AI and IoT for Grid Analytics

Develop the “Grid of the Future” using AI and digital twins

Scientists, engineers, and analysts use MATLAB® and Simulink® to develop artificial intelligence (AI) and machine learning algorithms, deploy AI solutions to edge devices, and deliver predictive insights on consumer behavior and system performance.

With MATLAB and Simulink, you can:

  • Collect data from smart meters and IoT devices in real time
  • Combine machine learning, deep learning, and dynamic modeling methods in a single platform to analyze data in real time
  • Develop load, price, and DER forecasting algorithms using machine learning and AI
  • Deploy forecast models to enterprise, cloud systems, and connect to regional wholesale electricity markets, meteorological data, and other data streaming services
  • Develop enterprise and portfolio risk management solutions

“When you deal with numbers all day and work with sophisticated analytical models, having an integrated environment is invaluable. With MATLAB we visualize data, conduct back-testing, and plot graphs to see the results of changes we make, all in one environment, and that saves time.”

Simone Visonà, A2A

AI and IoT for Smart Utility Infrastructure

The Internet of Things (IoT) enables power producers, public utilities, and energy companies to collect and analyze data from hundreds of industrial or residential buildings in near real time. Combine machine learning, deep learning, signal processing, and dynamic modeling methods in a single platform to analyze data in real time. Interactive apps in Statistics and Machine Learning Toolbox™ let you apply machine learning techniques without having to be an expert in data science. MATLAB also provides a single, high-performance environment for working with big data—be it structured or unstructured.


Energy and Price Forecasting

Gather historical data from multiple sources and develop production-ready forecast models using machine learning in MATLAB. Deploy your forecast models to enterprise and cloud systems, and connect to regional wholesale electricity markets, meteorological data, and other data streaming services.


Big Data Analytics and Digitization

Today’s utility world is online and interconnected. To conquer this changing market, MathWorks can help you adopt and implement big data strategies specific to the needs of your organization. You can connect MATLAB directly to OSIsoft® PI systems and enable real-time operational intelligence. You can use prebuilt MATLAB toolboxes and reference architectures to simplify a wide range of applications from integrating with enterprise IT systems, the cloud, and production data infrastructures to scaling your computation to clusters to deploying your models as applications to share with users working outside of MATLAB.


Predictive Customer Analytics

Using MATLAB, collect customer parameters as well as energy consumption behavior profiles, such as the charging patterns of electric vehicles, to develop predictive models and customer solutions. Use machine learning and AI techniques to create individual services and rate plans and retain most profitable customers. Combine outage data (type and duration) and spatial data to predict outage cause, level of impact, and time to restore power..


Process Improvement with Data Modeling

Use multivariate analysis tools in MATLAB to determine the independent driving variables affecting process performance. System Identification Toolbox™ lets you create and use models of dynamic systems that are not easily modeled from first principles or specifications. The toolbox also lets you interactively perform online parameter and state estimation.


Beyond the Desktop

With the push of a button, you can generate C, C++, and HDL code to run on hardware. Create hardware-independent IEC 61131-3 Structured Text and Ladder diagrams, and deploy them on PLCs and PACs. Use prebuilt big data analysis techniques and dedicated toolboxes to run your algorithms on multicore processors, clusters, and NVIDIA® GPUs without learning new programming languages. Scale your programs to the cloud without recoding. Call MATLAB functions from PI systems without creating custom architectures.