Welcome!

Open Source Cloud Authors: Pat Romanski, Carmen Gonzalez, Elizabeth White, Jnan Dash, 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.

@ThingsExpo Stories
In his keynote at 18th Cloud Expo, Andrew Keys, Co-Founder of ConsenSys Enterprise, provided an overview of the evolution of the Internet and the Database and the future of their combination – the Blockchain. Andrew Keys is Co-Founder of ConsenSys Enterprise. He comes to ConsenSys Enterprise with capital markets, technology and entrepreneurial experience. Previously, he worked for UBS investment bank in equities analysis. Later, he was responsible for the creation and distribution of life sett...
20th Cloud Expo, taking place June 6-8, 2017, at the Javits Center in New York City, NY, will feature technical sessions from a rock star conference faculty and the leading industry players in the world. Cloud computing is now being embraced by a majority of enterprises of all sizes. Yesterday's debate about public vs. private has transformed into the reality of hybrid cloud: a recent survey shows that 74% of enterprises have a hybrid cloud strategy.
Whether your IoT service is connecting cars, homes, appliances, wearable, cameras or other devices, one question hangs in the balance – how do you actually make money from this service? The ability to turn your IoT service into profit requires the ability to create a monetization strategy that is flexible, scalable and working for you in real-time. It must be a transparent, smoothly implemented strategy that all stakeholders – from customers to the board – will be able to understand and comprehe...
An IoT product’s log files speak volumes about what’s happening with your products in the field, pinpointing current and potential issues, and enabling you to predict failures and save millions of dollars in inventory. But until recently, no one knew how to listen. In his session at @ThingsExpo, Dan Gettens, Chief Research Officer at OnProcess, discussed recent research by Massachusetts Institute of Technology and OnProcess Technology, where MIT created a new, breakthrough analytics model for ...
DevOps is being widely accepted (if not fully adopted) as essential in enterprise IT. But as Enterprise DevOps gains maturity, expands scope, and increases velocity, the need for data-driven decisions across teams becomes more acute. DevOps teams in any modern business must wrangle the ‘digital exhaust’ from the delivery toolchain, "pervasive" and "cognitive" computing, APIs and services, mobile devices and applications, the Internet of Things, and now even blockchain. In this power panel at @...
More and more brands have jumped on the IoT bandwagon. We have an excess of wearables – activity trackers, smartwatches, smart glasses and sneakers, and more that track seemingly endless datapoints. However, most consumers have no idea what “IoT” means. Creating more wearables that track data shouldn't be the aim of brands; delivering meaningful, tangible relevance to their users should be. We're in a period in which the IoT pendulum is still swinging. Initially, it swung toward "smart for smar...
With major technology companies and startups seriously embracing IoT strategies, now is the perfect time to attend @ThingsExpo 2016 in New York. Learn what is going on, contribute to the discussions, and ensure that your enterprise is as "IoT-Ready" as it can be! Internet of @ThingsExpo, taking place June 6-8, 2017, at the Javits Center in New York City, New York, is co-located with 20th Cloud Expo and will feature technical sessions from a rock star conference faculty and the leading industry p...
"We build IoT infrastructure products - when you have to integrate different devices, different systems and cloud you have to build an application to do that but we eliminate the need to build an application. Our products can integrate any device, any system, any cloud regardless of protocol," explained Peter Jung, Chief Product Officer at Pulzze Systems, in this SYS-CON.tv interview at @ThingsExpo, held November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA.
Internet of @ThingsExpo has announced today that Chris Matthieu has been named tech chair of Internet of @ThingsExpo 2017 New York The 7th Internet of @ThingsExpo will take place on June 6-8, 2017, at the Javits Center in New York City, New York. Chris Matthieu is the co-founder and CTO of Octoblu, a revolutionary real-time IoT platform recently acquired by Citrix. Octoblu connects things, systems, people and clouds to a global mesh network allowing users to automate and control design flo...
In addition to all the benefits, IoT is also bringing new kind of customer experience challenges - cars that unlock themselves, thermostats turning houses into saunas and baby video monitors broadcasting over the internet. This list can only increase because while IoT services should be intuitive and simple to use, the delivery ecosystem is a myriad of potential problems as IoT explodes complexity. So finding a performance issue is like finding the proverbial needle in the haystack.
Data is the fuel that drives the machine learning algorithmic engines and ultimately provides the business value. In his session at 20th Cloud Expo, Ed Featherston, director/senior enterprise architect at Collaborative Consulting, will discuss the key considerations around quality, volume, timeliness, and pedigree that must be dealt with in order to properly fuel that engine.
According to Forrester Research, every business will become either a digital predator or digital prey by 2020. To avoid demise, organizations must rapidly create new sources of value in their end-to-end customer experiences. True digital predators also must break down information and process silos and extend digital transformation initiatives to empower employees with the digital resources needed to win, serve, and retain customers.
The WebRTC Summit New York, to be held June 6-8, 2017, at the Javits Center in New York City, NY, announces that its Call for Papers is now open. Topics include all aspects of improving IT delivery by eliminating waste through automated business models leveraging cloud technologies. WebRTC Summit is co-located with 20th International Cloud Expo and @ThingsExpo. WebRTC is the future of browser-to-browser communications, and continues to make inroads into the traditional, difficult, plug-in web co...
In his general session at 19th Cloud Expo, Manish Dixit, VP of Product and Engineering at Dice, discussed how Dice leverages data insights and tools to help both tech professionals and recruiters better understand how skills relate to each other and which skills are in high demand using interactive visualizations and salary indicator tools to maximize earning potential. Manish Dixit is VP of Product and Engineering at Dice. As the leader of the Product, Engineering and Data Sciences team at D...
The Internet of Things (IoT) promises to simplify and streamline our lives by automating routine tasks that distract us from our goals. This promise is based on the ubiquitous deployment of smart, connected devices that link everything from industrial control systems to automobiles to refrigerators. Unfortunately, comparatively few of the devices currently deployed have been developed with an eye toward security, and as the DDoS attacks of late October 2016 have demonstrated, this oversight can ...
What happens when the different parts of a vehicle become smarter than the vehicle itself? As we move toward the era of smart everything, hundreds of entities in a vehicle that communicate with each other, the vehicle and external systems create a need for identity orchestration so that all entities work as a conglomerate. Much like an orchestra without a conductor, without the ability to secure, control, and connect the link between a vehicle’s head unit, devices, and systems and to manage the ...
"Once customers get a year into their IoT deployments, they start to realize that they may have been shortsighted in the ways they built out their deployment and the key thing I see a lot of people looking at is - how can I take equipment data, pull it back in an IoT solution and show it in a dashboard," stated Dave McCarthy, Director of Products at Bsquare Corporation, in this SYS-CON.tv interview at @ThingsExpo, held November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA.
Unsecured IoT devices were used to launch crippling DDOS attacks in October 2016, targeting services such as Twitter, Spotify, and GitHub. Subsequent testimony to Congress about potential attacks on office buildings, schools, and hospitals raised the possibility for the IoT to harm and even kill people. What should be done? Does the government need to intervene? This panel at @ThingExpo New York brings together leading IoT and security experts to discuss this very serious topic.
We are always online. We access our data, our finances, work, and various services on the Internet. But we live in a congested world of information in which the roads were built two decades ago. The quest for better, faster Internet routing has been around for a decade, but nobody solved this problem. We’ve seen band-aid approaches like CDNs that attack a niche's slice of static content part of the Internet, but that’s it. It does not address the dynamic services-based Internet of today. It does...
Data is the fuel that drives the machine learning algorithmic engines and ultimately provides the business value. In his session at Cloud Expo, Ed Featherston, a director and senior enterprise architect at Collaborative Consulting, discussed the key considerations around quality, volume, timeliness, and pedigree that must be dealt with in order to properly fuel that engine.