BERTO: an Adaptive BERT-based Network Time Series Predictor with Operator Preferences in Natural Language
This work addresses energy efficiency and performance trade-offs for cellular network operators, but it is incremental as it adapts existing BERT methods to a specific domain.
The paper tackles traffic prediction and energy optimization in cellular networks by introducing BERTO, a BERT-based framework that uses natural language prompts to balance power savings and performance, achieving a 4.13% reduction in MSE and operating over a flexible range of 1.4 kW in power and up to 9x variation in service quality.
We introduce BERTO, a BERT-based framework for traffic prediction and energy optimization in cellular networks. Built on transformer architectures, BERTO delivers high prediction accuracy, while its Balancing Loss Function and prompt-based customization allow operators to adjust the trade-off between power savings and performance. Natural language prompts guide the model to manage underprediction and overprediction in accordance with the operator's intent. Experiments on real-world datasets show that BERTO improves upon existing models with a $4.13$\% reduction in MSE while introducing the feature of balancing competing objectives of power saving and performance through simple natural language inputs, operating over a flexible range of $1.4$ kW in power and up to $9\times$ variation in service quality, making it well suited for intelligent RAN deployments.