Neural Network Based Bin Analysis for Indirect/Direct Evaporative Cooling of Modular Data Centers

2018 ◽  
Author(s):  
Abhishek Walekar ◽  
Ashwin Siddarth ◽  
Abhishek Guhe ◽  
Nikita Sukthankar ◽  
Dereje Agonafer
Keyword(s):  
Neural Network ◽  
Data Center ◽  
Climatic Condition ◽  
Data Centers ◽  
Evaporative Cooling ◽  
Ann Model ◽  
Cooling Mode ◽  
Direct Evaporative Cooling ◽  
Modular Data ◽  
Psychrometric Chart

With an increase in the need for energy efficient data centers, a lot of research is being done to maximize the use of Air Side Economizers (ASEs), Direct Evaporative Cooling (DEC), Indirect Evaporative Cooling (IEC) and multistage Indirect/Direct Evaporative Cooling (I/DEC). The selection of cooling configurations installed in modular cooling units is based on empirical/analytical studies and domain knowledge that fail to account for the nonlinearities present in an operational data center. In addition to the ambient conditions, the attainable cold aisle temperature and humidity is also a function of the control strategy and the cooling setpoints in the data center. The primary objective of this study is to use Artificial Neural Network (ANN) modelling and Psychrometric bin analysis to assess the applicability of various cooling modes to a climatic condition. Training dataset for the ANN model is logged from the monitoring sensor array of a modular data center laboratory with an I/DEC module. The data-driven ANN model is utilized for predicting the cold aisle humidity and temperatures for different modes of cooling. Based on the predicted cold aisle temperature and humidity, cold aisle envelopes are represented on a psychrometric chart to evaluate the applicability of each cooling mode to the territorial climatic condition. Subsequently, outside air conditions favorable to each cooling mode in achieving cold aisle conditions, within the ASHRAE recommended environmental envelope, is also visualized on a psychrometric chart. Control strategies and opportunities to optimize the cooling system are discussed.

CFD Modeling of Indirect/Direct Evaporative Cooling Unit for Modular Data Center Applications

2013 ◽  
Author(s):  
Betsegaw Gebrehiwot ◽  
Nikhil Dhiman ◽  
Kasturi Rajagopalan ◽  
Dereje Agonafer ◽  
Naveen Kannan ◽  
...  
Keyword(s):  
Data Center ◽  
Cooling System ◽  
Evaporative Cooling ◽  
Cfd Modeling ◽  
Published Data ◽  
Cfd Model ◽  
Cold Air ◽  
Cooling Unit ◽  
Direct Evaporative Cooling ◽  
Modular Data

An information technology (IT) container needs to be supplied with cold air to cool IT equipment housed in it. The type of cooling system to be used depends on many factors including geographical location of the modular data center. Data centers located in regions where the climate is cold benefit from use of air-side economization (ASE) and those located in hot and dry climate benefit from use of direct and/or indirect evaporative cooling (DIEC) systems. In terms of energy saving, ASE, direct evaporative cooling (DEC) system, and indirect evaporative (IEC) systems are better than compressor based cooling systems such as computer room air conditioning (CRAC) units and air handling units (AHU). In this study, an existing DIEC unit which can also be operated in ASE mode is modeled in a computational fluid dynamics (CFD) tool. The cooling unit is intended to be used for supplying cold air to a containerized data center with specified volume flow rate, dry-bulb temperature and relative humidity. The CFD model is compared with published data of the cooling unit to see how well the CFD model represents the actual system and few design improvement ideas are tested by modifying the CFD model and running simulations. Results show that supplying air horizontally or as a downdraft to an IT container has negligible effect on the overall system. Results also show that orientation of dampers and placement of blanking panels inside the mixing chamber could affect the lifespan of air filters.

Weather Analysis Using Neural Networks for Modular Data Centers

2018 ◽  
Author(s):  
Feyisola Adejokun ◽  
Ashwin Siddarth ◽  
Abhishek Guhe ◽  
Dereje Agonafer
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Data Center ◽  
Evaporative Cooling ◽  
Weather Conditions ◽  
Cooling Control ◽  
The Neural Network ◽  
Modular Data

The objective of this work is to introduce the application of an artificial neural network (ANN) to assist in the evaporative cooling in data centers. To achieve this task, we employ the neural network algorithms to predict weather conditions outside the data center for direct evaporative cooling (DEC) operations. The predictive analysis helps optimize the cooling control strategy for maximizing the usage of evaporative cooling thereby improving the efficiency of the overall data center cooling system. A typical artificial neural network architecture is dynamic in nature and can perform adaptive learning in minimal computation time. A neural network model of a data center was created using operational historical data collected from a data center cooling control system. The neural network model allows the control of the modular data center (MDC) cooling at optimum configuration in two ways. First way is that the network model minimizes time delay for switching the cooling from one mode to the other. Second way, it improves the reaction behavior of the cooling equipment if an unexpected ambient condition change should come. The data center in consideration is a test bed modular data center that comprises of information Technology (IT) racks, Direct Evaporative cooling (DEC) and Indirect Evaporative Cooling (IEC) modules; the DEC/IEC are used together or in alternative mode to cool the data center room. The facility essentially utilizes outside ambient temperature and humidity conditions that are further conditioned by the DEC and IEC to cool the electronics, a concept know as air-side economization. Various parameters are related to the cooling system operation such as outside air temperature, IT heat load, cold aisle temperature, cold aisle humidity etc. are considered. Some of these parameters are fed into the artificial neural network as inputs and some are set as targets to train the neural network system. After the training the process is completed, certain bucket of data is tested and further used to validate the outputs for various other weather conditions. To make sure the analysis represents real world scenario, the operational data used are from real time data logged on the MDC cooling control unit. Overall, the neural network model is trained and is used to successfully predict the weather conditions and cooling control parameters. The prediction models have been demonstrated for the outputs that are static in nature (Levenberg Marquardt method) as well as the outputs that are dynamic in nature i.e., step-ahead & multistep ahead techniques.

scholarly journals Load balancing method for KDN-based data center using neural network

2021 ◽  
pp. 87-97
Author(s):  
Alex M. R. Ruelas ◽  
Christian E. Rothenberg
Keyword(s):  
Neural Network ◽  
Load Balancing ◽  
Data Center ◽  
Network Performance ◽  
Data Centers ◽  
Ann Model ◽  
Network Analytics ◽  
Cloud Application ◽  
Artificial Neural Network Ann ◽  
Knowledge Plane

The growth of cloud application services delivered through data centers with varying traffic demands unveils limitations of traditional load balancing methods. Aiming to attend evolving scenarios and improve the overall network performance, this paper proposes a load balancing method based on an Artificial Neural Network (ANN) in the context of Knowledge-Defined Networking (KDN). KDN seeks to leverage Artificial Intelligence (AI) techniques for the control and operation of computer networks. KDN extends Software-Defined Networking (SDN) with advanced telemetry and network analytics introducing a so-called Knowledge Plane. The ANN is capable of predicting the network performance according to traffic parameters paths. The method includes training the ANN model to choose the path with least load. The experimental results show that the performance of the KDN-based data center has been greatly improved.

scholarly journals An Artificial Neural Network Approach to Forecast the Environmental Impact of Data Centers

Information ◽  
2019 ◽  
Vol 10 (3) ◽  
pp. 113 ◽  
Author(s):  
Joao Ferreira ◽  
Gustavo Callou ◽  
Albert Josua ◽  
Dietmar Tutsch ◽  
Paulo Maciel
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Energy Consumption ◽  
Co2 Emissions ◽  
Data Center ◽  
Data Centers ◽  
New Technologies ◽  
Operational Costs ◽  
The Us ◽  
Artificial Neural

Due to the high demands of new technologies such as social networks, e-commerce and cloud computing, more energy is being consumed in order to store all the data produced and provide the high availability required. Over the years, this increase in energy consumption has brought about a rise in both the environmental impacts and operational costs. Some companies have adopted the concept of a green data center, which is related to electricity consumption and CO2 emissions, according to the utility power source adopted. In Brazil, almost 70% of electrical power is derived from clean electricity generation, whereas in China 65% of generated electricity comes from coal. In addition, the value per kWh in the US is much lower than in other countries surveyed. In the present work, we conducted an integrated evaluation of costs and CO2 emissions of the electrical infrastructure in data centers, considering the different energy sources adopted by each country. We used a multi-layered artificial neural network, which could forecast consumption over the following months, based on the energy consumption history of the data center. All these features were supported by a tool, the applicability of which was demonstrated through a case study that computed the CO2 emissions and operational costs of a data center using the energy mix adopted in Brazil, China, Germany and the US. China presented the highest CO2 emissions, with 41,445 tons per year in 2014, followed by the US and Germany, with 37,177 and 35,883, respectively. Brazil, with 8459 tons, proved to be the cleanest. Additionally, this study also estimated the operational costs assuming that the same data center consumes energy as if it were in China, Germany and Brazil. China presented the highest kWh/year. Therefore, the best choice according to operational costs, considering the price of energy per kWh, is the US and the worst is China. Considering both operational costs and CO2 emissions, Brazil would be the best option.

Supply Air Temperature Prediction in an Air-Handling Unit Using Artificial Neural Network

2018 ◽  
Author(s):  
Nikita Sukthankar ◽  
Abhishek Walekar ◽  
Dereje Agonafer
Keyword(s):  
Neural Network ◽  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Artificial Neural Network ◽  
Air Temperature ◽  
Data Center ◽  
Operating Conditions ◽  
Cfd Analysis ◽  
Ann Model ◽  
Air Handling Unit

Continuous provision of quality supply air to data center’s IT pod room is a key parameter in ensuring effective data center operation without any down time. Due to number of possible operating conditions and non-linear relations between operating parameters make the working mechanism of data center difficult to optimize energy use. At present industries are using computational fluid dynamics (CFD) to simulate thermal behaviour for all types of operating conditions. The focus of this study is to predict Supply Air Temperature using Artificial Neural Network (ANN) which can overcome limitations of CFD such as high cost, need of an expertise and large computation time. For developing ANN, input parameters, number of neurons and hidden layers, activation function and the period of training data set were studied. A commercial CFD software package 6sigma room is used to develop a modular data center consisting of an IT pod room and an air-handling unit. CFD analysis is carried out for different outside air conditions. Historical weather data of 1 year was considered as an input for CFD analysis. The ANN model is “trained” using data generated from these CFD results. The predictions of ANN model and the results of CFD analysis for a set of example scenarios were compared to measure the agreement between the two. The results show that the prediction of ANN model is much faster than full computational fluid dynamics simulations with good prediction accuracy. This demonstrates that ANN is an effective way for predicting the performance of an air handling unit.

Net-Zero Water (NZW) Reuse Desiccant Assisted Evaporative Cooling System for Data Centers

2019 ◽  
Author(s):  
David Okposio ◽  
A. G. Agwu Nnanna ◽  
Harvey Abramowitz
Keyword(s):  
Surface Area ◽  
Data Center ◽  
Data Centers ◽  
Waste Heat ◽  
Cooling System ◽  
Evaporative Cooling ◽  
Water Flow Rate ◽  
Peltier Effect ◽  
Water Recovery ◽  
Data Center Cooling

Abstract The cooling effect of evaporative cooling systems is well documented in literature. Evaporative cooling however introduces humidity into the cooled space, which is unsuitable for data centers. Desiccants (liquid, solid or composites) adsorb moisture from the cooled air to control humidity and is regenerated using waste heat from the data center. This work is an experimental and theoretical investigation of the use of desiccant assisted evaporative cooling for data center cooling according to ASHRAE thermal guideline TC 9.9 . The thickness of the cooling pads is varied with specific surface area, velocity of air through the pad measured, the product of the air velocity and surface area yields the volumetric flowrate of the air, the water flow rate varied as well. The configuration is such that the rotary desiccant wheel (impregnated with silica gel) comes after the evaporative cooler. A novel water recovery system using the Peltier effect is proposed to recover moisture from the return air stream thereby optimizing the water consumption of evaporative cooling technology and providing suitable air quality for data center cooling.

A Thermo-Mechanical Study on Vertically Split Distribution-Wet Cooling Media Used in Data Centers

2018 ◽  
Author(s):  
Mullaivendhan Varadharasan ◽  
Dereje Agonafer ◽  
Ahmed Al Khazraji ◽  
Jimil Shah ◽  
Ashwin Siddarth ◽  
...  
Keyword(s):  
Relative Humidity ◽  
Flow Rate ◽  
Data Center ◽  
Data Centers ◽  
Air Flow ◽  
Scale Formation ◽  
Flow Rates ◽  
Direct Evaporative Cooling ◽  
The Media ◽  
Cooling Media

Direct evaporative cooling (DEC) is widely used in the data center cooling units to maintain the air condition inside the data centers. Often, the flow rate of the water over the wet cooling media in this DEC process is frequently varied to maintain the air condition inside the data centers based on changing weather conditions. Though the adopted method helps to control the air temperature and relative humidity, the scale formation occurs on the surface of wet cooling media due to the frequent variation of the flow rate and deposition of minerals present in the water at low flow rate values, which increases the total weight of the wet cooling media and it can lead to a wet cooling media collapse. In this paper an alternative and simplified method to control the air condition is presented. A vertically split wet cooling media is designed and tested in a commercial CFD tool to analyze the temperature and relative humidity parameters of the inlet and outlet air to the wet cooling media, in this approach the sections of the media can either be completely wet or completely dry which can potentially avoid the scale formation on the surface of the wet cooling media. In addition to the temperature and relative humidity parameters against the air flow rates, the pressure drop and cooling efficiency values for varied air flow rates are studied. The vertically split wet cooling media configurations are achieved by sectioning the media in to equal and unequal sections. In the equal configuration, media has been tested for 0%, 50% and 100% wetting conditions, and in the unequal configuration, media has been tested for 0%, 33%, 66% and 100% wetting conditions. The test results are used to emphasis the advantage of this staged wetting method and gives a possible solution to the scale formation problem on the wet cooling media during the direct evaporative cooling process in the data center.

Improving Energy Efficiency Through Thermal Control of a Modular Data Center

2012 ◽  
Author(s):  
John Guinn ◽  
Srujan Gondipalli
Keyword(s):  
Heat Exchanger ◽  
Data Center ◽  
Data Centers ◽  
Water Flow Rate ◽  
Thermal Control ◽  
Cooling Capacity ◽  
Thermal Control System ◽  
Modular Data ◽  
Fan Speed ◽  
Usage Efficiency

As the IT industry’s demand for greater power density racks grows, the operating cost associated with power and cooling IT equipment remains an ever present concern facing data centers. A key component in reducing Total Cost of Ownership (TCO) for a facility is to optimize their cooling system design. Hewlett-Packard has developed a self contained enclosure for high density servers and mass storage devices called a Modular Data Center (MDC). This unit is intended to reduce issues that have plagued large scale data centers by increasing cooling capacity and efficiency. This paper takes a look at the thermal control logic for the MDC and explains ways to decrease energy costs by developing a thermal control scheme centered on optimizing Power Usage Efficiency (PUE). Tests were conducted to understand the relationships between fan power and fan speed, facility power and thermal capacity. Areas of large power drains were isolated and analyzed. Tests showed that there are two parts in managing power usage on the MDC, system and facility control. In the development of a smarter control algorithm, the fans and water valve (“system”) performance curves provided a road map to the hardware’s capability. This was accomplished by understanding how key variables such as inlet water temperature, water flow rate and fan speed impact the behavior of server inlet air temperature and cooling capacity. Facility control comes from optimizing what equipment is in place to support the MDC (i.e. dedicated chiller, campus chiller, pumps, etc…) within a data center. A significant goal of this project was to minimize the dependency MDC has on external cooling by optimizing the variables that affect facility power. For instance controlling heat removal rate and exiting water temperature affects chiller power; while water flow rate affects pump power. Knowledge of your system and facility’s capabilities directly impacts power management. Thermal performance testing of the heat exchanger in the MDC provided insight into how increasing thermal efficiency at the heat exchanger produced an overall drop in facility power. Tests revealed that the optimized thermal control system achieved an infrastructure energy savings up to 33% with a PUE improvement from 1.35 to 1.23 for a 100KW IT heat load. The results show that characterizing and incorporating the behavior of the fans and heat exchanger into the thermal control system produced an improved Power Usage Efficiency (PUE) and a smarter control method.

Qualitative Study of Cumulative Corrosion Damage of IT Equipment in a Data Center Utilizing Air-Side Economizer

2016 ◽  
Author(s):  
Jimil M. Shah ◽  
Oluwaseun Awe ◽  
Pavan Agarwal ◽  
Iziren Akhigbe ◽  
Dereje Agonafer ◽  
...  
Keyword(s):  
Relative Humidity ◽  
Data Center ◽  
Data Centers ◽  
Energy Savings ◽  
Evaporative Cooling ◽  
Corrosion Damage ◽  
Air Cooling ◽  
Single Server ◽  
Severity Level ◽  
Particulate Contamination

Deployment of air-side economizers in data centers is rapidly gaining acceptance to reduce the cost of energy by reducing the hours of operation of CRAC units. Use of air-side economizers has the associated risk of introducing gaseous and particulate contamination into data centers, thus, degrading the reliability of Information Technology (IT) equipment. Sulfur-bearing gaseous contamination is of concern because it attacks the copper and silver metallization of the electronic components causing electrical opens and/or shorts. Particulate contamination with low deliquescence relative humidity is of concern because it becomes wet and therefore electrically conductive under normal data center relative humidity conditions. IT equipment manufacturers guarantee the reliability of their equipment operating in environment within ISA 71.04-2013 severity level G1 and within the ASHRAE recommended temperature-relative humidity envelope. The challenge is to determine the reliability degrading effect of contamination severity levels higher than G1 and the temperature and humidity allowable ranges A1–A3 well outside the recommended range. This paper is a first attempt at addressing this challenge by studying the cumulative corrosion damage to IT equipment operated in an experimental data center located in Dallas, known to have contaminated air with ISA 71.04-2013 severity level G2. The data center is cooled using an air-side economizer. This study serves several purposes including: the correlation of equipment reliability to levels of airborne corrosive contaminants and the study of the degree of reliability degradation when the equipment is operated, outside the recommended envelope, in the allowable temperature-relative humidity range in geographies with high levels of gaseous and particulate contamination. The operating and external conditions of a modular data center, located in a Dallas industrial area, using air-side economizer is described. The reliability degradation of servers exposed to outside air via an airside economizer was determined qualitatively examining the corrosion of components in the servers and comparing the results to the corrosion of components in a non-operating server stored in a protective environment. The corrosion-related reliability of the servers over almost the life of the product was related to continuous temperature and relative humidity for the duration of the experiment. This work provides guidance for data center administration for similar environment. From an industry perspective, it should be noted that in the four years of operation in the hot and humid Dallas climate using only evaporative cooling or fresh air cooling, we have not seen a single server failure in our research pod. That performance should highlight an opportunity for significant energy savings for data center operators in a much broader geographic area than currently envisioned with evaporative cooling.

Sign in / Sign up

Export Citation Format

Share Document