Converge Transactional and Predictive Analytics to Effectively - PowerPoint PPT Presentation

Converge Transactional and Predictive Analytics to Effectively Scale IoT 2018

11 billion Is the number of connected devices… Not including phones and computers How can we leverage this information for context-sensitive insights that answer specific questions about specific things at the right point in time?

About GigaSpaces 300+ Direct customers We provide the leading in-memory computing platforms for real-time insight to action and extreme transactional processing. With GigaSpaces, 50+ / 500+ enterprises can operationalize machine learning and Fortune / Organizations transactional processing to gain real-time insights on their data and act upon them in the moment. 5,000+ Large installations in production (OEM) 25+ InsightEdge is an in-memory real- In-Memory Computing time analytics platform for instant Platform for microsecond ISVs insights to action; analyzing data scale transactional as it's born, enriching it with processing, data scalability, historical context, for smarter, and powerful event-driven faster decisions workflows

Our Customers Span Across Multiple Industries FINANCIAL RETAIL INSURANCE TELCO TRANSPORTATION SERVICES

Select Customers OEMs / ISVs / Partners

74% want to be data driven only 23% are successful,

Value of Data to Decision Re Real al-ti time me data ta is highly valuable if you act on it on time Time-cri Ti critical cal Tra Traditional “batch” dec decis isio ion busin bu ines ess in intel ellig igen ence Value ta is more valuable Ol Old + real al-ti time me data if you have the means to combine them Actionab Reactive Historical le Preventive/ Actionable Reactive Predictive Historical REAL-TIME SECONDS MINUTES HOURS DAYS MONTHS Time

Real-Time Applications Sma Smarte test st Deci De cision ons RE REAL-TI TIME HI HISTO TORICA CAL L VARIOUS DA DATA SOURCES

WHY ARE ONLY 23% SUCCESSFUL? FROM: TO: Big Data Insights Insights Real-Time Insights Real-Time Insights Real-Time Actions

Challenges of Internet of Things Application Enablement Foundations of an IoT Analytics Platform CENTER + EDGE CLOSED LOOP MULTI-TENANT, BATCH + REAL-TIME LOW-LATENCY ANALYTICS GEO-FEDERATED, DATA CONVERGENCE PROCESSING (INSIGHTS TRIGGER SCALE-OUT ON DATA FROM WORKFLOWS) VARIOUS SOURCES Focus on low IoT data ingestion is From sensors to “Graphs and latency and event- heterogeneous: actuators = from Topologies”, rather driven, rather than streaming, micro- insights to action than “Layers and high-throughput batch, and batch on (at low latency) Tiers” multiple data types

InsightEdge: Unifying Real-Time Analytics, AI and Transactional Processing in One Open Source Platform • Open Source & Open API • Rich ML & DL support • Extreme performance Machine Learning • Fully Transactional & Deep Learning • ACID Compliance • Enterprise-grade In-Memory KEY-VALUE GEO SPATIAL DOCUMENT (Security, High Availability) Multi Model Store TABLE COLUMNAR STREAMING • Co-located Apps and Services Intelligent Multi-tier Storage Management • Seamless integration with Big Data ecosystem STORAGE • Data sources (Kafka/Nifi/Talend) ORCHESTRATION • Data lakes (S3/Hadoop) CLOUD/HYBRID/ • BI tools (Tableau/Looker/etc.) ON-PREMISE

InsightEdge Architecture Overview MOBILE WEB IOT APPS & MICROSERVICES ANALYTICS & BIG DATA SEARCH, BI & QUERY MANAGEMENT AND MONITORING EVENT SECURITY AND AUDITING REST ORCHESTRATION MICROSERVICES MICROSERVICES EVENT MACHINE BigDL .NET JAVA SPARK SQL SQL/JDBC SEARCH STREAMING (REST) PROCESSING PROCESSING LEARNING (REST) RPC & RPC & DATA MODELS WEB CONTAINERS EVENT MAP/REDUCE MAP/REDUCE (SPATIAL, POJO, JSON) PROCESSING IN-MEMORY DATA GRID RAM SSD STORAGE-CLASS DATA REPLICATION STORAGE MEMORY & PERSISTENCE CLUSTER MANAGEMENT & SERVICE DISCOVERY CLOUD ON-PREMISE HYBRID

InsightEdge Unifying Fast Data Analytics, AI and Transactional Processing MOBILE WEB IOT Cloud Native Management, APPS & MICROSERVICES ANALYTICS & BIG DATA SEARCH, BI & QUERY Orchestration, and Analytics and AI SQL and BI Real-time Microservices EVENT SECURITY AND AUDITING MANAGEMENT AND MONITORING REST ORCHESTRATION MICROSERVICES MICROSERVICES EVENT MACHINE .NET JAVA SPARK SQL SQL/JDBC SEARCH STREAMING (REST) PROCESSING PROCESSING LEARNING (REST) Monitoring RPC & In-Memory Data Grid RPC & DATA MODELS WEB CONTAINERS EVENT MAP/REDUCE MAP/REDUCE (SPATIAL, POJO, JSON) PROCESSING IN-MEMORY DATA GRID RAM SSD STORAGE-CLASS DATA REPLICATION Multi-Tiered Data Storage and Replication STORAGE MEMORY & PERSISTENCE High Availability and Clustering CLUSTER MANAGEMENT & SERVICE DISCOVERY ON-PREMISE HYBRID CLOUD

Ultra-low latency and high throughput transactional processing IMDG Partitioned In-Memory Grid Shared-nothing, linear scalability, MOBILE WEB IOT elastic capacity Co-Location of Data and Business Logic Co-located ops, event-driven, ANALYTICS & BIG DATA APPS & MICROSERVICES SEARCH, BI & QUERY fast indexing SECURITY AND AUDITING MANAGENENT AND MONITORING MANAGENENT AND MONITORING EVENT MACHINE MICROSERVICES MICROSERVICES EVENT SPARKL SQL SQL/JDBC SEARCH STREAMING .NET JAVA Event-Driven Processing and LEARNING (REST) PROCESSING PROCESSING (REST) Map/Reduce No Downtime Auto-healing, multi-data center RPC & RPC & DATA MODELS WEB CONTAINERS EVENT replication, fault tolerance MAP/REDUCE MAP/REDUCE (SPATIAL, POJO, JSON) PROCESSING IN-MEMORY Fast Indexing Multi-Data Model DATA GRID POJO, .NET, Document/JSON, RAM SSD STORAGE-CLASS DATA REPLICATION Geospatial, Time-series STORAGE MEMORY & PERSISTENCE Seamless Integration wih Java/Scala ecosystem CLUSTER MANAGEMENT & SERVICE DISCOVERY Cloud Native ON-PREMISE HYBRID CLOUD

Co-located Analytics and AI with Transactional Processing MOBILE WEB IOT ANALYTICS & BIG DATA SEARCH, BI & QUERY APPS & MICROSERVICES SEARCH, BI & QUERY SECURITY AND AUDITING MANAGENENT AND MONITORING MANAGENENT AND MONITORING MACHINE MACHINE EVENT MICROSERVICES SPARK SQL MICROSERVICES EVENT STREAMING SQL/JDBC SQL/JDBC SEARCH SEARCH .NET JAVA LEARNING LEARNING (REST) PROCESSING PROCESSING (REST) Distributed SQL-99 Spark for ML and leading DL frameworks RPC & RPC & DATA MODELS WEB CONTAINERS EVENT Push-down predicate for ultra-low Real-time MAP/REDUCE MAP/REDUCE (SPATIAL, POJO, JSON) PROCESSING integration with latency filter (30x faster) IN-MEMORY Tableau and DATA GRID Business Shared RDDs/DataFrames RAM SSD STORAGE-CLASS DATA REPLICATION Intelligence tools STORAGE MEMORY & PERSISTENCE Streaming with 99.999% availability JDBC driver CLUSTER MANAGEMENT & SERVICE DISCOVERY Deep Learning with Intel BigDL Graph processing, text mining, geospatial ON-PREMISE HYBRID CLOUD

High Availability & Clustering MOBILE WEB IOT ZooKeeper-based clustering for 1000s of nodes Back-up and auto-healing for each grid container SEARCH, BI & QUERY ANALYTICS & BIG DATA APPS & MICROSERVICES N + 1 redundancy SECURITY AND AUDITING MANAGENENT AND MONITORING REST ORCHESTRATION EVENT MACHINE MICROSERVICES MICROSERVICES EVENT SPARKL SQL Unicast or Multicast discovery SQL/JDBC SEARCH STREAMING .NET JAVA LEARNING (REST) PROCESSING PROCESSING (REST) RPC & RPC & DATA MODELS WEB CONTAINERS EVENT MAP/REDUCE MAP/REDUCE (SPATIAL, POJO, JSON) PROCESSING IN-MEMORY DATA GRID SSD STORAGE-CLASS DATA REPLICATION RAM STORAGE MEMORY & PERSISTENCE CLUSTER MANAGEMENT & SERVICE DISCOVERY ON-PREMISE HYBRID CLOUD

Multi-Tiered Data Storage and Replication for Optimized TCO MOBILE WEB IOT In-Memory Data Processing (RAM) Intelligent Data Tiering between RAM, SSD and Storage-Class Memory such as Intel 3DXPoint - SEARCH, BI & QUERY ANALYTICS & BIG DATA APPS & MICROSERVICES Optane SSD/NVMe and Optane DC Persistence memory. Leverages RocksDB SECURITY AND AUDITING MANAGENENT AND MONITORING REST ORCHESTRATION EVENT MACHINE MICROSERVICES MICROSERVICES EVENT SPARKL SQL SQL/JDBC SEARCH STREAMING .NET JAVA LEARNING (REST) PROCESSING PROCESSING (REST) Multi-Data Center Replication Asynchronous Persistence to SQL/NoSQL RPC & RPC & DATA MODELS WEB CONTAINERS EVENT MAP/REDUCE MAP/REDUCE (SPATIAL, POJO, JSON) PROCESSING IN-MEMORY DATA GRID SSD STORAGE-CLASS DATA REPLICATION RAM STORAGE MEMORY & PERSISTENCE CLUSTER MANAGEMENT & SERVICE DISCOVERY ON-PREMISE HYBRID CLOUD * Apache Pass support in Q4 2018

Effectively Scale IoT: Real-time Analytics for Instant Insights To Action VARIOUS APPLICATION DATA SOURCES UNIFIED REAL-TIME ANALYTICS, AI & TRANSACTIONAL PROCESSING REAL-TIME INSIGHT TO ACTION IN-MEMORY MULTI MODEL STORE RAM HOT DATA STORAGE-CLASS MEMORY DASHBOARDS SSD STORAGE WARM DATA • No ETL, reduced complexity REAL-TIME LAYER • Built-in integration with external Hadoop/Data Lakes S3-like • Fast access to historical BATCH LAYER data • Automated DEPLOY ANYWHERE COLD life-cycle management CLOUD/ON-PREMISE DATA