With the increasing demands of digital computing, Data Centers (DCs) have become a leading scheme for global energy issues. Major efforts that can be observed for DC energy efficacy solutions are focusing on relatively problematic infrastructure designs. Nevertheless, we emphasised the managerial strategies of using the existing facilities to achieve energy efficiency through active intervention. It is believed that there exists a trade-off between the cooling devices and IT devices. Accordingly, the Vector Autoregressive Model- Reinforcement Learning(VAR-RL) approach will be proposed as a combination of traditional multivariate time series modeling technique and the artificial intelligence technique which allows us to predict and adjust the prediction of an error would help to explore the complex dynamic interrelationships between the two types of devices. Moreover, an optimization decision support system will also be conducted subsequently to optimize Power Usage Effectiveness (PUE) by controlling the combination of Air Conditioners (ACs). The proposed VAR-RL approach would not only increase the forecasting accuracy but also would adapt to the environment changes dynamically, this would give a better foundation for the DC energy efficiency optimization. The data we adopted is the real-time data from a DC located in Turkey. Consequently, the novel of this study would save the DC energy consumption tremendously.
DCs are energy-intensive industries and they are taking 1-1.5% of global electricity usage every year [1]. There are two main units of DCs that are supplied the energy, IT, Copyright © 2020 for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). and cooling units. Widely cited studies and conservatively evaluation demonstrated the fact that there are around 40% of energy has been taken by the cooling system in a typical air-cooling DC [2]. IT equipment, along with its respective power supply, creates heat when being in use and will raise the surrounding ambient temperature. In consequence, the equipment is likely to fail if the temperature becomes too high. Previous to 2004, IT companies were too fixated upon the performance of their equipment and adjusted the equipment’s environment with only reliability in mind, with little weighting to energy costs. Nowadays the temperature range has been wider to 18 − 27℃ (ASHRAE 2016)[3]. However, there are over 90% of DCs still keeping a constant temperature which means that the DCs are over-cooled and energy inefficiency [4].
Since most of the energy consumption lies in cooling, efforts have been made on reducing the cooling energy consumption in the DCs. It has been found that configuration design predominantly affects on energy consumption. As long as there is a design revolution, the application still requires a long time. As a result, traditional air-cooling will still domain the DC cooling system in the next few decades [5]. Therefore, we are seeking DC cooling efficiency solutions from a different aspect. As we mentioned earlier, cooling devices are the biggest energy consumers in the DC however there is no guideline on how to make the optimal usage of them. The common operations in DCs are still following traditional rules by turning off some certain number of ACs to save energy in winter. But to our knowledge, there is no sophisticated analysis so far to guide the optimal use of ACs combination, which gives us ideas to fill up this gap.
According to the relationship of energy consumption units both IT and Air conditioning devices, a lower temperature will increase the energy supplied, inversely, will reduce the energy consumption of IT devices due to an increasing computing efficiency. Therefore, smart operation management on DCs to find out the optimal solution on temperature control to minimize the energy consumption without affecting the performance of IT devices and meeting the service-level agreement has been investigated. Therefore, this has become our motivation for this study. The question can be modeled as a Linear Programming (LP) problem. However, applying the LP method to the problem requires understanding the complex interactions among many variables within the DC. To solve and simplify this issue, we adopt VAR model to identify such complex interactions. It has been taken to account for common features of the industry big data
Changes rapidly in the structures. Changes in server workload, outside environment, device locations or human intervention all can be reasons that lead to structural breaks of the series. Numerous empirical studies put attention on post-event detection, which wildly used for economic or business analysis, while rarely of them are looking at this issue in a real-time. Instead, we expect the model would able to autonomous evaluate itself and correct the mistake once it notices it. In this study, we adopt RL approach for dynamic real-time adjustment of VAR model. It would take the responsibility to detect the structural break and trigger the parameter re-estimated system. With the proposed VAR-RL approach, the subsequent optimization problem can be solved with the consideration of the changes in the environment in real-time.
Our contributions to the literature including the following: (1) Give the DC energyefficient solution without changing DC configurations. (2) A dynamic simulation system based on VAR-RL approach has been made, this will provide an efficient and accurate forecast for the complex environment with the adjustment of structural changes in the data. (3) Real-time optimization will be conducted based on the simulation result and future optimization also can be made by the forecasted data set. (4) This study will also arouse the environmental awareness of energy saving. 2
We have searched the empirical studies on DC effective cooling strategy of simulationbased optimization. Among the ten results, eight of them adopted the Computational Fluid Dynamic (CFD) while and the rest of them used Data-driven Models (DDM) model and other configuration design simulation tools for airflow simulation.
Most of them are from a pure configuration design and layout aspect, ie. [6] on
sensors placement strategy and [
We conservatively conclude that our VAR-RL approach would be the first study that
further extended Linear Regression (LR) based RL to analyze complex industrial
environment, then apply the simulation result to real-time optimization in industrial
practical case. Due to the limited resources, we reviewed similar studies that used the similar
method for different problems. RL approach has been used for an auto-select different
combination of data streams to feed to the parameters-fixed LRs and practical
application on typhoon rainfall prediction shows a better performance than traditional LRs
[
Our VAR-RL approach would take advantage of these empirical studies, moreover, we will adapt this into DC industrial practice: (1) Our model parameters will be dynamically changed according to the feedback from the learning process that would allow our model to adapt to the environment changes. (2) We will propose a time-series linear regression model that will not only consider the previous one step (MACOV) but the whole period which has an effect on the present. (3) RL tool will be plugin to determine whether the model should be reused or rebuilt. (4) We will also avoid using the technique which has a black-box property such as Artificial Neuron Network (ANN) because it hides the interrelationships into the black-box procedure which limited the interpretative of the model. (4) Also, as we expect to perform a light, fast, and efficient model to adapt to the rapid industrial practice. we will avoid the use of techniques that requires huge size of training data and local storage. (5) We will not change any DC configurations including the sensors, only managerial strategies will be applied to the DC energy-saving practice.
Based on the field study in TUKSAT DC target IT room, we identified the main factors that participated in the IT room computing environment. We are going to include ceiling sensors temperatures, Server rack inlet and outlet temperatures, air conditioner outflow temperatures as well as PDU values of the servers as our endogenous variables. To our knowledge, IT room objectives are mutually affected by each. As the graph shows below, we can infer that each variable can affect the others in two directions (direct or indirect), shown as a circulation (Fig.1). Statistical test (Granger causality test) results also confirmed the underlined inferences. Therefore, we briefly include all the related variables into one VAR model.
Here we present how VAR modelling the above dynamic. VAR assumes all the variables to be endogenous and explain those endogenous variables one by one by all their past values. This allows us to use the estimated model to predict the future values of variables. A ℎ order () can be represented as:
(1) × 1 × 1
Assume we have variables, then is the × 1 order constant vector, the П is the ×
order time series vector, is the order parameter matrix, is the order random error vector. We can extend the above equation to the matrix formula as following (The lag length will be selected by the combination of "AIC", "HQ", "SC", "FPE" criteria):
As VAR model is a dynamic forecasting model. We can use it to simulate the DC environment as well as forecast the future values of each variable. After we get the model parameters by real-time estimation, we will feed the data that cover the lag length and forecast the future value of each variable. To make it clear, here we summarize the procedure to train a VAR model and use it as a simulator to forecast DC environment in a flowchart (See Fig.2).
We first downloaded data from the historical Application Programming Interface (API) (Step 1). After data processing (Step 2), we use this data set to train a VAR model (Step 3). Then download historical data again (Step 4), after processing the data for another time (Step 5), we extract the most recent data which cover our lags, then input to the VAR model. The simulator will carry out iterations until reach to the requested forecasting length. 3.2
As we mentioned earlier, the data estimated in DC has a rapidly changing feature, therefore our fundamental simulator VAR may not apply for some special cases: ie., suddenly changing load by holidays or online exams, temperatures changes, or other human interventions. Therefore, we need to adjust our model to ensure the prediction accuracy and be able to detect the environment changes and adapt itself to the changing world. Reinforcement learning as an environment adaptor to VAR model will be introduced in this section. The process is shown in the following graph (Fig.3). With every prediction, we will have an evaluation of the accuracy. And we will give a reward (or punishment) to each prediction. The accumulated reward would be: = ∑=1 + Where
is the total cumulated reward values, is the reward for each forecast evaluation. With the number of time steps increasing, the difficulty level to predict would be increasing too, to make it fair enough for the judgement, we assign the weight to each reward, and the weight of the reward would be decreasing over the time. = ∑∞=0 ++1 , ∈ [0,1)
(3) (4) Time windows will be plugin at every seasonality changing point. And the system will trigger RL to evaluate the prediction result. In this case, the prediction result from the fundamental simulator VAR will be evaluated by the error rate. A reward will be given to each evaluation. When the accumulated reward value reaches to a certain boundary, the environment changes will be detected. Then the RL adaptor will trigger the alarm then the VAR model parameters and features will be rebuilt. 3.3
Empirical evidences show that increasing the AC setpoint by a single degree can result
in 4-5% energy cost savings; and increasing the setpoint by 10 degrees, which is also a
realistic number, can result in savings of over 40% [
We will use the following notations:
{ 1, 2, … , } denotes the Server rack number 1 to = { 1, 2, … , } is a set of ACs unit number 1 to . ( ): the temperature supply of the ℎ AC unit at time . ( ): the inlet temperature of the ℎ server rack at time .
( ): the outlet temperature of the ℎ server rack at time .
( ): the room temperature at time .
( ): the computational power (PDU) for the ℎ server rack at time . ( ): the computational power for the ℎ AC unit at time . ( )]: the estimated workload (CPU usage) for the ℎ server rack at time . : the coefficient of performance.
is the thermal correlation index.
The IT consumption . Assumingly, the IT power consumption would not only be influenced by the computational workload, but also will be affected by the working temperature because the temperature will affect its working performance. Hence, at any time , the total IT computing power of server rack is the function of power spent on executing IT jobs and the rack inlet temperature. = [ ( ) = [ ( )] + ( )
(5)
The cooling consumption ( ) = ( ( )) ( )
(6)
. Based on [
( ) by maximise the allowable supplied cold air temperature, ( ) that satisfies the constraint of redline thresholds. The simulation approach will also be used to get the function of is the thermal correlation index,
=∆ , which represents the influence of each AC unit on inlet
temperature of server rack . As defined in Eq. (6), it quantifies the response of the server
’s inlet temperature
to a step-change in the supply temperature
is a static metric, which is stable with time but based on the physical
configuration of the DC. Hence, we use the simulation approach to get the value of
of .
. The
detailed explanation of this metric can be seen in [
Thermal modelling . According to the law of energy conservation, almost all the computing power consumed by a server is transformed into heat, hence the relationship between the power consumption and inlet/outlet temperature of server rack can be presented as: ( )
(7)
Where = is the thermal-physical term. This can be estimated by our data
obtained in DC.
plied air temperature (
Typically, the server’s inlet temperature (
) tends to be higher than the AC’s
sup) due to the phenomenon so-called heat recirculation where
the hot air from the server and the supplied cool air from the AC are mixed then
recirculats in the room. Based on the energy conservation as described in Eq. (8) and the
assumption of the fixed airflow pattern in the computer room, prior studies (eg. [
. Here we adjust this to matrix = { } denotes the heat increased at the inlet of server rack caused by the heat recirculated inside the rack due to computation. Hence, the inlet temperature of a server rack comes from the combination of the supplied cold air from the AC and hot air recirculated inside the rack. This relationship can be written as: (8) (9) ( ) = ∑=1 ( )+ ( ) Where
is a binary variable which equals to 1 if the AC unit is assigned to supply cold air to the rack slot of server rack , and 0 otherwise. As the DC layout is fixed, the value of
will be given by VAR estimation.
With equations (5) and (8), we can transfer ( ) to the function of ( ). 1−
( )+ [ ( )]
Optimization solution Moreover, for each AC, there are thresholds ( 4 the AC temperatures to be within the range (0 − 30℃). ) and ( 5
), which will restrict Similarly, by aligning with Eq. (9), we can transfer the constraints functions Eq. (13,14) to the function of
In short, the operational problem that we will address at the first stage is to optimize the objective function in Eq. (12) by determining the optimal supplied cold temperature of the AC devices, given the constraints in Eq. (13, 14, 15). The optimization would start once we estimate the DC may perform inefficiently by VAR-RL forecasting, and . is also defined by VAR-RL). target temperature combination will be set at 1 − periods on the timeline (Where 4
Future studies will be made on forecasting verification and model adjustment. An application UI (User Interface) will be applied for the DC managers to make sustainable DC management. Field trial studies will also be conducted subsequently, we will modify our models and further studies will be done accordingly. (14) (15) (2016). tute (2013). 1577–1588, (2013).
(2014). 1. A. Andrae and T. Edler: On Global Electricity Usage of Communication Technology: Trends to 2030. Challenges, 6(1). 117–157, (2015).
technologies. Energy Procedia, 83, 484–493, (2015). 2. A. Capozzoli and G. Primiceri: Cooling systems in data centers: state of art and emerging 3. ASHRAE: Data Center Power Equipment Thermal Guidelines and Best Practices. pp.1–60, 4. M.K. Stansberry: JulianUptime Institute 2012. Data Center Industry Survey, Uptime Insti
Energy & Buildings, 179, 264–277, (2018). 5. Lu, H., Zhang, Z., Yang, L: A review on airflow distribution and management in data center. 6. Wang, X., Xing, G., Chen, J., Lin, C. X., Chen, Y. Intelligent sensor placement for hot server detection in data centers. IEEE Transactions on Parallel and Distributed Systems, 24(8), 7. Volk, E., Rathgeb, D., Oleksiak, A., Volk, E., Rathgeb, D, Rathgeb, D., Oleksiak, A.: CoolEmAll-optimising cooling efficiency in data centres. Compute Sci Res Dev, 29, 253–26,