BERTO: Intent-Driven Network Time Series Forecasting via Natural Language Operator Preferences

TL;DR

BERT-based BERTO framework enables intent-driven cellular traffic forecasting with natural language prompts, balancing power savings and SLA violations without retraining.

Contribution

Introduces BERTO, a transformer-based model that adapts forecasting bias via natural language prompts for flexible, decision-aware network predictions.

Findings

Achieves high prediction accuracy across multiple regimes.

Operates within a 1.4 kW power range while balancing SLA violations.

Uses prompt-based conditioning to shift forecasting bias dynamically.

Abstract

Traditional cellular traffic forecasting models are optimized for minimizing symmetric errors, leaving them indifferent to shifting operational priorities. To bridge this gap, we introduce BERTO, a BERT-based framework for traffic prediction and energy optimization in cellular networks. Built on transformer architectures, BERTO achieves high prediction accuracy while enabling a single fine-tuned model to operate across multiple forecasting regimes via natural-language operator prompts. By combining a Balancing Loss Function (BLF) with prompt-based conditioning, BERTO adaptively shifts its forecasting bias toward underprediction or overprediction depending on the operator's desired trade-off between power savings and service quality. This allows the same model to dynamically generate different decision-aware forecasts without retraining or modifying model parameters. Experiments on real-world datasets demonstrate that BERTO can operate across a flexible range of approximately 1.4 kW in power consumption while balancing 9x variation in service level agreement (SLA) violations, making it well suited for intelligent RAN deployments.