Big Data and Intel® Intelligent Systems Solution for Intelligent transportation


Published on

Explications sur comment il est possible d'utiliser la puissance d'Hadoop pour analyser les vidéos des caméras présentent sur les réseaux routiers avec pour objectif d'identifier l'état du trafic, le type de véhicule en déplacement et même l'usurpation de plaques d'immatriculation.

Published in: Technology, Business
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Big Data and Intel® Intelligent Systems Solution for Intelligent transportation

  1. 1. Big Data and Intel® IntelligentSystems Solution for IntelligentTransportationXiao Dong Wang, Manager, Big Data Solution Team, IntelRobin Wang, Platform Solution Architect, IntelAlbert Hu, Solution Architect, IntelEMBS001
  2. 2. Agenda • Intelligent Transportation System (ITS) landscape in China • Blueprint for ITS • Big Data overview and benefit for ITS • Intel® Architecture based products for Big Data on ITS • ITS case study in China The PDF for this Session presentation is available from our Technical Session Catalog at the end of the day at: URL is on top of Session Agenda Pages in Pocket Guide2
  3. 3. Agenda • Intelligent Transportation System (ITS) landscape in China • Blueprint for ITS • Big Data overview and benefit for ITS • Intel® Architecture based products for Big Data on ITS • ITS case study in China3
  4. 4. China Environment “Sensing China” (IoT) strategy -- China Premier Wen Jiabao, ‘09 Government Objective • Government 12-5Y Plan/Social Harmony • Determine to lead in Internet of Things (IoT) ‒ Setting international standards for new technology ‒ $0.8Bn government funds Mega Trend Challenges & Government approach “The biggest development potential lies in the process of urbanization.” • Urbanization -- China New Premier Li Keqiang, ‘12 ‒ 690Mn now to 900Mn by ‘25 • IoT/Smart City is one way to solve the challenges ‒ IoT market size $80~120Bn by ‘15 ‒ 90+ smart cities plans underway ‒ Gaps: Core technology, standards, immature ecosystem, deployment model4
  5. 5. PRC Transportation Infrastructure Landscape 1 22011 Investment (Bn RMB) 1600 1400 Highway 1200 4,500,000km 1000 Total Number of Vehicles will exceed 800 200 Million by 2020 600 400 Railway 200 Waterway 120,000km 126,000km Urban Public 0 394,000km -200 -2% 0% 2% 4% 6% 8% 10% 2011-2015 CAGR (in terms of length) Infrastructure build-out trending to be stabilized. Key challenges due to large scale of the infrastructure network, growing number of vehicles, yet still higher traveler, vehicle/infrastructure density: Safety, Infrastructure/Traveler’s efficiency, Environment. 1 Source: China Ministry of Transportation’s 12th 5 year plan 2 Source: ISH* Research Report5
  6. 6. Big Data Source From Transportation Worldwide Enterprise and IP Storage used 0.3PB ~ 6.7PB/Day Video Data for Video Surveillance by End User (2016) generated for Smart City Environment Banking & Finance 2016 Casinos & Gaming 2% 3% City Surveillance 13% Commercial Education 37% 7% 3% Government 7% Industrial, Manufacturing, & Utilities Retail How to effectively 21% Transport 3% collect, aggregate, 4% Other manage and analyze data Source: IMS Enterprise and IP Storage used for Video Surveillance – World-2012 to help Intelligent Transportation System (ITS) application?6
  7. 7. Agenda • Intelligent Transportation System (ITS) landscape in China • Blueprint for ITS • Big Data overview and benefit for ITS • Intel® Architecture based products for Big Data on ITS • ITS case study in China7
  8. 8. Goals of Intelligent Transportation System • Traffic Management – Enforcing traffic regulations – Transportation planning support – Adaptive traffic control – Case investigation for police • Traveler information system – Real-time road condition  Speed & congestion  Historical camera images & statistics – Travel time information  Available to various terminals  Proactive travel plan • Commercial vehicle systems – Commercial vehicle management, tracking, administration • Public security – Video surveillance (remote video streaming & video searching)8
  9. 9. Intelligent Transportation System (ITS) End-to-End Solution NVR/DVR/ Hybrid NVR Decoder Collect, store, Data Center Edge transform, analyze Morphology Edge Video Server • Embedded Analytic and mine • Cloud service • Proprietary • High-performance Data Center Solutions Distributed Filesystem – HDFS* Terminal Device Abundant data visualization Distributed data analysis – Hadoop* Data analysis and cache Distributed real-time database – HBase*9
  10. 10. Intelligent Transportation System (ITS) Cross Region Deployment10
  11. 11. Agenda • Intelligent Transportation System (ITS) landscape in China • Blueprint for ITS • Big Data overview and benefit for ITS • Intel® Architecture based products for Big Data on ITS • ITS case study in China11
  12. 12. Scale Up or Scale Out Intelligent Transportation System (ITS) Data Burst Relational Database Distributional Database shift left shift right12
  13. 13. Intelligent Transportation System (ITS) Software Architecture MapReduce Online/Interactive Data Mining Offline analysis Applications HBase* Distributed Database for texts & images Sqoop* Data RDB Integration Aggregated results Legacy Applications13
  14. 14. Big Data Intel® Distribution for Apache Hadoop* Software Optimized Software Stack • Stable, enterprise-ready Hadoop* • Optimized for Intel® Architecture • Bring “Real-time” analysis to Hadoop by HBase* • Enhanced features to Hadoop for vertical enhancements segments Intel® Manager for Apache Hadoop Software 2.3 Deployment, Configuration, Monitoring, Alerting and Security Mahout* 0.7 R - statistics Hive* 0.9.0 Pig* 0.9.2 Oozie* 3.3.0 Sqoop* 1.4.1 RDB Data Collector Data Mining Data Manipulation Data Warehouse Data Manipulation Workflow Scheduler ZooKeeper* 3.4.5 MapReduce 1.0.3 Distributed Processing Framework Coordination HBase 0.94.1 Flume* 1.3.0 Log Data Collector Real-time Distributed Big Table HDFS* 1.0.3 Hadoop Distributed File System14
  15. 15. Intel® Distribution for Apache Hadoop* Software Enhancements for Intelligent Transportation System Enhancement Benefit for ITS Cross-site Big Table for HBase* • Data are stored in different region data center with a global virtual view • Each data center is the live backup to provide data access high availability SQL Layer on top of HBase • Real-time statistics on the big mount of traffic data • The interactive query and offline statistic share the same set of data Full-text indexing and near-real- • Provide the full text search capability on the time search for HBase structured data in distribution database system • Build in index make sure that the traffic data always synchronize with the index Efficiently Big Object Storage in • Increase the traffic image store performance HBase with the standard HBase interface R language statistics support to • Brings the mature R language library to the Hadoop* MapReduce, HDFS* and HBase • Reduce the effort to develop the complex data mining logic15
  16. 16. Agenda • Intelligent Transportation System (ITS) landscape in China • Blueprint for ITS • Big Data overview and benefit for ITS • Intel® Architecture based products for Big Data on ITS • ITS case study in China16
  17. 17. Value for Edge Analytics Video created Video analyzed Video Cold storage Video metadata stored Camera Video Storage (Edge or Private Cloud Public Cloud Centralized) Management Police System Car Video Edge Client Indexer/Analyzer/Transcoder Data Center/ Cloud Data Services (Video capture) (Image extraction & Metadata Creation) (Private/Public) (VSaaS, VAaaS) Smart Checkpoint District City  Province  PRC 1 Edge VA’s Value By end of 2017 By end of 2017 • Real-time intelligence (into metadata) 76 PB 457 PB raw video 1/6 of video data Metadata for traffic • Reduce the footage to be 1/8 ~ 1/12 Per Day generated per day of its original size • Resolve the bandwidth issue and People, cars, backend storage capacity constrain license plates 1 Source: Internal Team Analysis based on IHS* Research Report17
  18. 18. Enhanced NVR (Network Video Recorder) Key Features for Intelligent Transportation System (ITS) 闯红灯// Run the 车牌颜色识别 // Plate red light colour recognition 逆行 // 车身颜色识别 // Vehicle Retrogradation colour recognition 车牌识别 // Plate 交通拥堵 // Traffic jam Recognition 车流统计// Vehicle 行使缓慢 // Run slowly counting 禁停// No parking 行使超速 // Speeding 禁左禁右 // No turn 行人横穿//Jaywalk Crossing vehicle right or left capture 占道(不按规定车道行使) 车标识别//Auto logo recognition 变道 // Lane 机动车抓拍 // Change Abnormality quick shot 压线 // Line 超速 // Speeding crossing Vehicle features recognition18
  19. 19. Intel® Architecture Base NVR Intel® Xeon® Processor E3 * Family, Intel® C216 Chipset -Up to 32G DDR3 Memory -4 x 10M/100M/1000M Base-T LAN -16 x SATA3.0 or 24 x SATA3.0 -2 x MSATA; -3U or 4U rack-mounted Chassis 3rd Generation Intel® * Core™ Processor Family - 4 x 8G DDR3 Memory - 2 x 10M/100M/1000M Base-T LAN - 8 x SATA3.0 or 16 x SATA3.0 - 1 x MSATA - 2U or 3U rack-mounted Chassis Intel® Atom™ Processor D2550, Intel® NM10 Express Chipset - 1 x 4G DDR3 Memory * - 2 x 100M/1000M LAN - 8 x SATA3.0; - 1 x MSATA; - 2U rack-mounted Chassis19
  20. 20. Big Data Appliance Reference Intel® Server Board Design from Intel S2600GZ “Grizzly Pass” Intel® Server System R2000 “Big Horn Peak” HDFS* Data Node • Large Storage Capacity • Large Memory Capacity • Extreme Power Efficiency • Extreme FDR InfiniBand • Extensive I/O • Optional SSD or PCI Express* SSD InfiniBand* and Ethernet Switches Intel Server Board S2600JF “Jefferson Pass” Intel Server System H2000 “Bobcat Peak” HDFS Name Node • High Density Form Factor • High Memory Bandwidth • Extreme FDR InfiniBand • Optional SSD or PCI Express SSD Can be data node for compute-intensive Big Data applications20
  21. 21. Big Data Appliance Reference Design: Turnkey Platforms for ISV/SI/LOEM Easy to Use Quality • Easy to deploy • Integrated validation of all • Easy to scale-out components • Easy to manage • OS and device drivers • Rapid deployment in days • Big Data software packages • Quickly isolate root cause • BIOS, firmware, etc. between appliance and • Embedded acceptance test application • Disk health monitoring Power Efficiency Performance • Spread core design • 10GbE, InfiniBand* • Cold Redundant Power Supply • Advanced storage controller • Intelligent disk spin-up/off • SSD and PCI Express* SSD • ACPI* S3/S4 support • SW tuning: block size, # of • DCM integrated at rack reducers, etc. Big Data ISV/SI/LOEM all look forward to a total solution21
  22. 22. Big Data Appliances Reference Design from Intel® Performance & Power Advantages • 10GbE & InfiniBand* FDR 80 PLUS 230V Internal Certification Redundant • Network protocol advances % of Rated Load 20% 50% 100% • SSD, PCI Express* SSD, Hybrid 80 PLUS Bronze 81% 85% 81% 80 PLUS Silver 85% 89% 85% • Advanced storage controller 80 PLUS Gold 88% 92% 88% • Balance oriented optimization 80 PLUS Platinum 90% 94% 91% Low Power Technology Sources CRPS (5-10% up) Power Supply: 80 PLUS Platinum HW Power Supply: “cold” redundancy HW Utilization (%) Spread-core server board layout HW Normal ACPI S3 support HW-SW PSU ACPI S4 support HW-SW 1 module 2 modules Staggered disk spin up HW-FW works work Intelligent disk spin off control HW-SW Load (%) Data center, rack, and node level Threshold (40%) HW-FW-SW power monitoring and limiting Cold Redundancy Power Supply (CRPS)22
  23. 23. Agenda • Intelligent Transportation System (ITS) landscape in China • Blueprint for ITS • Big Data overview and benefit for ITS • Intel® Architecture based products for Big Data on ITS • ITS case study in China23
  24. 24. Case Study: Intelligent Monitoring and Recording System Traffic Flow Analysis Vehicle History Hive* Behavior Edge Video Analytic MapReduce (Enhanced NVR) ETL 3G HBase* Real-time Vehicle HDFS* License Analysis24
  25. 25. Case Study: Intelligent Transportation System (ITS) Solution Traffic Management • Real-time road conditions report • Over speed vehicles detection in road segment • Fake plate number detection Public Security • Tracking vehicle in real-time • Alerts and alarms based on blacklist Traveler Guide • Real-time road condition by getting latest camera images and traffic flow statistics • Travel time estimation for road segments in the city25
  26. 26. Case Study: Intelligent Transportation System (ITS) Result Illegal vehicle tracking efficiency 违法车辆追踪效率提升 Through the massive data real-time analysis function, the 通过海量数据实时分析处理功能能将违法车辆数据定位时间由小时 illegal vehicle location data time is by the hour Level 级缩减为分钟级甚至秒级 reduced to minutes or even seconds. Deaths in bad traffic accidents 恶性交通事故死亡人数减少 Through the floating vehicle monitoring system to collect vehicle 通过浮动车监控系统收集车辆信息并且实时分析,能够对事故高发车 information and real-time analysis to monitor high Service Vehicles 辆(如工程货车)进行行为监控,降低恶性事故率。 (such as engineering truck ) behavior and reduce the accident rate. Road congestion rate 道路拥堵率下降 通过路况监控设备收集路况信息并实时处理,能够精确绘制道路拥堵线 Through the traffic monitoring equipment to collect traffic information and real-time processing, the road congestion coil can be drawn 圈,提供交管部门快速处理突发事故,并提供给大众平台供驾驶员参考 accurately, emergency can be routed to traffic management 从而疏导车流 departments rapidly and traffic drivers can be diverted accordingly.26
  27. 27. Summary • Intelligent Transportation System (ITS) is Intel® global focus now and future • Intel®’s end-to-end analytics architecture fits ITS solution development • Intel® has rich resources to help developers for ITS related application development27
  28. 28. Additional Sources of Information: Other Sessions • EMBS002 ‒ Real Time Cloud Infrastructure and Virtualized Data Plane Design with Intel® Architecture: April 10, 14:30 in Room 307A • EMBL001 ‒ Hands-on Lab: Next Generation Firewall and Deep Packet Inspection on Intel® Platforms: April 10, 13:15 in Room 306A • EMBL001R ‒ Repeat of Hands-on Lab: Next Generation Firewall and Deep Packet Inspection on Intel® Platforms: April 10, 15:45 in Room 306A • EMBS003 ‒ Telecommunication Platforms: Streaming Media Processing on Intel® Architecture: April 11, 15:45 in Room 307A • EMBS004 ‒ Create Intelligent Retail Solutions that Deliver Engaging User Experiences: April 11, 15:00 in Room 307A Demos in the showcase ‒ Booth No.: E20 “Hikvision* demo” ‒ Booth No.: E40 “Intel® Server Solutions” More web based info: ‒ DSS web link: ‒ Server Edge: www.IntelServerEdge.com28
  29. 29. Legal DisclaimerINFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL® PRODUCTS. NO LICENSE, EXPRESS ORIMPLIED, BY ESTOPPEL OR OTHERWISE, TO ANY INTELLECTUAL PROPERTY RIGHTS IS GRANTED BY THIS DOCUMENT. EXCEPTAS PROVIDED IN INTELS TERMS AND CONDITIONS OF SALE FOR SUCH PRODUCTS, INTEL ASSUMES NO LIABILITY WHATSOEVERAND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY, RELATING TO SALE AND/OR USE OF INTEL PRODUCTS INCLUDINGLIABILITY OR WARRANTIES RELATING TO FITNESS FOR A PARTICULAR PURPOSE, MERCHANTABILITY, OR INFRINGEMENT OF ANYPATENT, COPYRIGHT OR OTHER INTELLECTUAL PROPERTY RIGHT.• A "Mission Critical Application" is any application in which failure of the Intel® Product could result, directly or indirectly, in personal injury or death. SHOULD YOU PURCHASE OR USE INTELS PRODUCTS FOR ANY SUCH MISSION CRITICAL APPLICATION, YOU SHALL INDEMNIFY AND HOLD INTEL AND ITS SUBSIDIARIES, SUBCONTRACTORS AND AFFILIATES, AND THE DIRECTORS, OFFICERS, AND EMPLOYEES OF EACH, HARMLESS AGAINST ALL CLAIMS COSTS, DAMAGES, AND EXPENSES AND REASONABLE ATTORNEYS FEES ARISING OUT OF, DIRECTLY OR INDIRECTLY, ANY CLAIM OF PRODUCT LIABILITY, PERSONAL INJURY, OR DEATH ARISING IN ANY WAY OUT OF SUCH MISSION CRITICAL APPLICATION, WHETHER OR NOT INTEL OR ITS SUBCONTRACTOR WAS NEGLIGENT IN THE DESIGN, MANUFACTURE, OR WARNING OF THE INTEL PRODUCT OR ANY OF ITS PARTS.• Intel may make changes to specifications and product descriptions at any time, without notice. Designers must not rely on the absence or characteristics of any features or instructions marked "reserved" or "undefined". Intel reserves these for future definition and shall have no responsibility whatsoever for conflicts or incompatibilities arising from future changes to them. The information here is subject to change without notice. Do not finalize a design with this information.• The products described in this document may contain design defects or errors known as errata which may cause the product to deviate from published specifications. Current characterized errata are available on request.• Intel® product plans in this presentation do not constitute Intel plan of record product roadmaps. Please contact your Intel representative to obtain Intels current plan of record product roadmaps.• Intel® processor numbers are not a measure of performance. Processor numbers differentiate features within each processor family, not across different processor families. Go to:• Contact your local Intel sales office or your distributor to obtain the latest specifications and before placing your product order.• Copies of documents which have an order number and are referenced in this document, or other Intel literature, may be obtained by calling 1-800-548-4725, or go to:• Grizzly Pass, Big Horn Peak, Jefferson Pass, Bobcat Peak and other code names featured are used internally within Intel to identify products that are in development and not yet publicly announced for release. Customers, licensees and other third parties are not authorized by Intel to use code names in advertising, promotion or marketing of any product or services and any such use of Intels internal code names is at the sole risk of the user• Intel, the Intel logo, Intel Atom, Intel Atom Inside, Intel Core, Core Inside, Intel Sponsors of Tomorrow., the Intel Sponsors of Tomorrow. logo, Xeon and Xeon Inside are trademarks of Intel Corporation in the United States and/or other countries.• *Other names and brands may be claimed as the property of others.• Copyright © 2013 Intel Corporation.29
  30. 30. Risk Factors The above statements and any others in this document that refer to plans and expectations for the first quarter, the year and the future are forward-looking statements that involve a number of risks and uncertainties. Words such as “anticipates,” “expects,” “intends,” “plans,” “believes,” “seeks,” “estimates,” “may,” “will,” “should” and their variations identify forward-looking statements. Statements that refer to or are based on projections, uncertain events or assumptions also identify forward-looking statements. Many factors could affect Intel’s actual results, and variances from Intel’s current expectations regarding such factors could cause actual results to differ materially from those expressed in these forward-looking statements. Intel presently considers the following to be the important factors that could cause actual results to differ materially from the company’s expectations. Demand could be different from Intels expectations due to factors including changes in business and economic conditions; customer acceptance of Intel’s and competitors’ products; supply constraints and other disruptions affecting customers; changes in customer order patterns including order cancellations; and changes in the level of inventory at customers. Uncertainty in global economic and financial conditions poses a risk that consumers and businesses may defer purchases in response to negative financial events, which could negatively affect product demand and other related matters. Intel operates in intensely competitive industries that are characterized by a high percentage of costs that are fixed or difficult to reduce in the short term and product demand that is highly variable and difficult to forecast. Revenue and the gross margin percentage are affected by the timing of Intel® product introductions and the demand for and market acceptance of Intels products; actions taken by Intels competitors, including product offerings and introductions, marketing programs and pricing pressures and Intel’s response to such actions; and Intel’s ability to respond quickly to technological developments and to incorporate new features into its products. The gross margin percentage could vary significantly from expectations based on capacity utilization; variations in inventory valuation, including variations related to the timing of qualifying products for sale; changes in revenue levels; segment product mix; the timing and execution of the manufacturing ramp and associated costs; start-up costs; excess or obsolete inventory; changes in unit costs; defects or disruptions in the supply of materials or resources; product manufacturing quality/yields; and impairments of long-lived assets, including manufacturing, assembly/test and intangible assets. Intels results could be affected by adverse economic, social, political and physical/infrastructure conditions in countries where Intel, its customers or its suppliers operate, including military conflict and other security risks, natural disasters, infrastructure disruptions, health concerns and fluctuations in currency exchange rates. Expenses, particularly certain marketing and compensation expenses, as well as restructuring and asset impairment charges, vary depending on the level of demand for Intels products and the level of revenue and profits. Intel’s results could be affected by the timing of closing of acquisitions and divestitures. Intel’s current chief executive officer plans to retire in May 2013 and the Board of Directors is working to choose a successor. The succession and transition process may have a direct and/or indirect effect on the business and operations of the company. In connection with the appointment of the new CEO, the company will seek to retain our executive management team (some of whom are being considered for the CEO position), and keep employees focused on achieving the company’s strategic goals and objectives. Intels results could be affected by adverse effects associated with product defects and errata (deviations from published specifications), and by litigation or regulatory matters involving intellectual property, stockholder, consumer, antitrust, disclosure and other issues, such as the litigation and regulatory matters described in Intels SEC reports. An unfavorable ruling could include monetary damages or an injunction prohibiting Intel from manufacturing or selling one or more products, precluding particular business practices, impacting Intel’s ability to design its products, or requiring other remedies such as compulsory licensing of intellectual property. A detailed discussion of these and other factors that could affect Intel’s results is included in Intel’s SEC filings, including the company’s most recent Form 10-Q, report on Form 10-K and earnings release. Rev. 1/17/1330
  31. 31. Backup31
  32. 32. Intelligent Transportation System (ITS) 200 benefits from Interactive Hive Query 159 150 100 million records 98 over a 8-node cluster 100 68 63 50 28 Hive* 0.9.0 (M/R) (sec) 18 0.2 0.2 Interactive Hive (sec) 0 Query 1 Query 2 Query 3 Query 4 User Scenario Query Calculate each day’s internet traffic of a specific SELECT sum(down+up) FROM cdr201209 WHERE user number = 13300000000 GROUP BY day; Get the 10 most heavily called numbers for a SELECT TOP(10) tonumber, sum(call_length) len FROM specific user cdr_201209 WHERE number = 13300032810 GROUP BY tonumber ORDER BY len DESC Get the top 1000 call length from all user phone SELECT TOP(1000) number, call_length FROM calls cdr_201209 ORDER BY call_length DESC Get the top 1000 users having highest total SELECT TOP(1000) number, sum(fee) f FROM monthly charge cdr_201209 GROUP BY number order by f DESC Intel® Distribution for Apache Hadoop*32 Software Enhancement
  33. 33. Intelligent Transportation System (ITS) benefits form Cross-site Big Table Two deployment models: 1. Global Table View 1. In transportation system, 2. Data are physically stored each district has a DC, one in geo-distributed data can connect to any DC and centers view all of the data 3. Higher availability 2. In banks, provincial branch Data Center 4. Better locality has its own DC. Central bank A can view all of the data, but 5. Distributed aggregation branches can not see each removes data transfer other. Virtual Big Table Data Center C Data Center B Async Replication Intel® Distribution for Apache Hadoop*33 Software Enhancement
  34. 34. Intelligent Transportation System (ITS) Benefits From HBase* Big Object Storage Insertion Performance(Single Client, No pre-split) Insert performance increase 250 records/second Insertion Performance(500KB/record) 200%,insert latency 200 reduces 90% 150 100 50 * hbase(no presplit) hbase lob 0 0s 100s 200s 300s 400s 500s Insertion Delay(Pre-split 32 regions, 6 Client Nodes) Delay: 120 Insertion hbase*lob delay/s Test setup: (intel-01 cluster, 6 machines, E5- 100 hbase delay/s 2620, 24core, 48G memory). 80 No client cache, No WAL. For HBase* (no split), after insertion, the region count is 20. 60 40 20 0 0s 200s 400s 600s 800s 1000s 1200s Intel® Distribution for Apache Hadoop*34 Software Enhancement