SAS Support Communities

Check out Tom Tuning's newest instructional video, where he explains the key concepts and functionalities of connectors and adapters in SAS Event Stream Processing (ESP). The video underscores the vital role these components play in ingesting and exporting real-time data to and from the ESP engine, enabling continuous analysis and swift decision-making. It covers the characteristics, advantages, and disadvantages of connectors (which run within the ESP process) and adapters (which operate as separate processes), as well as the hybrid approach offered by the adapter connector.     ... View more

In the latest episode of IoT Innovators, Brandon Kooman hosted experts Daniel Wilkins and Divya Gupta to discuss the integration of Azure Arc and Azure IoT Operations with SAS Streaming Analytics. They highlighted several key points:   Azure Arc: Extends Azure capabilities to hybrid and multi-cloud environments, allowing seamless management and governance of resources. Simplifies deployment management across hybrid and multi-cloud environments, streamlining operations. Azure IoT Operations: Provides a unified data plane for edge devices, simplifying the collection, processing, and analysis of IoT data. Integrates seamlessly with existing cloud services, offering a robust platform for IoT deployments. SAS Streaming Analytics: Provides real-time analytics that are crucial for industries needing immediate insights, enhancing operational efficiency and decision-making. Enhances real-time data processing at the edge, enabling timely actions on generated data. Tune in to the episode to discover how this integration offers powerful solutions for managing hybrid environments, boosting real-time analytics, and advancing IoT innovation.   Link to video ... View more

Explore Tom Tuning's latest presentation on SAS Event Stream Processing (ESP), a cutting-edge platform designed for real-time streaming analytics. One of the standout features he highlights is the pattern window, a powerful tool that identifies significant sequences in streaming data that traditional monitoring systems might overlook. This capability is crucial for detecting complex patterns and anomalies in real-time data streams.   In his presentation, Tom showcases ESP's impressive capabilities through a compelling security use case involving employee badge swipe activity. By leveraging the pattern window, ESP can detect anomalies such as fast swipes, frequent swipes, and multiple building entries. These insights are invaluable for enhancing security monitoring, as they allow organizations to identify and respond to potential security threats promptly.   Moreover, ESP's ability to analyze data patterns in real-time provides valuable operational insights that can drive better decision-making and improve overall efficiency. Whether it's for security monitoring or other applications, ESP's advanced analytics and real-time processing capabilities make it a powerful tool for any organization looking to harness the power of streaming data.   Link to the recording ... View more

In this how-to-video, Rik de Ruiter explores the innovative use of custom windows within SAS Event Stream Processing (ESP). These custom windows act as reusable building blocks, significantly enhancing project functionality and fostering collaboration among users.   Rik's demonstration showcases the seamless integration of pre-built windows, using a computer vision annotation example to illustrate the process. He walks through the steps an administrator would take to add these windows from sources like GitHub. This involves uploading the custom window's code, which can be written in Python or Lua, and managing the settings, inputs, and outputs within the ESP environment.   One of the key takeaways from Rik's presentation is the ease of updating custom windows. Notifications ensure that all users are working with the latest version, promoting efficient code reuse and maintaining consistency across projects.   Rik's insights into custom windows within SAS ESP highlight their potential to streamline workflows and enhance collaborative efforts, making them a valuable asset for any project. ... View more

  In this detailed "how to" video, Joydeep Bhattacharya explores the complexities of how SAS Event Stream Processing (ESP) handles streaming data aggregation. The presentation highlights two main approaches: in-memory aggregation and aggregation using external data stores, each with its own unique benefits and specific use cases. The primary role of ESP is to enable real-time analysis of streaming data, which is a crucial aspect of modern data processing.   Key Themes and Ideas: Streaming Data Aggregation as a Core Operation: Streaming data aggregation is depicted as a vital step for nearly every streaming use case, adding significant value and enabling real-time insights. The fundamental concept involves collecting and processing streaming events to derive meaningful summaries or statistics, such as calculating the average price of a stock over time. In-Memory Aggregation with ESP: Process: ESP performs data aggregation in memory based on incoming events, using "aggregate windows." These windows group events according to a specified "key field" (e.g., stock symbol) and then apply aggregation functions (e.g., average price) to each group. Performance: Aggregation is executed with high throughput and low latency because the data is stored in memory, ensuring rapid processing. Stateful Nature: Aggregate windows are stateful, meaning they retain incoming events and continuously update the aggregations. State Management with Retention: Due to their stateful nature, ESP employs retention policies to manage the size of in-memory data. Retention can be: Time-based (sliding or jumping): Data is retained for a specified duration (e.g., "last 5 seconds"). Count-based (sliding or jumping): Only a certain number of the most recent events are kept. Aggregation with ESP using External Data Store Process: ESP uses StateDB windows that can write and read data from in-memory external data stores that can match ESP performance. Stateless nature: The ESP projects can themselves be stateless but store all the concerned data in the external data stores. State Management: The external dedicated data stores allow huge data for extended time keeping the ESP project performant and robust.   SAS ESP provides a flexible platform for real-time streaming data aggregation, capable of accommodating various requirements through either in-memory or external data storage options. The choice between these approaches depends on the specific needs of the use case. ESP empowers users to process streaming data efficiently and in real time.   Click on this link to learn more.   ... View more

  In this latest episode of IoT Innovators, host Brandon Kooman (@bkooman) chats with experts Steve Enck and Sarah Gauby about the game-changing potential of SAS AutoML for IoT. They delve into its advantages over traditional methods and explore its real-world applications across various industries.   Key Highlights: Simplifying Real-Time Analytics Deployment: SAS AutoML for IoT streamlines the deployment of real-time analytics by balancing aspects of both traditional batch processing and streaming data methods. This ensures that users can both monitor their assets continuously and integrate world class analytics, crucial for industries relying on smart technology and automation to maintain efficiency and responsiveness. Concept of the Digital Twin: Users can create a digital twin, a virtual representation of physical assets, tailored to their specific use case. This digital twin is then enhanced with new calculated metrics and machine learning models, resulting in more accurate and actionable insights. Importance of Data Enrichment: Enriching data allows for a more thorough analysis, essential for supporting the development of robust machine learning models. These models can then be easily trained and deployed, providing valuable predictions and optimizations for various IoT applications. Seamless Integration of SAS Products: SAS offers a full suite of tools that cover the entire end-to-end analytic lifecycle. SAS AutoML for IoT provides a significant level of automation that integrates these tools and enhances the overall efficiency and effectiveness of IoT solutions. By simplifying analytics deployment and enhancing user accessibility, SAS AutoML for IoT is set to revolutionize how industries leverage real-time analytics and machine learning in their IoT applications.   Click here to watch the full episode!   ... View more

  In this month's episode of IoT Innovators, host Brandon Kooman (@bkooman) dives deeper into the world of streaming analytics with IoT experts Priya Sharma (@PriyaSharma) and Katy Salamati. Together, they unpack the benefits and innovative methods of streaming analytics, highlighting how it can significantly enhance data value, facilitate real-time decision-making, and boost operational efficiency across a wide range of industries.   The discussion explores predictive maintenance, smart cities and more, highlighting real-life applications where streaming analytics has made a tangible and significant impact. They also look ahead to future trends in the field, such as the integration of artificial intelligence (AI), and emphasize the critical importance of sustainability and scalability in developing robust streaming analytics solutions.   Listeners will gain valuable insights into how streaming analytics is transforming industries and what the future holds for this exciting technology. Whether you’re a seasoned professional or new to the field, this episode offers a wealth of knowledge and inspiration.   Click here to watch the full episode!   ... View more

  In the latest episode of IoT Innovators, host Brandon Kooman talks with experts Sanjeev Heda and Tom Stock about Predictive Maintenance (PdM), with a focus on Remaining Useful Life (RUL) prediction. They delve into how PdM sets itself apart from traditional methods, highlighting the crucial shift from reactive to proactive maintenance strategies.   The conversation underscores the advantages of using SAS Analytics for IoT to enhance maintenance planning and optimize spare parts management. Through real-world examples from the transportation and manufacturing sectors, they demonstrate how PdM significantly boosts operational efficiency.   Additionally, the experts tackle the challenges of implementing predictive maintenance strategies and explore the future of this field, driven by advancements in AI and machine learning.   Click here to watch the full episode!   ... View more

Predictive maintenance is revolutionizing industries by minimizing downtime and enhancing asset performance. In this insightful video, Sanjeev Heda (@saheda) delves into SAS’s robust capabilities in implementing predictive maintenance to a fleet of assets. Each aspect of predictive maintenance that showcased in this video will show data exploration, data processing and modeling, and how the end results can be consumed by the end users to drive action and value.   Key Highlights: Predicting Pending Failures in Real-Time: Create a real-time multi-layer model for predicting diverse pending failures using SAS Event Stream Processing (ESP). Remaining Useful Life (RUL): Develop reliability and survival models to estimate Remaining Useful Life with this being personalized per asset using time-series data. Power of SAS Analytics of IoT – showcasing use of SAS AIoT Data Model, Explorations, Custom Analytic Framework, along with other SAS tools such as SAS Studio, SAS Visual Data Mining and Machine Learning (VDMML), etc. This proactive approach not only reduces maintenance costs but also significantly boosts operational efficiency. By predicting potential failures, companies can schedule timely interventions, ensuring uninterrupted production and extending the lifespan of essential machinery.   Check out this video demo to discover how SAS can transform your maintenance strategy and drive your operational success!   ... View more

In our latest episode of IoT Innovators, Brandon Kooman sits down with Divya Gupta and Kushagra Kapoor to explore the rapidly evolving technological landscape. They delve into the concept of edge-to-cloud architecture, which optimizes data processing and analytics by leveraging both edge devices and cloud environments.   The discussion highlights three common methods for deploying SAS Event Stream Processing (ESP): Full Cloud Deployment: ESP operates either as a standalone (lightweight) or alongside Viya. Edge Deployment in Containers: ESP is deployed at the edge within containers. Hybrid Deployment: This combines a standalone (lightweight) deployment at the edge/cloud with the second option. Additionally, the experts share insights on integrations, automation, and best practices. Be sure to check it out!    Link to Episode 2 ... View more

IoT Streaming Analytics Community,   Take a look at @TomStock’s latest community post and demo video, “Chemical Stability Monitoring with PCA and Change Detection.”  He demonstrates how to configure and use SAS Event Stream Processing (ESP) with unsupervised models to detect real-time changes in the conditions of a chemical process using the Tennesse Eastman Process.         Community Post SAS User Video ... View more

In the realm of renewable energy, a revolution is unfolding, driven by Utility Scale Photovoltaics. Globally, solar energy is poised to surpass coal and natural gas, shaping the future of our power supply. In the United States, projections estimate a staggering 428 GW of new solar farm generation by 2033.   In this solar farm remote monitoring demonstration, we tackle two critical challenges:   Operations and Maintenance: Reactive and preventative maintenance can lead to unplanned downtime, excessive costs, and reduced efficiency. Solar operators require the ability to proactively identify underperformance issues caused by weather, temperature, electrical failures, or mechanical fatigue. The goal is to catch these issues before they result in prolonged downtime. Supply Chain Issues: Limited parts visibility can lead to shortages, impacting installations and maintenance. Managing critical parts inventory and tracking warranties (which can last up to 25 years for solar panels and 10 years for inverters) is crucial.   To address these challenges, SAS and ClearBlade have joined forces. SAS provides automated machine learning and real-time decision-making for streaming data, while ClearBlade offers an advanced IoT platform for secure, real-time applications. Our demonstration illustrates the deployment of machine learning algorithms and decision management using this advanced IoT platform. The result? Predictive maintenance strategies at scale for solar operators, optimizing outage scheduling and supply chain decisions.   For more information about our capabilities and to request a demo, visit www.sas.com/ClearBlade.  ... View more

Hi IoT Streaming Analytics Community,   Dedicated to highlighting the innovative ways SAS Event Stream Processing (ESP) empowers customers, this new web series, IoT Innovators, will explore the ideas, designs, and implementation for cutting-edge IoT solutions to help you accelerate your time to value on IoT projects.      Episode 1: From Pixel to Actionable Insights   Available on-demand, the first episode host Brandon Kooman (@bkooman) discusses computer vision and streaming analytics with experts, Juthika Khargharia (@Juthika) and Tom Tuning (@TomTuning) – sharing real-world examples, field challenges and advances they foresee the industry making in the next few years.   From practical use cases to groundbreaking advancements, this new series promises insights you won’t want to miss. Tune in to gain valuable insights that will help shape the way you think about SAS and IoT.  2.sas.com/61105eh4KX     ... View more

SAS Analytics for IoT is a complete AI-embedded IoT analytics solution that covers the entire IoT analytics life cycle. It was created for all types of users --business users, engineers, data scientist and IT professionals -- who want to accelerate time to value (new insight, fast & accurate decision making, desirable outcomes) from their use cases. The solution enables them to organize their diverse IoT data, create data selections, visually explore massive volumes of high frequency data, and launch data sets that can be leveraged in SAS, third party and open source applications. With this capability, organizations can extend the use of IoT analytics and collaboration across the enterprise, while optimizing their ecosystem of IoT investments –SAS, third party and open source.   Check out this GitHub repo to learn more about SAS Analytics for IoT and its different components. ... View more

Check out this GitHub repo to learn how the Japan IoT Team used an accelerometer, a simple rotating fan, and an SVDD model to demonstrate anomaly detection capabilities.  This demo was developed to be an way to demonstrate anomaly detection using a real-time vibration data and SAS ESP.  Input data is flowing in via MQTT at a rate of 12.8 kHz with RMSA calculated every second.  After that, the SVDD model for is used for scoring. (Note: The SVDD model was trained using SAS Studio)   As shown in the video below, we made a device with 2 rotating fans (one with normal fan and another with a blade broken) and used SVDD to detect when the condition of the machine (fan) changes. The output is SVDD distance (top graph) and SVDD score (bottom graph). When the normal fan is rotating, the score is -1 (normal state) but when the device is switched to the broken fan, the SVDD score changes to 1 (faulty state).       Below is an instructional video on how to built your own fan simulator device that you can switch between normal and failure modes. The team attached an accelerometer to gather the vibration data and send to an ADLink USB-2405 DAQ.  (Note: It is also possible to use ADLink MCM-100 DAQ (edge device) which is basically a DAQ device and also a PC)   ... View more