A cloudless spring Saturday on a grid with 480 MW of rooftop solar, 60 MW of customer batteries, and 41,000 EVs behind the meter. By noon, feeders run backwards. By seven, solar is gone and everyone plugs in at once, a 940 MW ramp in three hours. This is the duck curve, and it happens somewhere in America every sunny day. Watch GridCORTEX plan the whole day as one co-optimized strategy, inverters, batteries, EVs, and market position together, with a human in the loop, and watch the duck curve itself bend at the bottom of the map. GridCORTEX is not a DERMS: it is the intelligence layer above your DERMS and ADMS, and every dispatch in this demo executes through the systems you already own.
| Without | With GridCORTEX | Δ |
|---|
| Without | With GridCORTEX | Δ |
|---|
The scenario is one cloudless spring Saturday, 06:00 to midnight, on a fictional grid rich in customer-owned energy devices: 480 megawatts of rooftop solar across 41,000 homes, 60 megawatts of customer batteries, and 41,000 electric vehicles. Days like this produce the industry's famous duck curve: the demand the utility must supply sags in the middle of the day as solar floods in, then snaps upward at sunset when solar quits and everyone plugs in at once. At 06:12 the forecast confirms a fully clear day. By 08:12 the Solara Hills corridor sees demand falling fast, with only 22 percent of hosting-capacity margin left; hosting capacity is how much solar a local circuit can absorb before it needs upgrades. By 09:30, 11 circuits are running backwards, pushing power toward the substation instead of drawing it, one reading hits 126.1 volts against the 126-volt national standard limit that protects customer equipment, and the automatic voltage adjusters in the substations begin hunting up and down.
Three decisions come to the operator. At 10:45, the first answers the midday glut without wasting any solar: switch 3,900 smart solar inverters into a mode that supports local voltage, and have 60 megawatts of customer batteries charge on the crowded circuits, deliberately soaking up solar now so the batteries are full when evening comes. By 11:30 every voltage is back inside limits, and nobody's solar was curtailed, meaning turned down and wasted. Solar peaks at 468 megawatts at 13:00. At 15:45, the second decision arms the evening: the forecast shows demand climbing 940 megawatts in three hours after sunset. The computed cheapest safe answer is a virtual power plant: thousands of small customer devices coordinated by software so they act like one large power plant. At 19:00 the utility will dispatch 92 megawatts of it, 60 from customer batteries plus 32 from businesses with flexibility contracts, through the device-control software the utility already owns. The alternative, starting two standby gas plants and buying emergency power, is $286,000 worse. At 17:45, the third decision shifts 28 megawatts of electric-vehicle charging past 22:00 across 4,100 volunteer vehicles, every one still guaranteed full by its owner's departure time.
The evening executes the plan. At 19:00 the 92 megawatts discharge across 2,600 customer batteries and business sites as one coordinated resource, and every gas plant stays cold. Managed charging holds back 28 megawatts of vehicle load until 22:00, then lets it fill the quiet overnight hours: same energy, better hours, and a cooler neighborhood transformer. The steep climb crests at 21:30. The day ends with 2 voltage violations instead of 34, zero standby-plant starts instead of two, and an operating cost of $118,000 instead of $404,000.
The passive-grid day runs the old playbook. At midday the only tool is a blanket order to curtail: 61 megawatt-hours of customer solar turned down and wasted, 34 voltage violations logged, and roughly 4,000 solar customers with a complaint for the state commission. In the evening, the 940-megawatt climb is served the expensive way: one standby gas plant starts at 18:30, a second at 19:30, plus an emergency purchase of 120 megawatts at $210 per megawatt-hour, several times the normal price. In one neighborhood, clustered vehicle charging cooks a transformer at 118 percent of its rating for 2.5 hours, an asset with a 9-month replacement lead time. The day costs $404,000 and adds 184 tonnes of carbon dioxide. The core failure: five separate customer programs each make their own decision, and nothing plans the whole day as one problem.
The change is one plan for the whole day, computed across programs the utility currently runs separately. A live physics model of every circuit says what each one can safely absorb (use case 6.2). A flexibility optimizer solves the midday glut without wasting solar (use case 6.3). Virtual-power-plant orchestration serves the evening climb from customer devices instead of gas plants (use case 6.4), all solved together against grid physics and that evening's market prices. Every dispatch keeps a human in charge: the operator approves all three recommendations, every device stays inside its owner's contract and comfort settings, and commands flow through the control software the utility already owns. The winning numbers: violations 34 down to 2, zero solar wasted, zero standby-plant starts, $286,000 saved on the day, about $25.8 million a year across roughly 90 such days, and a $14 million wire-upgrade project deferred.
| Measure | Without GridCORTEX | With GridCORTEX | Delta |
|---|---|---|---|
| ANSI voltage violationstimes delivery voltage strayed outside the national standard band that protects customer equipment | 34 | 2 | 94 percent fewer |
| Customer solar curtailedcustomer solar energy ordered turned down and wasted, in megawatt-hours | 61 MWh | 0 MWh | none |
| Reverse-flow feederscircuits running backwards at midday, pushing solar power toward the substation | 11: 3 in violation | 11: all inside limits | managed |
| Evening ramp (940 MW) served bywhat filled the 940-megawatt climb in demand after sunset; a peaker is a standby gas plant, and a VPP is thousands of customer devices acting as one power plant | 2 peakers + 120 MW purchase | 92 MW VPP + 28 MW EV shift | the customer fleet did it |
| Peaker startshow many expensive standby gas plants had to fire up | 2 | 0 | two starts avoided |
| EV-cluster transformer overloadtime a neighborhood transformer spent running beyond its rating under clustered electric-vehicle charging | 2.5 hours @ 118% | 0 hours | asset saved |
| Solar customers affectedcustomers whose solar was ordered turned down | ~4,000 curtailed | 0 | trust kept |
| Day operating costwhat it cost to run the grid for this one day | $404K | $118K | $286,000 saved |
| Peaker starts + fuelthe cost of firing up and fueling the standby gas plants | $96K | $0 | $96,000 avoided |
| Market purchase (120 MW at scarcity)emergency power bought at several times the normal price | $252K | $0 | $252,000 avoided |
| Curtailment compensationwhat the utility pays customers whose solar it wastes | $9K | $0 | $9,000 avoided |
| VPP event paymentswhat the utility paid customers whose devices served the evening peak | $0 | $71K | the fleet got paid, not the fuel supplier |
| Annualized (~90 such days)the same day's math spread across a year's worth of sunny days | $36.4M | $10.6M | $25.8 million a year |
| Solara Hills reconductorthe project to replace the corridor's wires with heavier ones to carry more solar | Needed this cycle | Deferred: $14M | a big spend postponed |
| CO₂ this dayextra carbon dioxide from running the standby gas plants | +184 t (peakers) | baseline | 184 tonnes avoided |
The safety effect here is indirect and we will say so plainly. Nobody climbs anything because of a hosting capacity map. The real mechanism is that accurate capacity values keep DER, distributed energy resources, from being approved onto feeders that then need reactive voltage work, emergency reconfiguration, and field verification trips to sort out.
Counted in units you already track:
Planning engineering hours come back to the distribution planning group and to interconnection staff, who stop running the same screening study over and over.
The numbers we need from you to run that formula:
| Cost driver | How it is calculated, from a rate you supply |
|---|---|
| Planning engineering labor | engineering hours avoided x your loaded planning engineer rate |
| Outside study support | feeder studies you currently contract out x your consultant fee per feeder study |
| Interconnection screening labor | screening studies avoided x your loaded interconnection analyst rate |
| Deferred reinforcement | your own cost per feeder upgrade x the upgrades you decide are deferrable once you can see real headroom, a judgment you make, not us |
| Queue carrying cost | your internal cost of holding a project in queue per month x months of queue time removed |
You pay for the scoped engagement that builds and runs this, for the integration into your GIS and your DER enrollment records, and for your own planners to validate the twin against a sample of feeders they have already studied by hand. The honest large item is network model data quality. If your connectivity and transformer data are rough, the cleanup is real work and it is work you would have had to do anyway.
Payback is dominated by planning engineering hours and contracted study fees, because those are the two you can audit line by line. Treat deferred reinforcement as upside, not as the base case.
The safety effect is indirect and worth stating honestly. Managing over generation with dispatch rather than with hardware and switching means fewer manual field actions taken under time pressure on a constrained feeder.
Counted in units you already track:
Event handling hours come back to the DER operations engineer on shift, and settlement hours come back to the back office analyst who reconciles curtailment.
The numbers we need from you to run that formula:
| Cost driver | How it is calculated, from a rate you supply |
|---|---|
| Avoided curtailment payments | megawatt hours of curtailment avoided x your compensation rate per megawatt hour under the applicable interconnection or program agreement |
| Operations labor | event handling hours avoided x your loaded DER operations engineer rate |
| Settlement labor | reconciliation hours avoided x your loaded settlement analyst rate |
| Deferred reinforcement | your own cost per feeder or transformer upgrade x the upgrades you judge deferrable because flexibility now manages the constraint |
| Make whole exposure | your contractual make whole or lost production payment per megawatt hour x megawatt hours no longer curtailed |
You pay for the scoped engagement that builds and runs this, for the integration into your DERMS, the distributed energy resource management system, and for telemetry quality work on enrolled resources, because an optimizer is only as good as the measurements it dispatches against. Plan on running it in shadow mode through one shoulder season while your operators build trust, and count that operator time as real cost.
Payback is dominated by avoided curtailment payments if you compensate for curtailed energy, and by deferred reinforcement if you do not. Work out which of those two you actually are before you build the case.
The safety effect is indirect. A VPP that actually delivers what it promised on a peak day reduces the emergency operations that follow when it does not: manual load transfers, callouts, and field staff working a hot afternoon into the night.
Counted in units you already track:
Event day hours come back to the program director and the monthly reporting week comes back to the program analyst.
The numbers we need from you to run that formula:
| Cost driver | How it is calculated, from a rate you supply |
|---|---|
| Capacity value delivered | incremental megawatts delivered against commitment x your capacity price or your own avoided capacity cost |
| Program labor | event and reporting hours avoided x your loaded program staff rate |
| Underdelivery exposure | your penalty or shortfall charge per megawatt x the shortfall megawatts you currently incur in a typical season |
| Market revenue | megawatt hours bid into energy or ancillary products x the settled price in your market, for the hours the portfolio was previously idle |
| Incentive efficiency | your incentive payment per enrolled device x the devices you no longer need to call because the dispatch is better ordered |
You pay for the orchestration platform, for an integration to each vendor DERMS dispatch interface, and for the contract work to get the vendors to expose those interfaces at all, which is often the slow part. Your program staff also need time to validate the combined forecast against a season of real events before they will offer against it.
Payback is usually dominated by the capacity value of delivering the commitment plus the penalty exposure you stop carrying. Program labor is real but it is the smaller line.
What is this, exactly? It is AI software: intelligent agents and models built and delivered by SoftServe, running on NVIDIA accelerated computing. It is not a hardware appliance and it does not replace the systems you run today. It deploys in your own cloud or on your premises, connects read-only to your existing systems, and recommends; your people approve every action, starting in shadow mode until it earns trust.
A real-time optimization service for DER operations staff that produces a recommended dispatch plan for enrolled flexible resources during over-generation periods, with the expected curtailment avoided. The demo above uses synthetic data; everything below describes what the real deployment needs from your organization.
| Your system | Typical products | How we connect |
|---|---|---|
| DER management (DERMS) and DER program platforms | Schneider, GE Vernova, EnergyHub | read-only API; recommendations are written back only after a person approves, via your existing system's own interface |
| Advanced Distribution Management System (ADMS/DMS) | Schneider EcoStruxure ADMS, GE Vernova PowerOn | read-only API |
| SCADA historian | AVEVA PI System, AspenTech eDNA | historian mirror (one-way feed) |
| Weather and environment | National Weather Service feeds, commercial forecast services | read-only API |
| Market and grid operator interfaces | PJM, MISO, CAISO portals; settlements | read-only API |
| Metering (AMI head-end and meter data management) | Itron, Landis+Gyr, Oracle meter data systems | database replica refreshed nightly |
| Geographic Information System (GIS) | Esri ArcGIS Utility Network, GE Smallworld | scheduled file export (CSV or CIM XML) |
Runs in your cloud account on GPU instances or on an on-premises NVIDIA server, with read-only connections and no direct link to control systems; any dispatch goes through your DERMS only after an operator approves it. It starts in shadow mode alongside your current protocol.
The Approve button you just clicked in the demo above is the real workflow. This is what it looks like on the screen of the DER operations engineer on shift in the GridCORTEX console:
Approve sends the dispatch schedule to your DERMS through its existing dispatch interface; the DERMS issues device commands under its own controls and confirmations. GridCORTEX never talks to a device directly, and your operator can amend or cancel the schedule in the DERMS at any time.
The trigger is automatic: over-generation conditions come from the weather, SCADA, and ADMS feeds, so no manual entry is needed.
Runs on ADMS state and SCADA telemetry every few seconds and weather every 15 minutes; every card shows the as-of timestamp of its inputs.
Lives in the GridCORTEX console beside the DERMS dispatch view; mobile push when an event needs action within the hour. The console runs in a browser beside your existing screens on day one; embedding into your own systems is a roadmap step once the read-only phase has earned trust. Approve, Modify, and Decline are all captured in an audit trail your compliance team can pull, and GridCORTEX never blocks or overrides anything in the systems you run today.
The first question from any utility with a modern stack: "Our DERMS already does volt-var events and our ADMS manages the network, what's new here?" Fair question. Here's the honest answer.
When someone asks "what did it actually calculate?", this is the list. Every voltage flag, curtailment avoided, and dispatch decision in this demo is the output of analyses across the categories below. In the simulation these factors drive the storyline; in a pilot they are computed from your AMI, DERMS/ADMS, inverter telemetry, network model, and market feeds.
Presenter's one-liner: "It watched every meter, every inverter, and every feeder's voltage, forecast the whole day's net-load curve hours ahead, and co-optimized one plan across inverters, batteries, EVs, and the market, then executed it through the DERMS and ADMS the utility already owns. Your DERMS is the hands. This is the brain that decides what the hands should do, and proves it was the cheapest safe choice."