PCP-2LSTM: Two Stacked LSTM-Based Prediction Model for Power Consumption in Data Centers

Summary Due to the rapid increase in the number and scale of data centers, the information and communication technology (ICT) equipment in data centers consumes an enormous amount of power. A power prediction model is therefore essential for decision‐making optimization and power management of ICT equipment. However, it is difficult to predict the power consumption of data centers accurately due to the complex power patterns and nonlinear interdependencies among components. Existing methods either rely on standard formulas, or simply treat it as time series, both leading to poor power prediction accuracy. To overcome those limitations, in this article, we present a systematic power prediction framework called characteristic aware attention‐augmented deep learning‐based prediction method. In particular, we first analyze the different power consumption series to illustrate their different temporal characteristics. Second, we perform different data processing for the corresponding characteristics of power series samples. Third, we propose an accurate and efficient neural network model to predict future power consumption with the pretreated data. The experimental results show that the proposed model is able to achieve superior prediction accuracy.

show abstract

“…• PCP-2LSTM: 20 A stacked layers of LSTM for nonstationary power consumption prediction, which we compare with on the CPU-intensive dataset only.…”

Section: Baseline Methodsmentioning

confidence: 99%

Data characteristics aware prediction model for power consumption of data center servers

Shen

Zhou

Zhang

et al. 2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Tang et al [13] have proposed an Empirical pattern Decomposition Deep Neural Network (EMDDNN) algorithm has been proposed by combining time windows with deep neural networks. [14] has put forward a power consumption prediction framework called PCP-2LSTM based on average smoothing and long short-term memory networks. A power consumption prediction method based on multiple energy-related features has been proposed in [15], which differs from other methods that only focus on a few performance features, it filters out multiple key energy-related features and using a deep learning model for full training.…”

Section: Introductionmentioning

confidence: 99%

An Improved ANN-based Power Prediction Algorithm for Multi-type Jobs on Heterogeneous Computing Server

Chao

2022

Preprint

View full text Add to dashboard Cite

This paper exploits the advantage of Artificial Neural Network (ANN) to design and implement an improved algorithm of power prediction on heterogeneous computing server with various types of jobs.First, the impact of multi-type of jobs has been taken into account. We divide the jobs into four categories: CPU-intensive, memory-intensive, I/O-intensive and GPU-intensive. We collect the data trace from these jobs by a set of benchmarks.Then, based on the collected data trace, power prediction algorithm has been established, so that developing an improved ANN-based power prediction algorithm with CNN-BiLSTM neural network and attention mechanism.Last, the experiment has been conducted via real-world heterogeneous computing based platform.Compared with the traditional neural network based prediction algorithms and non-neural network based prediction algorithms, our proposed prediction algorithm has better performance in prediction accuracy on power consumption.

show abstract

CBLA_PM: an improved ann-based power consumption prediction algorithm for multi-type jobs on heterogeneous computing server

Chao

2023

Cluster Comput

View full text Add to dashboard Cite

PCP-2LSTM: Two Stacked LSTM-Based Prediction Model for Power Consumption in Data Centers

Cited by 10 publications

References 21 publications

Data characteristics aware prediction model for power consumption of data center servers

Data characteristics aware prediction model for power consumption of data center servers

An Improved ANN-based Power Prediction Algorithm for Multi-type Jobs on Heterogeneous Computing Server

CBLA_PM: an improved ann-based power consumption prediction algorithm for multi-type jobs on heterogeneous computing server

Contact Info

Product

Resources

About