Sustainable operation and management of data center chillers using temporal data mining

Patnaik, Debprakash; Marwah, Manish; Sharma, Ratnesh; Ramakrishnan, Naren

doi:10.1145/1557019.1557159

Cited by 51 publications

(45 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sequence analysis techniques, such as motif mining, were used by Patnaik et al [39] to enhance the performance of cooling infrastructure. In this same line, Shao et al [40] extracted temporal episodic relationships to better compare systematic consumption trends in residential and commercial buildings with different electrical infrastructure.…”

Section: Analysis Of Infrastructures and Retrofittingmentioning

confidence: 99%

Data science for building energy management: A review

Molina-Solana

Ros

Ruiz

et al. 2017

Renewable and Sustainable Energy Reviews

204

105

View full text Add to dashboard Cite

The energy consumption of residential and commercial buildings has risen steadily in recent years, an increase largely due to their HVAC systems. Expected energy loads, transportation, and storage as well as user behavior influence the quantity and quality of the energy consumed daily in buildings. However, technology is now available that can accurately monitor, collect, and store the huge amount of data involved in this process. Furthermore, this technology is capable of analyzing and exploiting such data in meaningful ways. Not surprisingly, the use of data science techniques to increase energy efficiency is currently attracting a great deal of attention and interest. This paper reviews how Data Science has been applied to address the most difficult problems faced by practitioners in the field of Energy Management, especially in the building sector. The work also discusses the challenges and opportunities that will arise with the advent of fully connected devices and new computational technologies.

show abstract

Section: Analysis Of Infrastructures and Retrofittingmentioning

confidence: 99%

Data science for building energy management: A review

Molina-Solana

Ros

Ruiz

et al. 2017

Renewable and Sustainable Energy Reviews

204

105

View full text Add to dashboard Cite

show abstract

“…Motif discovery is used to reveal trends, relationships, and anomalies, and assist users in hypothesis evaluation and knowledge discovery. Efficient algorithms for detecting motifs in time series data [4] have been used in many applications, such as identifying words in different languages, detecting anomalies in patients' medical records over time [5], and chiller efficiency in data centers [14]. Frequently occurring patterns in the time series also known as motifs, which are represented by rectangles of different sizes.…”

Section: Motivationmentioning

confidence: 99%

“…Each motif is specified in terms of its starting and ending times. Motifs can be of varying lengths, with many shorter motifs nested within longer motifs, as a consequence of the level-wise motif mining algorithm [14]. Motifs are colored according to how efficiently the chiller ensemble performs within the motif.…”

Section: Motivationmentioning

confidence: 99%

Visual exploration of frequent patterns in multivariate time series

Hao

Marwah

Janetzko

et al. 2012

Information Visualization

View full text Add to dashboard Cite

The detection of frequently occurring patterns, also called motifs, in data streams has been recognized as an important task. To find these motifs, we use an advanced event encoding and pattern discovery algorithm. Since a large time series can contain hundreds of motifs, there is a need to support interactive analysis and exploration. In addition, for certain applications, such as data center resource management, service managers want to be able to predict the next day's power consumption from the previous months' data. For this purpose, we introduce four novel visual analytics methods: (1) motif layout, using colored rectangles for visualizing the occurrences and hierarchical relationships of motifs; (2) motif distortion, enlarging or shrinking motifs for visualizing them more clearly; (3) motif merging, combining a number of identical adjacent motif instances to simplify the display; and (4) pattern preserving prediction, using a pattern preserving smoothing and prediction algorithm to provide a reliable prediction for seasonal data. We have applied these methods to three real-world data sets: data center chilling utilization, oil well production, and system resource utilization. The results enable service managers to interactively examine motifs and gain new insights into the recurring patterns to analyze system operations. Using the above methods, we have also predicted both power consumption and server utilization in data centers with a 70-80% accuracy.

show abstract

“…For example, [85] recently investigated a motifbased algorithm for controlling the performance of data center chillers, and reported "switching from motif 8 to motif 5 gives us a nearly $40,000 in annual savings!". Motif discovery is a core subroutine in many research projects on activity discovery [42][67], with applications in elder care [105], surveillance and sports training.…”

Section: Time Series Motifmentioning

confidence: 99%

Exact Primitives for Time Series Data Mining

Mueen

2012

Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Sustainable operation and management of data center chillers using temporal data mining

Cited by 51 publications

References 18 publications

Data science for building energy management: A review

Data science for building energy management: A review

Visual exploration of frequent patterns in multivariate time series

Exact Primitives for Time Series Data Mining

Contact Info

Product

Resources

About