Grid Optimization and Resilience with Dynamic Grid Modeling

Share Button

A new white paper from Veritone explains how Cooperative Distributed Inferencing (CDI) technology delivers cost-effective resilience and grid optimization through real-time dynamic grid modeling.

Get the full report.

Today’s electrical grids are dynamic and unpredictable. Extreme weather, natural disasters, fluctuating power and unpredictable green energy sources have led to higher energy costs and a grid that can no longer provide uninterrupted power. In its new report, Veritone shows how CDI “self-learns and adapts to ensure all energy devices in a microgrid, such as solar and battery power, deliver optimal energy at peak demand times and continue to operate autonomously if isolated from the main grid due to extreme weather or natural disaster.”

CDI is the “grid modeling and learning core” of Veritone’s artificial intelligence-based energy solutions. With CDI as its backbone, Veritone’s energy solutions offer near real-time optimal economic dispatch, real-time demand response, volt/VAR optimization, microgrid energy management control and resiliency, solar smoothing, and near real-time energy arbitrage. While other solutions on the market are static, CDI evolves in real time as conditions change. This real-time dynamic modeling makes the technology unique in the marketplace.

To reduce latency, CDI uses a distributed agent-based approach, according to the paper. It’s also an integrated system “fusing together real-time forecasting, economics, rules and real-time learning for device and network model building/updating to deliver autonomous energy grid management and control.”

The report provides several use cases for CDI’s real-time dynamic modeling. With electric car batteries, for instance, Veritone says that its technology will improve the battery’s range and life span, as well as reduce the risk of a thermal event. Veritone explains that the technology can be applied to electric vehicle charging stations as well.

Veritone’s CDI technology also works seamlessly with the edge controller of each component in a microgrid.

“CDI … generates a tracking signal representing the most optimal model at any point in time. That model combines dynamic, optimal demand satisfaction with rules describing device longevity, operational limits and other device characteristics.” — Veritone, “Veritone Energy: CDI for Grid Optimization and Resilience

The authors explain their CDI and edge control system work to combine the data gathered from the rule translator, CDI agent, edge controller, blackboard and forecaster to optimize energy dispatch.

Download the full report, “Veritone Energy: CDI for Grid Optimization and Resilience” and learn more about how Veritone and CDI are delivering real-time dynamic grid modeling and control for predictable, cost-effective and resilient energy dispatch – Click Here.

Share Button


  1. Scott M says:

    Finally! This is the first time in two years I’ve seen VAR Optimization mentioned. I don’t think I’ve seen an article on PMU Synchrophasors and how the utilities have deployed them here for years. Missing the reactive power requirements/VARs are the missing big pictures on why microgrids promoters seem so simplistic and think incorrectly that microgrids are adding resiliency to the grid. They aren’t. In a perfect world, your neighbor would have all resistive loads and all generators would run at unity. That’s not the case as large generator units actually are doing extra voltage correction for the PV coming on-line, while following voltage schedules and operating in the lead or lag to support inductive system loads like 50-200hp sewer and water plant pumps, plus all the substation transformers expelling heat from radiators. From the utilities side since 99% of the microgrids will be connected to the distribution system, the only benefit I see is the operating engineers not having Tmen switch in some of the seasonal CAP Banks near the cogeneration. From a transmission aspect, microgrids for which 99% will be under 10MWs have absolutely no requirement in the interconnect agreements to support reactive power/VARs and instead maintain a unity power factor. This means the generators and peakers larger than 10MWs are supporting the VARS. In transmission a 500/230kV transformer bank loaded to nameplate can consume up to 120MVARS and require external CAPS and shunt reactors/RX’s as those banks are not load tap changers/LTCs. If there is a total system blackout the grid lines sequentially energized but not yet loaded are hugely capacitive and the Ferranti effect escalates voltage sometimes past insulator voltage ratings where they will flashover to ground. The utility needs the distribution load to lower high transmission line voltage during a blackout restoration. But, if the microgrid has islanded it is of no help to the system until all load in the microgrid is dropped and the cold-load is switched back to the utilities distribution system to help lower transmission voltage. Where it is typical to have distribution line regulators and CAP banks, the distribution system doesn’t have line reactors and uses load augmented by regulators and LTCs to reduce voltage. Basically, I’m saying the microgrid is not going to get the opportunity to have a seamless re-parallel with the grid. It is going to be a “drop and pickup” as the utility is not going to risk damaging their equipment/breaker on a bad parallel with the island and like I just explained the utility needs the distribution load to lower transmission voltage.
    While I’m here let me also dispel that microgrid jobs gained will offset jobs lost at the utilities. The microgrid owner and the utility both will contract out construction, so there is basically no difference is the construction labor force. Operating staff though is totally different. A microgrid operator is likely to have only one dayshift operator/electrician that is on-call after hours and weekends. The utility conversely must fill the operator positions for each 168 hour week. This means a minimum of 4-40 hour shift with the extra 8 hours being overtime spread evenly over the 4 man rotation. The utility will also have full time engineers, relay techs, substation electricians, environmental specialists, and various other support staff on their payroll fulltime whereas the microgrid owner will do piece-meal contracts as needed for those functions. It is a fact that solar farms have fewer shift employees than do a nuke or natural gas powerplant. I have never seen a solar plant operator being paid more than a utility steam powerplant auxiliary operator/AO.

Leave a Comment