Grid4C
AI-Powered Energy Insights

The Internet, electricity, and cellular phones are all technological innovations that have given rise to new business models, have radically transformed economies, and forever changed the way that mankind lives and works. Artificial Intelligence (AI) and machine learning offer similar transformational potential, but with even greater opportunity: Humans no longer need to explain or program exactly how to accomplish all the tasks for new systems or innovations.

Grid4C is applying AI and machine learning to the world of energy, delivering powerful solutions for smart grid / smart devices predictive analytics, where energy value chain participants are empowered with the ability to radically optimize the electric grid and deliver new energy business models. Through these predictive analytics insights, utilities can ensure the reliability of a more distributed electric grid, consumers can recognize appliances on the verge of failure and more effectively optimize their energy consumption, and grid operators can leverage predictive consumption forecasts to better plan for the future. “Data from IoT devices and connected appliances such as thermostats and smart meters enables our self-learning algorithms to deliver intelligent forecasts, diagnostics, and insights,” explains Dr. Noa Ruschin-Rimini, founder and CEO of Grid4C.

"Recognized by Greentech Media Research as the #1 Predictive Analytics solution for the Energy industry, Grid4C is setting its sights on solving some of the toughest challenges the industry faces"

Led by Noa,having a in PhD AI and Machine Learning with predictive analytics and anomaly detection of Big Data as specialization, the company aims enable engagement among various energy value chain participants. Grid4C applies a plug and play AI and machine learning solution to address some of the prominent challenges associated with the decentralization of electric grids concerning renewable energy sources, electrification of transportation, and energy storage, which cannot be coordinated and optimized through today’s traditional forecasting and control methodologies. The company employs its expertise and AI-driven approach to streamline and leverage existing data sources to deliver accurate forecasts and predictions of distributed energy production and consumption. Their value proposition lies in their ability to derive higher value from existing, ubiquitous data sources non-intrusively, without the need for newer sensors for data collection.

Fault Detection and Diagnostics through Machine Learning

“Customer demands are just starting to catch up with the capabilities that we can provide,’’ says Dr. Ruschin-Rimini.

One of the most innovative capabilities we’re providing is embedding our algorithms directly into smart grid hardware, like smart meters, to make local decisions at the grid edge

A solution that is generating a lot of excitement in the market is Fault Prediction, Detection and Diagnostics (FDD) for home appliances, based on smart meter data, which can be enriched with data from smart appliances such as connected thermostats, enabling the same algorithms to deliver deeper diagnostics and insights.

“With smart meter data,” explains Dr. Ruschin-Rimini, “we can not only detect mechanical problems for HVAC systems or leaks in water heaters, but can even predict problems before they happen.” This can prevent slight inefficiencies from transcending into larger problems of much more severe consequences. “The core of our products is our proprietary AI self-learning engine, so all you need to do is ‘throw’ any data that may be relevant into it,’’ claims Dr. Ruschin-Rimini.

Empowering the Energy Value Chain

Grid4C’s solutions help the energy value chain on three fronts: customer-facing applications that help businesses and consumers not only save money but predict problems with the appliances they rely on, predictive customer analytics that facilitate segmentation and micro-targeting, and predictive operational analytics that optimize procurement, grid operations and the integration of solar, energy storage and electric vehicles. Grid4C is currently analyzing billions of smart meters and smart devices reads from four continents, generating millions of predictions each day, working with the biggest energy providers and smart meter vendors in the world.

The company’s product portfolio caters to a diverse customer base across the energy value chain with multiple domain-specific requirements. “We have noticed contrasting trends in the industry where certain customers require an economical solution that saves money and predicts problems with day-to-day appliances, whereas, another customer base requires energy segmentation, micro-targeting, and predictive operational analytics,” states Dr. Noa. Additionally, Grid4C also supports users seeking solutions for procurement optimization, grid operations, integration of solar systems, energy storage, and electric vehicles.

Grid4C has partnered with several global energy providers to help address various challenges related to energy utilization.

One of their successful partnerships is with Direct Energy—a retailer of energy services—which deployed Grid4C’s customer facing Machine Learning insights for more than one million residential customers in the U.S. Today, Grid4C’s machine learning product portfolio fuels DE’s “Direct your Energy” platform to drive new revenue streams and enhance customer interactions while optimizing DE’s products and services. Grid4C upholds their client’s goal of ‘Making a difference in people’s lives’ by empowering users with intelligent insights for energy conservation.’

Similarly, Grid4C works with Dalia Power Energies (DPE), Israel’s largest independent power producer, as their load forecasting platform, to deliver granular load and distributed energy resource (DER) predictions to improve operational efficiency and optimize profit margins. “By building a predictive model to each meter separately and analyzing data like meter and device reads, weather data, customer data and more, Grid4C’s engine automatically learns the underlying correlations and hidden patterns and generates predictions in a plug-and-play manner,’’ explains Dr. Ruschin-Rimini. The plug-and-play approach allows predictions to be generated very quickly, which means customers have the added benefit of short time-to-value.

"Data from IoT devices and connected appliances such as thermostats and smart meters enables our self-learning algorithms to deliver intelligent forecasts, diagnostics, and insights"

Another interesting example is Grid4C’s solutions for ENGIE-Think Energy, which are delivering new value add services for its residential customers. By leveraging Grid4C’s machine learning insights to extract more value from meter and smart thermostat data, ENGIE provides each customer insights such as smart thermostat optimizations, simulations regarding the impact of changing thermostat settings on the next bill, prediction, detection and diagnostics of appliances (HVAC, water heaters, refrigerators and pool pumps) faults and inefficiencies, and more.

Predicting the Future of Grid4C

Recognized recently by Greentech Media Research as the #1 Predictive Analytics solution for the Energy industry, the company is setting its sights on solving some of the toughest challenges the industry faces. “One of the most innovative capabilities we’re providing is embedding our algorithms directly into smart grid hardware, like smart meters, to make local decisions at the grid edge,” says Dr. Ruschin-Rimini. Grid4C’s edge lies in the ability ‘’to squeeze the greatest value from existing, ubiquitous data sources, non-intrusively, without needing to wait for new sensors to reach mass adoption.’’ In this sense, the smart meter becomes the real-time sensor, and can be used to save lives by predicting or detecting gas leakages, or managing demand rates for consumers in real-time. Grid4C is partnering with the world’s most successful smart grid leaders to develop the most valuable use cases for AI and machine learning at the grid edge, and will continue to leverage advanced machine learning capabilities to drive value from the exponential growth in IoT data.