Welcome!

Python Authors: Pat Romanski, Matt Davis, AppDynamics Blog, Donald Meyer, Liz McMillan

News Feed Item

Fujitsu Develops World's First Stream Aggregation Technology to Rapidly Process Both Historical Data and Incoming Data

Kawasaki, Japan, Nov 19, 2012 - (JCN Newswire) - Fujitsu Laboratories Limited announced development of the world's first stream aggregation technology able to rapidly process both stored historical data and incoming streams of new data in a big data context.

The nature of big data requires that enormous volumes of data be processed at a high speed. When data is aggregated, longer aggregation times result in larger data volumes to be processed. This means computation times lengthen, which causes frequent updating operations to become more difficult. This is why improving the frequency of updates when aggregation times are lengthened has so far been challenging. Fujitsu Laboratories has therefore developed a technology that returns computation results quickly and manages snapshot operations, without re-doing computations or re-reading a variety of data types that change over time. As a result, even with high-frequency updating and long aggregation times, data can be processed 100 times faster than before.

This technology promises to improve both large volumes of batch processing and the processing of streaming data. Furthermore, in meteorology, it is now possible to show concentrated downpours in specific areas. As well as the utility gained for future weather forecasting, it may also have uses in new fields that demand the ability to process longitudinal data in real time.

Details of this technology will be announced at a special workshop lecture of the Special Interest Group on Software Interprise Modeling (SWIM) of the Institute of Electronics, Information and Communication Engineers (IEICE) held on Friday, November 30, at the Takanawa campus of Tokai University in Japan.

Background

Many companies are interested in using advanced ICT technology to improve their competitive position by rapidly processing large volumes of data. Some uses are large-scale batch processes performed periodically on transaction data, or processing streaming data in real time based on changing stock prices.

In the data processing of such activities, aggregating computations is essential. In large-volume batch processing, however, there are differences in the aggregation times and update frequency. Typically, large-volume batch processes that emphasize throughput operate on aggregation times lasting weeks or months. Streaming data processes emphasize response, on the other hand, and are in units of seconds or minutes. Update times roughly correspond with these.

Technological Challenges

The emphasis on batch processes and streaming processes is different, and therefore the process needs to be adapted according to application.

1. Large-volume batch processing technology

Large-volume batch processing handles large volumes of historical data, so each round of processing re-reads all data, which creates long delays before results are ready.

2. Conventional stream processing technology

The constant flow of data is held in a buffer - known as a window - and therefore each round of processing does not need to re-read any earlier data. Depending on the type of computation, however, the process does need access to all the data in that window in order to obtain computation results. For this reason, the duration of one round of computations will be proportionate to the window length, which diminishes responsiveness.

When using both historical (stored) and current (realtime streaming) data, with conventional processing methods, it has been difficult to simultaneously lengthen the aggregation intervals and raise the frequency of updates for the reasons outlined above.

Newly Developed Technology

Fujitsu Laboratories has developed a fast stream aggregation technology for long aggregation intervals and frequent updates, based on a combination of the two technologies described below.

1. Rapid pattern matching technology:

This is a technology that efficiently and directly picks out relevant items from an incoming stream of data. The conventional technique begins by analyzing the structure of input data and temporarily accumulating all input data in the memory. Next, it performs an extraction process of the items needed for aggregation to extract data. Structural analysis and item extraction is necessarily a two-step process. This technology is different in that it specifies the positions where items to be extracted will appear based on pattern matching, skipping over unneeded items thereby speeding up the process. Also, because pattern-matching is flexible, as well as using it with fixed-format data (such as CSV data) that conventional techniques use, it can work with other forms of data having recursive or hierarchical structures (such as XML data).

2. Snapshot operation management technology:

This is a technology that quickly returns computation results to deal with a variety of data types that change over time, without re-reading or re-computing data. The conventional technique is to store in memory an incoming stream of data following its time sequence. This technology stores the data even as it performs required computations, such as sorting according to a predefined order. It is always managed based on its computed state (snapshot operation), and therefore never needs to redo computations that involve all the data, including not only sums and averages but also minima, maxima, and medians. This lets it quickly pick out computation results.

Results

The response time for aggregation results when using a window length of 500,000 records was shown to be roughly 100 times faster than the commonly used open-source Complex Event Processing engine. It was also demonstrated that response time does not depend on window length (Figure 3).

This technology is expected to have applications with regard to the utilization of high-precision sensor data. Fujitsu Laboratories conducted verification of the technology using rainfall data generated by XRAIN(1), a project conducted by the Water and Disaster Management Bureau of the Ministry of Land, Infrastructure, Transport and Tourism. In the case of aggregating rainfall volume data collected over several hours from 500,000 locations in the Kansai region of western Japan, every several minutes a window of approximately 100 million records needs to be processed. The test conducted by Fujitsu Laboratories confirmed the technology's ability to execute data aggregation within intervals and no variation in aggregation times, and that the smooth movement of the rainfall area could be replicated, even for such a wide range of data. More than a sudden downpour, the actual volume of rainfall is what is strongly associated with disasters, and now, areas that require vigilance due to concentrated downpours can be readily verified.

Moreover, applications are anticipated for existing batch processing and stream processing. By enhancing the real-time aggregation of sales data, for example, it becomes possible to further strengthen production and inventory management.

Future Plans

Fujitsu plans to incorporate the new technology into its Big Data Platform and Big Data Middleware in fiscal 2013.

(1) Rainfall data generated by XRAIN:Rainfall data generated by the X-band MP Radar Rainfall Data, or XRAIN project, conducted by the Ministry of Land, Infrastructure, Transport and Tourism. XRAIN seeks to maintain extremely localized weather data, capturing rainfall data every 250 meters at one-minute intervals over a wide area.

About Fujitsu Laboratories

Founded in 1968 as a wholly owned subsidiary of Fujitsu Limited, Fujitsu Laboratories Limited is one of the premier research centers in the world. With a global network of laboratories in Japan, China, the United States and Europe, the organization conducts a wide range of basic and applied research in the areas of Next-generation Services, Computer Servers, Networks, Electronic Devices and Advanced Materials. For more information, please see: http://jp.fujitsu.com/labs/en.

About Fujitsu Limited

Fujitsu is the leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions and services. Over 170,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (TSE:6702) reported consolidated revenues of 4.5 trillion yen (US$54 billion) for the fiscal year ended March 31, 2012. For more information, please see www.fujitsu.com.



Source: Fujitsu Limited

Contact:
Fujitsu Limited
Public and Investor Relations
www.fujitsu.com/global/news/contacts/
+81-3-3215-5259

Technical Contacts

Fujitsu Laboratories Ltd.
Software Systems Laboratories
Intelligent Technology Lab
E-mail: [email protected]


Copyright 2012 JCN Newswire. All rights reserved. www.japancorp.net

More Stories By JCN Newswire

Copyright 2008 JCN Newswire. All rights reserved. Republication or redistribution of JCN Newswire content is expressly prohibited without the prior written consent of JCN Newswire. JCN Newswire shall not be liable for any errors or delays in the content, or for any actions taken in reliance thereon.

IoT & Smart Cities Stories
The deluge of IoT sensor data collected from connected devices and the powerful AI required to make that data actionable are giving rise to a hybrid ecosystem in which cloud, on-prem and edge processes become interweaved. Attendees will learn how emerging composable infrastructure solutions deliver the adaptive architecture needed to manage this new data reality. Machine learning algorithms can better anticipate data storms and automate resources to support surges, including fully scalable GPU-c...
Machine learning has taken residence at our cities' cores and now we can finally have "smart cities." Cities are a collection of buildings made to provide the structure and safety necessary for people to function, create and survive. Buildings are a pool of ever-changing performance data from large automated systems such as heating and cooling to the people that live and work within them. Through machine learning, buildings can optimize performance, reduce costs, and improve occupant comfort by ...
The explosion of new web/cloud/IoT-based applications and the data they generate are transforming our world right before our eyes. In this rush to adopt these new technologies, organizations are often ignoring fundamental questions concerning who owns the data and failing to ask for permission to conduct invasive surveillance of their customers. Organizations that are not transparent about how their systems gather data telemetry without offering shared data ownership risk product rejection, regu...
René Bostic is the Technical VP of the IBM Cloud Unit in North America. Enjoying her career with IBM during the modern millennial technological era, she is an expert in cloud computing, DevOps and emerging cloud technologies such as Blockchain. Her strengths and core competencies include a proven record of accomplishments in consensus building at all levels to assess, plan, and implement enterprise and cloud computing solutions. René is a member of the Society of Women Engineers (SWE) and a m...
Poor data quality and analytics drive down business value. In fact, Gartner estimated that the average financial impact of poor data quality on organizations is $9.7 million per year. But bad data is much more than a cost center. By eroding trust in information, analytics and the business decisions based on these, it is a serious impediment to digital transformation.
Digital Transformation: Preparing Cloud & IoT Security for the Age of Artificial Intelligence. As automation and artificial intelligence (AI) power solution development and delivery, many businesses need to build backend cloud capabilities. Well-poised organizations, marketing smart devices with AI and BlockChain capabilities prepare to refine compliance and regulatory capabilities in 2018. Volumes of health, financial, technical and privacy data, along with tightening compliance requirements by...
Predicting the future has never been more challenging - not because of the lack of data but because of the flood of ungoverned and risk laden information. Microsoft states that 2.5 exabytes of data are created every day. Expectations and reliance on data are being pushed to the limits, as demands around hybrid options continue to grow.
Digital Transformation and Disruption, Amazon Style - What You Can Learn. Chris Kocher is a co-founder of Grey Heron, a management and strategic marketing consulting firm. He has 25+ years in both strategic and hands-on operating experience helping executives and investors build revenues and shareholder value. He has consulted with over 130 companies on innovating with new business models, product strategies and monetization. Chris has held management positions at HP and Symantec in addition to ...
Enterprises have taken advantage of IoT to achieve important revenue and cost advantages. What is less apparent is how incumbent enterprises operating at scale have, following success with IoT, built analytic, operations management and software development capabilities - ranging from autonomous vehicles to manageable robotics installations. They have embraced these capabilities as if they were Silicon Valley startups.
As IoT continues to increase momentum, so does the associated risk. Secure Device Lifecycle Management (DLM) is ranked as one of the most important technology areas of IoT. Driving this trend is the realization that secure support for IoT devices provides companies the ability to deliver high-quality, reliable, secure offerings faster, create new revenue streams, and reduce support costs, all while building a competitive advantage in their markets. In this session, we will use customer use cases...