**2. Background**

#### **2.1 Preventive and predictive maintenance**

Preventive maintenance implies to regular maintenance or TBM that maintains devices and systems up and operating as normal condition, prevent any unplanned

### *Condition-Based Maintenance for Data Center Operations Management DOI: http://dx.doi.org/10.5772/intechopen.93945*

downtime, uneconomical costs from unpredicted system failure, and preserve the operation running efficiency and effectiveness.

CBM comprehends as predictive maintenance. It is a useful mechanism of strategic approach for preventive maintenance that collaborates with monitoring and controlling conditions of critical devices and equipment parameters. This process will operate in order to predict device failure, to assess the RUL, and to avoid system risks, which could be happened if minimum conditions are exceeded. This strategy demonstrates the economical savings over observation of lessons or timebased preventive maintenance, because exertion will execute only when guaranteed.

A RUL defines based on the maintenance policy for single unit deteriorating system that all conditions are continually monitoring with deploying A-B-C analysis to device criticality build up on early successful diagnostics. The A-B-C analysis will diagnose and categorized level of system maintenance into 3 groups; reactive maintenance and excessive repairs and failures; proactive maintenance; and excessive PM and no failure and no repairs [2], as presented in **Figure 1**.

#### **2.2 Condition-based maintenance**

The research from Ponemon Institute [1] reports that the total average cost of data center downtime soared by 38 percent in 2010 from \$505,502 to \$740,357 per unplanned downtime in 2016. Thereby, to evade these costs of data center downtime; they require deploying more procedures of intensive training and operations,

Downtime costs are a part of operating expenditure (OPEX) subject to lawsuit or penalty costs that result of any incident. The legal punishment can avoid by PPM approach or called insurance investment, that help reduce TCO in long-term operations. TCO consists of the sum total of operational and capital expenses involved in erecting and maintaining a data center. PPM approaches is not just only protecting downtime costs but also preventing reputation costs of the company that

modern maintenance strategies, and experiencing data center's operators.

*Operations Management - Emerging Trend in the Digital Era*

The traditional approach to avoid a downtime is applying the action plan through time-based maintenance (TBM). This means that the maintenance team plan for maintenance or upgrade systems by monitoring and controlling up on the schedule time of weeks, months, or annually based on the supplier's recommend. Moreover, TBM approach prevents the system downtime by following these maintenance schedules; regular inspection, easy to deployment, no condition monitoring

needed; decision-maker control (maintenance age or MTBF) maintenance

performed when the device reaches MTBF. On the other hand, the condition-based maintenance (CBM) strategic approach relies on an online/offline data collection and continuous measurable condition of devices or systems entirely during they are executing. By applying sensor devices and tools, gathering information that can perform to establish database system for trend analysis, gathering information prediction, and estimated remaining useful lifetime (RUL) of a device or system. The CBM takes action when reaches over the condition of the measurable point that system performance is directly degrading or most likely failure. A prognostic approach of online performance monitoring needs for the throughout degrading processes, from the outset of the system design, installation, operations, and until system failure. This difference approach from scheduled intervals recommends

Since 21st century, the technological advancement, data-driven approach to PDS is predictable and precise. For this reason, many of these data center outages can avoid or mitigate with the properly maintenance approaches and deploying sensing technologies. Predictive maintenance is the complementary of preventive maintenance. Predictive maintenance imposes on the device working condition and track-

Preventive maintenance implies to regular maintenance or TBM that maintains devices and systems up and operating as normal condition, prevent any unplanned

ing operating environment before system breakdown happens. With online condition monitoring system, the predictive maintenance takes action when the deterioration level M reached. (Decision variable: M/threshold deterioration level). In this research, researcher proposes the preventive and predictive maintenance (PPM) which determines the CBM as systematic strategy of data center operations and maintenance. Use case examples of PDS of data center had examined to ensure their proper functionality and to reduce their deterioration rate. PPM approach can insure devices, sub-systems and systems operating safety, operate as their functional reliability and efficiency, reduce failure rates, and prevent unscheduled

may not be estimated.

with preventive maintenance.

downtimes.

**36**

**2. Background**

**2.1 Preventive and predictive maintenance**

The CBM imposes as the predictive maintenance strategy, which executes device or system maintenance based on setting up conditions, performance, parameter monitoring and the subsequent actions before device or system failures happened. The CBM is a maintenance pattern that advises for maintenance decisions refer to the data and information collecting from condition monitoring system processes. During operating condition, CBM is executing as monitoring appliance through sensing device, which can gauge parameter based on various monitoring attribute s, for example temperature, humidity, vibration, noise levels, contaminants, CO2 and CO scale, and lubricating oil concentration. The usefulness of CBM is the application of the condition monitoring process, where the signals and data are online monitoring by applying many types of sensors inform of wire and wireless technologies. The core of CBM is executing in a real-time assessment of devices and systems conditions in order to analyze all data to perform the decision analysis for maintenance conditions and solutions, while reduces an planned or unplanned

**Figure 1.** *Total maintenance related costs.*

downtime, eliminates unnecessary maintenance, and cuts related costs. Thereby, maintenance activities require only when they need after the decision analysis for maintenance conditions such as repairs or replacements before the failure [3].

for downtime inspections. The process and routine of inspection defines as difference in the length of time manner, therefore it creates the utility of the P-F Interval. The evasion of off-line inspections, which frequently cause of data center downtime and ruin reputation, can apply CBM methods for economically feasibility. The most

• Process Parameter Trending (e.g., flows, rates, pressures, temperatures, etc.)

Data center reliability is reinforced by creating redundant topology to each system such as utility supplies, backup power supplies (generators and UPSs), fiber optic communication connections, networking connectivity, environmental controls, and security devices. The report from Emerson [7], as presented in **Figure 3**, is described some critical devices that related to system failure. The racking top 3

The prognostics method, the condition monitoring process can be performed either continuously or periodically. Sensing devices and data collection systems may be required for continuous monitoring through DCIM [8, 9]. Graphically, how the prognostics method performs is demonstrated in **Figure 4**. The deterioration trend of the device condition is represented via the horizontal and vertical axes, which present the operating times, trend monitoring, condition levels, and forecast point

• Process Control Instrumentation (measurement and trending)

incidents are UPS battery, over capacity of UPS, and human error.

usually applied techniques of CBM monitoring are:

*Condition-Based Maintenance for Data Center Operations Management*

• Acoustic Emissions Detection (e.g., ultrasound)

• Vibration Measurement and Analysis

• Visual Inspection (look, listen and feel).

*Root causes and failure analysis inside data center operations.*

• Lubricant Sampling and Analysis

*DOI: http://dx.doi.org/10.5772/intechopen.93945*

• Corrosion Monitoring

• Motor Current Analysis

• IR Thermography

**2.3 Data center reliability**

**Figure 3.**

**39**

There are various techniques and technology to implement for data collecting, processing, diagnostics, and prognostics for performing CBM through the system performance operations. Lee (1998) [4] describes CBM strategic approach into three scenarios: data-driven, model-based, and knowledge-based.

First, the data-driven scenario has applied historical and statistical data to comprehend a numerical model of systematic determinants such as mean time between failure (MTBF), mean time to repair (MTTR), and maximum tolerable period of disruption (MTPD) [5]. However, this scenario has depended on the accuracy of sensing devices, operational data, data interpretation, and perceived condition of stressful situation.

Second, model-based scenario has deployed an analytical algorithm such as simulation modeling to demonstrate the system reliability, system degradation, and system efficiency. Mostly, this m0del-based need high-level application software for simulated models such as MATLAB or reliability block diagram (RBD).

Last, knowledge-based scenario has depended on human experience by applying from the past real case based analysis or deriving data from the past project information related to data collecting, gathering, analyzing, decision, and execution. Moreover, they are systematic approach of engineering knowledge and maintenance attention to system facilities to guarantee their proper functions and to reduce their deterioration rate. Sometime knowledge-based can be perform through machine learning or AI in the future.

CBM approaches provisioning load or trend profile the earliest probable prediction of device or system failure, with optimal advantage by reduced maintenance time, labor and inventory costs, eliminated downtime, increased device or system life, and cut capital expenditures. The P-F Curve in **Figure 2** depicts the performance condition of device or system, which declines overtime series, this condition leads to functional failure or potential failure. The CBM system is an on-line monitoring, controlling, and inspecting that prepare the greatest P-F Intervals, which are scarcely interrupting than traditional TBM. This helps inspector for a planning

**Figure 2.** *Optimization the P-F interval under CBM method [6].*
