A Bidirectional Gated Recurrent Unit Model for PUE Prediction in Data Centers

2025-12-23

AI Summary

To address energy efficiency optimization in data centers, this paper proposes a PUE time-series forecasting method based on Bidirectional Gated Recurrent Units (BiGRU). It is the first work to introduce BiGRU for PUE prediction, integrating Recursive Feature Elimination with Cross-Validation (RFECV) for dynamic selection of critical influencing factors and enabling end-to-end co-optimization of model architecture and hyperparameters. Evaluated on a Singapore data center simulation dataset (52,560 samples, 117 features), the method significantly reduces MSE and MAE compared to unidirectional GRU, achieving an R² of 0.983—demonstrating substantially improved prediction accuracy. Moreover, it precisely identifies core energy-driving features—including ambient temperature, humidity, and IT load—providing quantitative insights for targeted operational control. This work establishes a novel, interpretable, and high-accuracy predictive modeling paradigm for intelligent energy efficiency management in data centers.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• 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: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Data centers account for significant global energy consumption and a carbon footprint. The recent increasing demand for edge computing and AI advancements drives the growth of data center storage capacity. Energy efficiency is a cost-effective way to combat climate change, cut energy costs, improve business competitiveness, and promote IT and environmental sustainability. Thus, optimizing data center energy management is the most important factor in the sustainability of the world. Power Usage Effectiveness (PUE) is used to represent the operational efficiency of the data center. Predicting PUE using Neural Networks provides an understanding of the effect of each feature on energy consumption, thus enabling targeted modifications of those key features to improve energy efficiency. In this paper, we have developed Bidirectional Gated Recurrent Unit (BiGRU) based PUE prediction model and compared the model performance with GRU. The data set comprises 52,560 samples with 117 features using EnergyPlus, simulating a DC in Singapore. Sets of the most relevant features are selected using the Recursive Feature Elimination with Cross-Validation (RFECV) algorithm for different parameter settings. These feature sets are used to find the optimal hyperparameter configuration and train the BiGRU model. The performance of the optimized BiGRU-based PUE prediction model is then compared with that of GRU using mean squared error (MSE), mean absolute error (MAE), and R-squared metrics.

Problem

• Predicts Power Usage Effectiveness (PUE) in data centers using a BiGRU model
• Identifies key features affecting energy consumption to enhance efficiency
• Compares BiGRU with GRU performance using error and R-squared metrics

Innovation

• Bidirectional Gated Recurrent Unit for PUE prediction
• Recursive Feature Elimination with Cross-Validation for feature selection
• EnergyPlus simulation dataset for model training and evaluation