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

Modern cloud computing relies heavily on data centers, which usually host tens of thousands of servers. Predicting the power consumption accurately in data center operations is crucial for energy optimization. In this paper, we formulate the power consumption prediction at both the fine-grained and coarse-grained level. We carefully discuss the desired properties of an applicable prediction model and propose a non-intrusive, traffic-aware prediction framework for power consumption. We design a character-level encoding strategy for URIs and employ both convolutional and recurrent neural networks to develop a unified prediction model. We use real datasets to simulate requests and analyze the characteristics of the collected power consumption series. Extensive experiments demonstrate that our proposed framework can achieve superior prediction performance compared to other popular leading prediction methods.

Download Full-text

Outdoor Air-Cooling System for a Computer Room and Its Corresponding Energy-Saving Effect

Energies ◽

10.3390/en13215719 ◽

2020 ◽

Vol 13 (21) ◽

pp. 5719

Author(s):

JiHyun Hwang ◽

Taewon Lee

Keyword(s):

Power Consumption ◽

Energy Saving ◽

Data Centers ◽

Cooling System ◽

Stable Operation ◽

Air Cooling ◽

Outdoor Air ◽

Air Conditioners ◽

Air Cooling System ◽

Saving Effect

The recent expansion of the internet network and rapid advancements in information and communication technology are expected to lead to a significant increase in power consumption and the number of data centers. However, these data centers consume a considerable amount of electric power all year round, regardless of working days or holidays; thus, energy saving at these facilities has become essential. A disproportionate level of power consumption is concentrated in computer rooms because air conditioners in these rooms are required to operate throughout the year to maintain a constant indoor environment for stable operation of computer equipment with high-heat release densities. Considerable energy-saving potential is expected in such computer rooms, which consume high levels of energy, if an outdoor air-cooling system and air conditioners are installed. These systems can reduce the indoor space temperature by introducing a relatively low outdoor air temperature. Therefore, we studied the energy-saving effect of introducing an outdoor air-cooling system in a computer room with a disorganized arrangement of servers and an inadequate air conditioning system in a research complex in Korea. The findings of this study confirmed that annual energy savings of up to approximately 40% can be achieved.

Download Full-text

Data Driven Prediction Model (DDPM) for Server Inlet Temperature Prediction in Raised-floor Data Centers

2018 17th IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm) ◽

10.1109/itherm.2018.8419650 ◽

2018 ◽

Author(s):

Raymond Lloyd ◽

Marek Rebow

Keyword(s):

Prediction Model ◽

Data Centers ◽

Data Driven ◽

Inlet Temperature ◽

Temperature Prediction

Download Full-text

Fuzzy Rule-Based Systems for Optimizing Power Consumption in Data Centers

Advances in Intelligent Systems and Computing - Image Processing and Communications Challenges 5 ◽

10.1007/978-3-319-01622-1_34 ◽

2014 ◽

pp. 301-308 ◽

Cited By ~ 3

Author(s):

Moad Seddiki ◽

Rocío Pérez de Prado ◽

José Enrique Munoz-Expósito ◽

Sebastián García-Galán

Keyword(s):

Power Consumption ◽

Data Centers ◽

Fuzzy Rule ◽

Rule Based ◽

Rule Based Systems

Download Full-text

The Numerical Simulation of the Airflow Distribution and Energy Efficiency in Data Centers with Three Types of Aisle Layout

Sustainability ◽

10.3390/su11184937 ◽

2019 ◽

Vol 11 (18) ◽

pp. 4937 ◽

Cited By ~ 1

Author(s):

Jing Ni ◽

Bowen Jin ◽

Shanglei Ning ◽

Xiaowei Wang

Keyword(s):

Energy Efficiency ◽

Power Consumption ◽

Air Conditioning ◽

Data Centers ◽

Simulation Method ◽

Cooling Capacity ◽

Energy Utilization ◽

Improve Energy Efficiency ◽

Electricity Cost ◽

Airflow Distribution

The energy consumption of fast-growing data centers is drawing attentions from not only energy organizations and institutions all over the world, but also charity groups, such as Greenpeace, and research shows that the power consumption of air conditioning makes up a large proportion of the electricity cost in data centers. Therefore, more detailed investigations of air conditioning power consumption are warranted. Three types of airflow distributions with different aisle layouts (the open aisle, the closed cold aisle, and the closed hot aisle) were investigated with Computational Fluid Dynamics (CFD) methods in a typical data center of four rows of racks in this study. To evaluate the results of thermal and bypass phenomenon, the temperature increase index (β) and the energy utilization index (ηr) were used. The simulations show that there is a better trend of the β index and ηr index both closed cold aisle and closed hot aisle compared with free open aisle. Especially with high air flow rate, the β index decreases and the ηr index increases considerably. Moreover, the results prove the closed aisles (both closed cold aisle and closed hot aisle) can not only significantly improve the airflow distribution, but also reduce the mixture of cold and heat flow, and therefore improve energy efficiency. In addition, it proves the design of the closed aisles can meet the increasing density of installations and our simulation method could evaluate the cooling capacity easily.

Download Full-text

TAR Based Hotspot Prediction in Cloud Data Centres

International Journal of Grid and High Performance Computing ◽

10.4018/ijghpc.2019070101 ◽

2019 ◽

Vol 11 (3) ◽

pp. 1-22

Author(s):

Anu Valiyaparambil Raveendran ◽

Elizabeth Sherly Sherly

Keyword(s):

Prediction Model ◽

Resource Utilization ◽

Data Centers ◽

Linear Regression Analysis ◽

Load Prediction ◽

Bandwidth Utilization ◽

Virtual Machine Migration ◽

Cloud Data ◽

Network Bandwidth ◽

Cloud Data Centers

In this article, the authors studied hotspots in cloud data centers, which are caused due to a lack of resources to satisfy the peak immediate requests from clients. The nature of resource utilization in cloud data centers are totally dynamic in context and may lead to hotspots. Hotspots are unfavorable situations which cause SLA violations in some scenarios. Here they use trend aware regression (TAR) methods as a load prediction model and perform linear regression analysis to detect the formation of hotspots in physical servers of cloud data centers. This prediction model provides an alarm period for the cloud administrators either to provide enough resources to avoid hotspot situations or perform interference aware virtual machine migration to balance the load on servers. Here they analyzed the physical server resource utilization model in terms of CPU utilization, memory utilization and network bandwidth utilization. In the TAR model, the authors consider the degree of variation between the current points in the prediction window to forecast the future points. The TAR model provides accurate results in its predictions.

Download Full-text