GridCORTEX Live · ISO & Market Special  ·  ← All Demos
On this page What you are watching The business case Run this at your utility Where you see it and how you say yes

Blackstart Drill Synthetic Data · Simulation

The drill every operator dreads and every regulator requires: the system is black. Watch a joint restoration exercise (ISO, generator, and two transmission operators in one simulated room) as a hydro unit self-starts, the cranking path energizes bus by bus, a drill-master trips a unit mid-restoration, and the island re-sequences, recovers, and synchronizes back to the interconnection against the clock. The kind of drill that takes a year to schedule, run on demand, with every action scored. Nobody else can show this one.

T+0 MIN
SYSTEM BLACK: DRILL
⏳ DECISION POINT: TIME SLOWED
SYNTHETIC DATA
De-energized Energized island Cranking / picking up Blackstart unit Drill inject

Same black system. Two very different drills.

What an AI drill copilot is worth when the lights are off and the clock is running
,
Interconnection restored
,
Drill objectives met
,
EOP-005 evidence pack
The Restoration: Performance
WithoutWith GridCORTEXΔ
The Drill: Program Value
WithoutWith GridCORTEXΔ
Illustrative simulation on synthetic data; timings, ratings, and drill outcomes are placeholders. In a GridCORTEX pilot, the drill simulator is built from YOUR restoration plan, YOUR cranking paths, and YOUR relay settings, validated against the engines of record. See UC 20.7 "Demo and Proof Plan."
,
Island frequency
0 MW
Load restored
0 / 8
Buses energized
ON PLAN
Drill clock
Drill Feed: ISO · GenCo · 2 TOs · human-in-the-loop
Black
Crank
Inject
Sync
T+90
The Validated Use Cases Behind This Scenario
UC 20.7
Joint Blackstart Drill Simulator
The annual scheduling nightmare, run monthly: multi-party drills with live injects, scoring, and evidence capture.
UC 1.8
Restoration Sequencing Advisor
The re-sequencing brain: when the plan breaks mid-restoration, the next-best path is computed, not improvised.
UC 2.7
Cranking Path Validation Twin
Every path pre-validated against relay settings, line charging, and unit capabilities, before anyone closes a breaker.
187 UCs
One Framework
The Blackstart Drill is one of 187 validated use cases across 10 solution areas and 23 utility domains.
Inside the Demo
What you are watching, and what it proves

A blackstart is restarting the grid from a total blackout. Federal reliability rules require utilities to practice it, but a joint drill needs several companies in one room, so it usually happens once a year. This demo is that drill, run entirely on synthetic data, meaning realistic but invented numbers. Three parties share one simulated eight-substation grid: the regional organization that operates the grid, the fictional power producer PELICAN GENERATION, and two companies that own the high-voltage lines. At the start, every light is off. The goal is to reconnect to the neighboring grid at the LAKELINE tie point in under 100 minutes. Three power plants matter. PELICAN HYDRO is a 45 megawatt hydroelectric unit that can start itself with no outside power; one megawatt is roughly enough power for several hundred homes. BAYSIDE CC is a 180 megawatt gas plant that needs outside power before it can start. EASTPORT CT-3 is an 85 megawatt backup gas turbine.

Two minutes in, the first decision arrives. The software has already tested the restart route inside a digital twin, a working computer model of the grid used to try decisions safely before making them. The route is called a cranking path: the exact order in which lines and substations get power again. The model flags one trap in advance: powering one long line before any customer demand is attached would push its voltage 14 percent above normal and trip the automatic protection. The drill room approves the route, and human operators, not the software, close every switch. The hydro unit starts itself at minute 4 and creates a small live island of grid running at exactly 60 hertz, the frequency the grid must hold; think of it as the system's heartbeat. Substations come alive at minutes 8, 13, and 19. Customer demand returns in careful 5 megawatt blocks. By minute 26 the island carries 25 megawatts with a steady heartbeat of 59.98. Then at minute 33 the drill master springs a planned surprise: the big gas plant fails mid-start. That leaves 25 megawatts of demand hanging on the one 45 megawatt hydro unit, and the frequency falls to 59.31. Below about 59.5, the island is minutes from collapsing back into blackout.

The second decision is the heart of the demo. In seconds, the software computes a recovery plan: deliberately disconnect two blocks of customer demand worth 10 megawatts to stop the fall, keep the gas plant's startup alive rather than abandoning it, bring the backup turbine EASTPORT CT-3 online instead, and reconnect customers only after the frequency holds 59.9 for two full minutes. The room approves. The disconnection is done in 90 seconds; the frequency bottoms out at 59.24 and recovers. The backup turbine is running by minute 53, adding 85 megawatts of capability. The big gas plant joins at minute 61, adding 180 more. By minute 70, all 8 substations are live and the island carries 110 megawatts. At minute 78 the island is matched to the neighboring grid, and the LAKELINE tie closes at 82 minutes, well inside the 100-minute goal. The drill ends with 140 megawatts of customer demand restored, all 9 scored objectives met, and the evidence file required by federal reliability rule EOP-005 assembled automatically by minute 83.

Without GridCORTEX

The old way starts with a paper binder. The room argues over two candidate routes for 22 minutes, then picks one that powers a long line before any customer demand is attached. Voltage on that empty line spikes 18 percent above normal, a known physics effect, and the automatic protection trips the line. Restarting from scratch costs 30 more minutes. When the surprise plant failure hits, the improvised answer is to disconnect everyone and abandon the plant startup. The island survives, but it serves nobody, and the second startup attempt runs out the clock. The drill is suspended at minute 84 with 4 of 9 objectives met, only 4 of 8 substations live, and zero customer demand restored, followed by two weeks of after-action paperwork. The core failure is improvising under time pressure, with no way to test a route before throwing the switch.

With GridCORTEX

The software does three things. First, it tests every candidate route in the computer model before the room even asks, checking protection settings and the voltage spikes that empty lines produce, so the 22-minute debate and the trip never happen (use case 2.7). Second, when the surprise failure hits, it computes a recovery sequence in seconds instead of leaving the room to guess (use case 1.8). Third, it lets three companies drill together in one shared simulation, with automatic surprises, live scoring, and a compliance evidence file that builds itself during the run (use case 20.7). Every recommendation is an approval gate: the software suggests, the drill room decides, and human operators act. The winning numbers: tie closed at 82 minutes, 140 megawatts restored, 8 of 8 substations live, 9 of 9 objectives met.

The scorecard, side by side
MeasureWithout GridCORTEXWith GridCORTEXDelta
Cranking path selectionhow long the room spent choosing the restart route before anyone could act22 min of debatevalidated in advance22 minutes saved
Ferranti overvoltage tripa voltage spike on a long line powered with nothing at the far end; it trips protection and forces a restartyes: restart, −30 minprevented by sequencingno restart needed
Unit-trip inject responsewhat the room did when the drill master failed the big gas plant mid-startshed all + abort crankcomputed re-sequence, 90 sthe island survived
Interconnection tie restoredthe minute the island reconnected to the neighboring grid; the goal was under 100 minutesnot reachedT+82objective met
Load restored at drill endmegawatts of customer demand back on power when the drill ended0 MW140 MW140 megawatts of customers back
Buses energizedsubstations brought back to life along the restart route4 of 88 of 8every substation live
Drill objectivesthe scored goals the exercise was designed to test4 of 99 of 95 more objectives met
Joint drill frequencyhow often three organizations can practice a restart togetherannual (scheduling limit)monthly, on demand12 times as often
Drill-master inject prepthe work of preparing surprise events and scoring the response to themweeks, hand-builtgenerated + scored liveon demand
EOP-005 evidence packagethe proof file that federal reliability rule EOP-005 requires after every blackstart drill2 weeks after-actionassembled during the drillfinished at minute 83
Multi-party participationhow many organizations can join, and how hard the drill is to schedule3 orgs, 1 painful date3 orgs, any datecoordination solved
Operator reps per year (blackstart)how many full restart rehearsals each operator gets in a year112+practice adds up
Findings into plan revisionshow quickly lessons from a drill get written into the official restoration planannual cycleevery drilllessons land immediately
Real EMS/SCADA touchedthe live control systems that run the actual grid; the drill never connects to themneverneversimulation only
The live numbers on the dashboard
Island frequencyThe heartbeat of the restored island, measured in hertz. 60.00 is perfect health; anything below 59.5 means the island is minutes from collapsing back into blackout.
Load restoredMegawatts of customer demand back on power. Zero means a dead system; a steady climb to 140 by the end means the drill succeeded.
Buses energizedHow many of the 8 substations are alive again. Steady progress is good; stalling at 4 of 8 means the restart has broken down.
Drill clockProgress against the 100-minute goal. ON PLAN is good; BEHIND or COLLAPSING means the room is losing the race against the clock.

The Business Case: Safety, Hours, and Cost

A utility does not buy a demo. It buys a safety exposure that goes away and a cost that goes down. Below is that case for every use case behind Blackstart Drill, written the way a plant manager, a safety lead, and a CFO each need to read it. Every hour and every dollar is a formula you run with your own rates and volumes. There are no vendor benchmarks in here and no invented percentages. If a number is not yours, it is not a number.
UC 20.7 Joint Blackstart Restoration Drill Simulator

What happens today, without this

The ISO coordinates a joint blackstart restoration drill roughly once a year. The director of operations training and a small group build the scenario by hand over weeks, write a script with pre determined injects, and run it in a conference room or over a bridge with transmission owner, generator owner, and ISO desks reading from binders. Because it is scripted, participants can anticipate the next step, and because it is annual, most operators touch the procedure once between drills. Scoring is a facilitator's judgment written up afterward, with no baseline to score against. The NERC EOP-005 and EOP-006 evidence, meaning the standards covering system restoration plans and the reliability coordinator's role in restoration, is assembled after the fact from notes, sign in sheets, and someone's recollection of what happened when.

What it replaces or shrinks

  • Hand construction of the annual drill scenario and its scripted contingency injects
  • Conference room and bridge line delivery, replaced by each desk running its own procedures from its own control center
  • Facilitator judgment as the only scoring method, replaced by scoring against an optimal restoration sequencing baseline
  • After the fact assembly of NERC EOP-005 and EOP-006 drill evidence from notes and sign in sheets
  • Manual writing of per participant after action findings
  • Shrinks the travel and scheduling coordination required to get multiple member operators into one room on one day

Why it is safer

This is the one use case in this set with a real, traceable safety mechanism, and it is still system level rather than personal. Restoration is the most dangerous procedure the grid runs: crews perform switching on a system with unfamiliar configuration and uncertain energization status, and a desk that sequences a cranking path wrong sends field crews to the wrong place under the worst conditions. Practicing quarterly and unscripted, against real restoration physics, is how a mis switch during a real restoration becomes less likely and how restoration finishes sooner, which shortens the period customers are without power.

Counted in units you already track:

  • Switching operations performed during restoration, and specifically the count executed out of sequence or reversed because a desk had to correct course
  • Energized area entries by field crews during restoration, when energization status is least certain
  • Night driving hours and road miles driven by crews responding to a restoration, which shrink as coordinated restoration time shortens
  • Permits to work issued under restoration conditions, where the normal planning window does not exist

Man-hours it gives back

Scenario construction, facilitation, travel, and evidence assembly hours come back to the training organization and to every participating member, and the training director spends the time on after action coaching instead of on logistics.

HOURS AVOIDED PER YEAR = drills per year x scenario construction hours, plus drills per year x participants x travel hours per participant, plus drills per year x facilitator and observer hours, plus drills per year x hours spent assembling EOP-005 and EOP-006 evidence afterward, minus the operator hours actually spent in the simulator, which increase on purpose because more practice is the point.

The numbers we need from you to run that formula:

  • Drills run per year today, and how many you would run if scenario construction were not the constraint
  • Hours spent building one drill scenario and its injects, and by how many people
  • Participating desks per drill, across the ISO and its transmission and generator owners, and travel hours per participant
  • Hours spent assembling drill evidence for NERC EOP-005 and EOP-006 after each run
  • Loaded hourly rate for a system operator, a training instructor, and a compliance analyst

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Training and facilitation laborscenario construction, facilitation, and after action writing hours avoided x your loaded instructor and operator rate
Travel and logisticsparticipant travel hours and trips avoided x your loaded operator rate plus your actual travel and per diem cost per trip
Compliance evidence laborevidence assembly hours avoided x your loaded compliance analyst rate, across the ISO and each participating member
Restoration durationyour own estimated cost per hour of a regional restoration, including value of lost load, x the hours you believe better practiced sequencing removes, a share you set from your own drill scores
Member coordination efforthours each member spends today preparing for and reconciling after a joint drill x their loaded rates x number of participating members

Reliability and maintenance

Reliability
This touches restoration duration directly, which is the tail of your outage duration statistics and the part that dominates customer minutes lost in a major event. It does not change forced outage rate or the probability of the initiating event, only how fast and how correctly the system comes back once one has occurred.
Maintenance
The maintenance link is the blackstart resource itself and the restoration plan. Running the plan quarterly against real network physics surfaces cranking paths that no longer work, blackstart units whose capability has drifted, and procedure steps that reference equipment that has changed, which is degradation you would otherwise find during an actual restoration.

What else it moves

ComplianceNERC EOP-005 and EOP-006 drill evidence is produced by the run itself rather than reconstructed afterward, for the ISO and for every participating member, from a single record of what each desk actually did and when.
WorkforceOperators who will run a restoration once in a career get repeated, scored practice, and the training organization can see who is ready and who needs coaching before the event rather than after.
CustomerRestoration duration is what customers experience in a major event, and hours removed from a regional restoration are hours of customer outage removed.
Insurance and riskA documented, scored, quarterly restoration exercise program across the ISO and its members is a materially different risk posture than an annual scripted tabletop, and it is documented in a form your risk function can use.

What it costs you, stated honestly

You pay for the scoped engagement that builds and runs this and the simulation compute, for building the restoration physics model on your actual network model and keeping it current as the system changes, for integration into your training and compliance document systems, and for the operator hours spent in the simulator, which are real hours from a staffing plan that is already tight. Member participation is a negotiation, not a purchase, and getting transmission and generator owner desks to commit quarterly is the part that takes the longest.

How to build the payback case

Payback on labor and travel alone is straightforward to compute and usually modest. The case is really made on restoration duration, so decide up front what an hour of regional restoration is worth to you and to your regulator, and let the drill scores tell you whether that hour is moving.

This is a planning model built from your drill history, your participant counts, and your own view of restoration cost, not a vendor claim. Run two or three quarters, look at the scores against the optimal baseline, and re-run the case with what you actually see.
UC 1.8 Blackstart and Restoration Sequencing Advisor

What happens today, without this

An operations engineer owns the restoration plan. It is a document, refreshed on a periodic cycle from a planning study, and it assumes a system configuration that starts drifting the day it is filed. Tie line outages, generator test status, and blackstart unit availability are tracked in separate spreadsheets and emails. Drill preparation takes weeks of pulling that information together, and the sequence that gets drilled is often the filed one rather than the one that would actually work tonight.

What it replaces or shrinks

  • Manual redlining of the filed restoration document against current outage schedules and equipment status
  • Spreadsheet tracking of blackstart unit test status and tie line availability
  • Step by step hand verification of a cranking path against the one-line
  • Hand building the data package for each drill
  • Shrinks the periodic study refresh cycle by keeping the sequence current between formal studies

Why it is safer

The safety mechanism here is indirect but specific. A restoration sequence built on a stale configuration does not fail on paper, it fails in the field, mid-restoration, with crews already deployed and the system in an abnormal state. Discovering a mis-assumption during a validation run rather than during a real restoration is what keeps crews from executing steps against equipment that is not where the plan says it is.

Counted in units you already track:

  • Switching operations executed against an assumed configuration and then reversed
  • Permits to work and clearances issued during restoration against stale isolation assumptions
  • Energized area entries by crews executing restoration steps in an abnormal system state
  • Night driving hours for staff mobilized during restoration and drills

Man-hours it gives back

Plan maintenance and drill preparation hours come back to the operations engineers who own the restoration plan.

HOURS AVOIDED PER YEAR = plan revisions per year x engineer hours per revision, plus drills per year x preparation hours per drill x staff involved in preparation, plus hours per year spent reconciling outage schedules and generator test status against the filed plan, minus the licensed operator and engineer review time that stays, because no generated sequence is adopted without it.

The numbers we need from you to run that formula:

  • Restoration plan revisions per year and engineer hours per revision
  • Drills per year, preparation hours per drill, and how many staff are involved in preparation
  • Hours per year spent reconciling equipment and outage status against the plan
  • External consultant hours or fees if any part of the restoration study is outsourced
  • Loaded hourly rate for an operations engineer and for a licensed operator reviewer

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Engineering laborplan maintenance and reconciliation hours avoided x your loaded operations engineer rate
Drill preparationpreparation hours avoided per drill x drills per year x your loaded rate for the staff involved
Consultant studiesoutsourced restoration study hours displaced x your contracted consultant rate, where you use one
Restoration durationhours of wide area restoration shortened x your own cost per hour of unserved load, a figure you supply and defend, not one we give you
Documentationhours spent assembling drill and plan evidence x your loaded rate for the compliance analyst who does it today

Reliability and maintenance

Reliability
This does not move your everyday reliability indices, and it should not be sold as if it does. It touches restoration duration after a wide area event, which is a rare, extreme consequence that sits outside SAIDI, the system average interruption duration index, under most major event day practices. Frame it as extreme event exposure, not as an indices improvement.
Maintenance
Blackstart capability gaps become visible on a rolling basis rather than at the next drill. When a cranking unit's blackstart test is aging or a tie line the plan depends on is out through the summer, that shows up as a scheduled item instead of a surprise on drill day.

What else it moves

ComplianceYour restoration plan review, verification, and drill obligations all ask for evidence that the plan reflects the current system. A generated validation report with a timestamp and a topology reference is that evidence.
WorkforceRestoration planning knowledge usually sits with one or two engineers. Making the sequence reproducible from the current model rather than from one person's memory is a succession issue as much as an efficiency one.
Insurance and riskDemonstrable readiness for the least practiced, highest consequence scenario is a question that comes up in both regulatory and insurance reviews after any major regional event.

What it costs you, stated honestly

You pay for the scoped engagement that builds and runs this, for integration to your energy management system model and your outage scheduling system, and for engineer time to validate generated sequences, which is heavy in the first year and never goes to zero. Nothing here is sent to the energy management system and nothing operates equipment, so the licensed operator review stays in place permanently by design. Treat that review as a permanent line item, not a pilot cost.

How to build the payback case

Payback is driven by engineering plan maintenance and drill preparation hours, which are countable from this year's timesheets and drill schedule. The value of a shorter wide area restoration is the real reason to do it and is far too uncertain to anchor a business case on.

This is a planning model built from your engineering hours, your drill schedule, and your rates, not a vendor claim. Re-run it after the first full drill cycle with the actual preparation hours and the actual review time your licensed operators needed.
UC 2.7 Blackstart Cranking Path Validation Twin

What happens today, without this

The engineer who owns the EOP-005 restoration plan updates the blackstart cranking path on a calendar cycle, working from a one line drawing, the plan document, and a binder of blackstart unit test records. Verifying that the path still works means walking the sequence step by step, calling generation and transmission planning to ask what is out of service this month, and checking cranking unit capability against numbers from the last test. In practice the drill runs against the plan as written, so a step that depends on a breaker that has been out since last fall gets discovered during the drill, or it does not get discovered at all.

What it replaces or shrinks

  • The manual step by step walkdown of the cranking sequence against the current outage schedule
  • Phone calls to generation and transmission planning to confirm what is in and out of service
  • Hand checking each cranking unit's reactive capability against the last test record
  • Shrinks the scenario building work that goes into preparing each drill
  • Assembling the evidence packet showing the drill matched the grid as operated
  • Rebuilding an alternate path by hand when a planned outage lands on the primary one

Why it is safer

The direct exposure removed is small and the indirect one is large. During an actual blackstart, operators and field crews perform a long sequence of switching operations under extreme pressure, and a step that cannot succeed on today's topology turns into improvised switching and unplanned field trips. Validating the path before the event is how you keep the restoration on the written sequence instead of on somebody's judgment at three in the morning.

Counted in units you already track:

  • Switching operations attempted on a path step that cannot succeed on current topology
  • Energized area entries by field crews sent to verify or work around equipment status during a restoration
  • Road miles driven to substations to confirm equipment availability ahead of a drill
  • Permits to work coordinated for drill support that a validated path lets you scope narrowly

Man-hours it gives back

Restoration planning and drill preparation hours come back to transmission operations engineering, and the plan owner reviews only the steps the twin flagged.

HOURS AVOIDED PER YEAR = steps in the cranking path x minutes per step to verify against the current outage schedule and equipment status, x validations per year, plus drill preparation hours per drill x drills per year, plus hours spent per year rebuilding alternate paths around planned outages, minus the plan owner's review hours on flagged steps.

The numbers we need from you to run that formula:

  • Number of steps in each documented cranking path and how many paths you maintain
  • Minutes an engineer spends verifying one step today, including the phone calls
  • Drills run per year and the preparation hours behind each one
  • Times per year a planned outage forces a path rework, and hours per rework
  • Loaded hourly rate for a transmission operations engineer and for a licensed operator on drill time

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Restoration planning laborengineer hours avoided x your loaded transmission operations engineering rate
Drill preparation and facilitationpreparation hours avoided x your loaded rate for the staff who run the drill, plus operator hours pulled off desk x their loaded rate
Generation staff timehours your plant staff spend confirming cranking unit capability x their loaded rate
Restoration durationyour own value of customer minutes not served during a widespread restoration x the minutes you believe a validated path saves, a share you set, not us
Consulting supportyour current cost per commissioned restoration study x the studies you would no longer commission

Reliability and maintenance

Reliability
This touches restoration duration in the rarest and largest event you plan for, not day to day performance. Do not build the case on SAIDI (system average interruption duration index), because a blackstart event is almost certainly excluded from your reported figures as a major event day. Build it on the hours of restoration in a full or partial system collapse and on your own value of lost load.
Maintenance
The twin shows which restoration path steps depend on equipment that is chronically out of service, which gives maintenance planning a reason to prioritize restoration path assets over equally aged assets that are not on the path. That is the difference between finding out in a drill and finding out during an event.

What else it moves

ComplianceA dated validation record showing the drill scenario matched the topology and equipment status you actually operated, which is exactly what an examiner reviewing your restoration plan asks to see.
WorkforceRestoration plan knowledge usually lives with one or two engineers. Putting the verification into a repeatable model means the plan survives their retirement.
Insurance and riskA documented, currently validated restoration capability is a question your insurers and your board ask after every regional event elsewhere in the country.

What it costs you, stated honestly

You pay for the GridCORTEX simulation service, for integration into your topology model, your outage scheduling system, and your blackstart unit test records, and for engineering and operator time to compare the twin's result against a drill you have already run. The integration into outage scheduling is usually the larger and slower line item, because equipment status has to arrive automatically or the whole benefit evaporates.

How to build the payback case

Payback is driven by engineering and drill preparation labor, because those hours are on a timesheet you can pull. Avoided restoration time is the bigger number and the one your finance team will trust least, so carry it as upside.

This is a planning model driven by your topology, your outage schedule, and your rates, not a vendor claim. Re-run it with the actuals from your first validated drill before you commit to a program size.
Each of these opens in full on the use case page, alongside the integration plan, the data ask, the path to production, and the operator console. Open the use case library.
For Your Architects and Data Owners
Run this at your utility

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 multi-party restoration simulator for the ISO/RTO and its member operators. Each desk runs its own procedures against live restoration physics on the real network model, with an AI adversary injecting unscripted failures; output is scored drills and NERC EOP-005/006 evidence every run. The demo above uses synthetic data; everything below describes what the real deployment needs from your organization.

Systems it connects to

Your systemTypical productsHow we connect
Energy Management System (EMS) / transmission SCADAAspenTech OSI monarch, GE e-terrascheduled file export (CSV or CIM XML)
Document and knowledge storesblackstart plans, restoration procedures, prior drill recordsdocument upload
SCADA historianAVEVA PI System, GE Proficyhistorian mirror (one-way feed)
Plant control (DCS) for generationblackstart unit capability and test recordsdocument upload
Planning and study toolsPSS/E, PowerWorld, TARAscheduled file export (CSV or CIM XML)
Asset / work management (EAM/CMMS)IBM Maximo, SAP PM, Hitachi Asset Suitedatabase replica refreshed nightly

Data it needs from you

How it runs on your systems

Blackstart plans are highly sensitive, so this runs fully isolated with no internet connection, on-premises or in a dedicated enclave, with member desks connecting through the ISO's secured channels. It is simulation only, with no connection to production control systems.

Path to production

Weeks 1-6
Build the isolated environment and load models and procedures; CEII and member data-sharing approvals are the usual gate.
Weeks 7-12
Recreate the latest annual joint drill scripted, with the ISO desk and member operators validating realism.
Week 13
Run the adversarial session with three unscripted injections; same-day findings drive the go or no-go.
Months 4-6
Harden the environment, onboard more member desks, and formalize scoring and NERC evidence outputs.
Months 7-9 onward
In production: quarterly unscripted joint drills from every participant's own control center, each producing EOP-005/006 evidence.

What we need from your team

Full integration, data, and timeline detail for each use case in this scenario: UC 20.7 · UC 1.8 · UC 2.7
For Your Operators and Dispatchers
Where you will see it and how you say yes

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 ISO director of operations training in the GridCORTEX console:

GridCORTEX ConsoleSigned in: the ISO director of operations training
Notifications
Q3 joint blackstart drill scored: restoration 22% slower than optimal baseline; 2 of 3 unscripted injects mishandled
Daily model refresh complete; all connected feeds healthy
Recommendation
Schedule the Q4 joint drill with 3 member transmission operators
  • Q3 re-energized the cranking path 47 minutes behind optimal
  • The breaker-failure inject was mishandled by 2 desks
  • Each run produces NERC EOP-005 and EOP-006 evidence automatically
✓ Schedule Q4 drillModifyDecline
After you approve: The drill is scheduled with member training contacts and the scenario loads on the ISO network model, and an audit entry records who approved it and why.
Computed from data as of 17:42:10 local; every card shows the timestamp of the data behind it.

What happens when you hit approve

Approve schedules the drill in the simulator and notifies member training contacts, who confirm participation in their own processes. The simulator is fully separate from the production EMS; evidence files to the compliance document store as drafts for the training director.

How you tell it what it cannot see

Drills are console-driven: the director picks participants, date, and inject count. Network model updates flow automatically from the ISO's model export.

Live data, not stale data

Each run loads the latest approved network model export, not live SCADA; every drill report shows the model vintage it ran on.

Where it lives day to day

Lives in the GridCORTEX console, with evidence filed in the compliance document store; a scored drill report emails each participant's training lead. 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 Gap: Why Your Existing Systems Don't Already Do This

The fair question from any ISO or TO: "We have a dispatcher training simulator, a restoration plan, and we run the NERC-required drills, what's new here?" Here's the honest answer.

What you own keeps doing its job

  • The DTS (dispatcher training simulator), the physics engine of record for operator training. Nothing changes; the drill runs THROUGH it.
  • The restoration plan & cranking path studies, engineering documents of record, updated on their cycle.
  • NERC EOP-005 program, the drill requirements, documentation, and audits continue.
  • Your operators and drill coordinators, the judgment being exercised is the whole point.

The gap GridCORTEX fills, above them, not instead of them

  • Joint drills are scheduling nightmares, so they happen once a year. Getting the ISO, GenCos, and TOs into one exercise takes months of coordination. A shared simulation layer makes the joint drill a monthly event, not an annual one.
  • The DTS models YOUR system, not your neighbors'. Real restoration is multi-party. The drill you just watched had three organizations in one synthetic grid; no single DTS does that.
  • Injects are hand-built. The mid-restoration unit trip was generated, timed, and scored automatically, a drill master's semester of prep, on demand.
  • Improvised re-sequencing is where drills (and real events) fail. The re-sequencing advisor computed the recovery path in seconds; that capability doesn't exist in the binder or the DTS.
  • EOP-005 evidence assembles itself. Every action, decision, and timing captured (Relay traces) into the compliance package while the drill runs, not in the two weeks after.
Accent, don't replace: GridCORTEX drives scenarios, injects, coaching, and scoring ABOVE your DTS and your restoration plan · your operators make every call · and the evidence package lands in your EOP-005 program automatically. The drill gets harder, more frequent, and cheaper, all at once.
Under the Hood: What GridCORTEX Took Into Account in This Scenario

When someone asks "what did it actually calculate?", this is the list. In the simulation these factors drive the storyline; in a pilot they are computed from your restoration plan, network model, relay settings, and unit data.

🔌 Cranking Path Validation

  • Path options ranked: blackstart unit capability vs. path charging requirements, transformer energization inrush, and relay settings along every segment
  • Ferranti rise on lightly loaded lines, which segments can be energized open-ended and which need reactive absorption first
  • Load pickup block sizing against the island's frequency response, 5 MW blocks tonight, computed not guessed
  • Station-service requirements and critical timing for the next-start units

🏝 Island Operation

  • Frequency management of a small island: governor response, load-frequency sensitivity, and the trip margins that make 59.2 Hz survivable or fatal
  • Voltage control with minimal reactive resources, capacitor and reactor switching sequencing
  • Re-sequencing after the unit trip: shed which blocks, hold which cranks, re-route which path; computed against the live island state
  • Synchronization: phase angle, frequency, and voltage matching at the tie before the interconnection reclose

🎯 The Drill Layer

  • Inject generation: timed contingencies (unit trip, relay misoperation, comms loss) calibrated to the drill's training objectives
  • Multi-party coordination: ISO, GenCo, and TO actions in one shared synthetic grid, each seeing their own view
  • Scoring: every action timed against plan, every deviation classified as improvement or error
  • Coaching mode: the advisor can explain WHY each step is next, turning the drill into training, not just testing

🏛 Compliance & Governance

  • NERC EOP-005 drill evidence assembled live: participants, scenarios, actions, timings, findings
  • Every recommendation traced (NeMo Relay); the audit trail IS the drill record
  • Runs on the NVIDIA Agent Toolkit: Omniverse-class grid twin for the shared simulation, cuOpt for sequencing, OpenShell governance so the simulator can never touch the real EMS
  • Findings feed the restoration plan's next revision, the drill closes its own loop

Presenter's one-liner: "Three control rooms, one black grid. The agent validated the cranking path, sized every load pickup, survived a drill-master's unit trip by re-sequencing in seconds, and synchronized back to the interconnection, while writing its own NERC evidence package. A drill that takes a year to schedule, on demand. That's what you just watched."

GridCORTEX Live Scenario Demo · Synthetic data throughout, no ISO, utility, or actual restoration plan is depicted · The simulator never connects to real EMS/SCADA control paths · SoftServe + NVIDIA · Created by Ronnie Mauldin, NVIDIA Solutions Director, Power & Utilities, SoftServe · JUL 2026