There are many applications of AI/ML solutions across industries, especially in dynamic data-rich consumer markets. However, there are some industries such as the energy and utility sectors were historically a little behind in the application of emerging and trending technologies comparing to other fast-growing and innovating industries. The primary objective of energy grids is to be resilient and reliable for all types of commercial, industrial and residential customers, so IT investments are being allocated to support the level of resilience rather than experimenting to please customers. In addition to that, the energy distribution is a natural monopoly regulated by federal laws. With the growing development of distributed clean energy resources (DER) such as solar and battery solutions, the utilities have to learn how to diversify their services and incorporate DER into the electric grid. The AI / ML solutions are getting greater popularity to manage DER solutions and incorporate them into smart grids.
Veritone is a leading provider of artificial intelligence (AI) technology and solutions for a variety of industries including energy solutions. The company has developed the world’s first proprietary operating system for artificial intelligence, aiWARE™, “powering a diverse set of AI applications and intelligently process automation solutions that are transforming both commercial and government organizations”. aiWARE orchestrates an expanding ecosystem of machine learning models to transform audio, video, and other data sources into actionable intelligence.
In fall 2020, Veritone had launched its solution for the energy sector, which optimizes smart grid energy distribution by continuously knowing how much of what type of energy to deliver where. It provides grid resilience and autonomous microgrid management even though some parts of the grid fail, and optimal economic dispatch during normal operations. The suite of industrial energy solutions, powered by aiWARE, has a range of features such as energy supply/demand forecasting, energy smoothing and optimization, DER synchronization and predictive control, energy arbitrage, and smart grid simulation. As per the latest announcements, “the solutions collect current weather forecast data, energy demand, and pricing data, and detect the current state and capacity of all energy devices, to intelligently determine the ideal energy supply mix and pricing to meet grid demand, in real-time. Utilities and developers can now deliver profitable renewable energy with unparalleled grid efficiency and resiliency”.
Let’s have a quick view of the biggest challenges in electricity distribution and how specifically Veritone offers a solution. As was mentioned previously, the greatest challenge in the US electricity grid is the growing implementation of distributed energy resources (DERs) that are behind-the-meter and beyond the direct control of grid operators. These type of energy resources introduces instability in electric grids, even though residential and commercial investments in solar PV, batteries, and other DERs are helping to make the grid greener. Solar and wind power are by nature unpredictable, which makes them difficult to manage efficiently and smoothly.
In order to fulfill peak energy demand, it requires large capital outlays and sufficient lead times.
The power voltage system failures, battery malfunctions, and blackouts across the grid might be caused by energy fluctuations. In addition to that, energy trading requires real-time data on supply, demand, and pricing to generate profitable returns. With the broader usage of artificial intelligence (AI) and adaptive machine learning, the utilities are able to predict, optimize, control, and aggregate energy so that everyone in a residential community microgrid or commercial building receives the right amount of power at the right time and price.
Veritone offers several use cases for energy providers to make the residential and commercial microgrids more optimized and resilient.
- Demand Response
When there is a lack of energy supply, the applications can operate in the mode of demand response. It is basically real-time, reliable demand management occurring at the energy aggregator level, residential level, or commercial building level, where the aggregator signal is sent to individual residence or building controllers, which in turn control individual energy devices (thermostats, batteries, inverters, etc.). In a demand response application, the participant or energy aggregator receives an instruction signal from the utility, for instance, “Reduce the load by 50 kW.” The Controller responds instantly with an optimized energy level consistent with that instruction.
- Virtual Power Plant
In a VPP application, a residential community’s solar and battery energy can be aggregated, with the controller sending energy dispatch instructions based on which residence in the network needs it most, or sending excess battery energy back to the utility. This approach ensures reliable energy delivery at the lowest possible per-residence cost.
- Commercial Buildings – Smart Sensors
In a commercial building application using smart sensors, Veritone Energy Solutions has the ability to capture and analyze KPI data such as energy use, renewable utilization, etc. Using temperature sensors located inside and outside the building, the solutions can control HVAC and other heating/cooling devices to improve equipment efficiency and lower overall building energy consumption.
Technically, it consists of 3 subsystems:
- Forecaster: A distributed forecaster service that generates predictions of the state of the smart grid devices
- Optimizer: A real-time distributed agent–CDI (Cooperative Distributed Inferencer)–that learns, optimizes, and tunes models of smart grid components, generates desired behavior directions, and provides synchronization of smart grid components
- Controller: A bank of edge controllers that implements the desired behavior as a function of the predictive state of the smart grid
The Veritone Arbitrage solution connects these subsystems together to deliver predictive energy buy, sell and dispatch capabilities, whereas the OS aiWARE provides deployment, integration, data services, and weather services to these subsystems.
To summarize, it is worth mentioning that Veritone is highly recognized in the market and has now the highest honors in the Business Intelligence Group annual AI industry awards program. Veritone wins the 2021 Artificial Intelligence Excellence Award for Second Consecutive Year. The proven IT industry players such as NVIDIA are excited to partner with Veritone and offer its accelerated computing platforms to streamline the management and optimization of clean energy. As was said by Keith Cockerham, Utilities Industry Lead at NVIDIA: “The combination of Veritone CDI and NVIDIA EGX provides the millisecond-level autonomous decision-making capabilities required for smart grid management and resiliency.” The partnership opens many possibilities to run solutions on-premise, hybrid, or in the public cloud across a variety of industries as energy, security, smart cities, media and entertainment, contact centers, and industrial and manufacturing.