SOURCE: MemSQL

MemSQL

June 15, 2015 10:00 ET

MemSQL Presents the Smart and Connected City of the Future at Spark Summit West

Combining Apache Spark and Tableau, MemSQL Designs "MemCity," a Futuristic City Where All Household Energy Devices Are Tracked Simultaneously in Real-Time

SAN FRANCISCO, CA--(Marketwired - Jun 15, 2015) - SPARK SUMMIT WEST, Booth #K6 -- MemSQL (www.memsql.com), the leader in real-time databases for transactions and analytics, will present the company's concept and design of "MemCity," a futuristic metropolitan city where home device energy consumption across a metropolis are tracked, processed and analyzed in real-time. The entire real-time data pipeline and visualization for 1.4 million households, approximately the size of Chicago, runs on four Amazon EC2 nodes at a hardware cost of $2.35 per hour or $21,000 per year.

The MemCity showcase tracks -- by the minute -- each device within households according to timestamp, device identification and watts consumed. From there, MemSQL integrates the data points into Apache Spark for further enrichment with geographical coordinates and zip codes. Visual representation, mapping and charting is presented through Tableau.

MemSQL Presents the Smart and Connected City of the Future at Spark Summit West -- Click to Tweet

MemCity is built using three distributed in-memory systems, quickly emerging as a real-time trinity of data pipelines: Apache Kafka, Apache Spark and MemSQL. First is the message queue of Apache Kafka, which enables publish and subscribe messaging. Next is Apache Spark, which provides real-time transformation and data enrichment. Finally, MemSQL provides a persistence layer for Spark and the ability to rapidly stand up analytics dashboards and applications based on SQL. In MemCity, Tableau serves as the visualization layer.

With this showcase, MemSQL brings to reality a true Internet of Things -- the analysis of real-time data gathered within a smart and connected city of the future. Modern in-memory database applications like MemCity enable urban planners and energy companies to see what is possible, and economically viable, for smarter energy systems and efficient energy consumption. MemCity will be showcased this week during the Spark Summit West conference in San Francisco at MemSQL booth #K6.

"We designed MemCity as a prototype of the future and the powerful possibilities real-time data analysis within a 'smart city' can bring to our lives," said Eric Frenkiel, CEO of MemSQL. "Today, real-time solutions like MemSQL and Spark enable enterprises to gather deep and meaningful insights from millions of sensors. Tomorrow, we become an even more connected world, using data to make better and smarter decisions. Being able to do this at such a low cost will make these new applications accessible."

MemSQL 4 Community and Enterprise Editions
MemCity was built with MemSQL 4, recently released including a free unlimited scale and capacity MemSQL Community Edition and a free 30-day trial of MemSQL Enterprise Edition available at www.memsql.com/download.

MemCity Technical Details

  • 3 m3.2xlarge instances for Kafka, Spark, MemSQL (8 vCPUs, 30GB RAM, 2x80GB SSD)
    • m3.2xlarge instances cost $0.532/hour in AWS US EAST
  • 1 c3.2xlarge instance for Tableau Server
    • c3.2xlarge instances cost $0.752/hour with Windows Server
  • Total AWS costs $2.35/hour or $21,000 per year
  • Running Kafka, Spark, MemSQL, Tableau
  • MemCity Metropolis Details
    • 1.4 million households (approximately the size of Chicago)
    • 8 devices per house reporting per minute interval
      • Each house has more devices overall
    • 186,667 transactions per second from Kafka to Spark to MemSQL
      • Timestamp, device identification watts consumed, geolocation information
    • Simultaneous, real-time SQL queries via Tableau

Spark Summit Details

The Spark Summit brings the Apache Spark community together. Attendees will hear from leading production users of Spark, Spark Streaming and related projects, find out where the project development is going and learn how to use the Spark stack in a variety of applications.

About MemSQL
MemSQL is the leader in real-time databases for transactions and analytics. As a purpose built database for instant access to real-time and historical data, MemSQL uses a familiar SQL interface and a horizontally scalable distributed architecture that runs on commodity hardware or in the cloud. Innovative enterprises use MemSQL to better predict and react to opportunities by extracting previously untapped value in their data to drive new revenue. MemSQL is proven in production environments across hundreds of nodes in high velocity Big Data environments. Based in San Francisco, MemSQL is a Y Combinator company funded by prominent investors including Accel Partners, Khosla Ventures, First Round Capital and Data Collective. Follow us @MemSQL or visit at www.memsql.com.