base stations

Innovation

• Embedding layer integrates BSID for unique patterns
• Masked training method enhances model generalization
• Attention mechanism improves estimation accuracy significantly