DER orchestration
Installed capacity without coordinated dispatch is a liability dressed as an asset
The US has installed over 30 GW of distributed generation and storage, but less than 20% participates in organized markets. The gap is not hardware or communication. It is the orchestration layer that converts thousands of individual assets into a dispatchable fleet. Without coordinated dispatch, DERs create grid management challenges instead of solving them.
A megawatt of uncoordinated DER is a problem. A megawatt of orchestrated DER is a power plant.
Distributed generation without distributed intelligence
30 GW of behind-the-meter generation and storage is installed across US homes and businesses. Most operates on static time schedules, unaware of grid conditions, wholesale prices, or neighboring device behavior. The gap between installed DER capability and realized grid value grows every quarter as deployments accelerate but orchestration stagnates. Utilities see DER as a planning problem; the market is waiting for someone to make it an optimization problem.
Installed capacity without coordinated dispatch is a liability dressed as an asset.
How AI orchestrates distributed energy resources
Discover and onboard assets
Automated discovery of DER capabilities through smart inverter protocols and metering data. Each asset gets characterized by response speed, capacity, availability windows, and physical constraints.
Create virtual power plant portfolios
Group assets into dispatchable portfolios that meet market participation requirements. A virtual power plant needs minimum capacity, response time guarantees, and performance history.
Optimize portfolio dispatch strategy
Determine which market products each VPP targets: energy arbitrage, frequency regulation, capacity, or demand response. Strategy shifts as market conditions and asset availability change.
Execute and verify performance
Dispatch commands flow to individual assets while aggregate performance is measured against market commitments. Real-time verification ensures the VPP delivers what it promises.
Static DER schedules vs AI-coordinated dispatch
| Metric | Manual Process | AI-Optimized |
|---|---|---|
| Forecasting accuracy (MAPE) | 8-10% | 3.21% |
| Decision cycle time | 4-8 hours | 15 minutes |
| Billing query resolution | 2-3 days | < 5 minutes |
| Residual value model refresh | Quarterly | Daily |
| Operational data utilization | < 30% | 98%+ |
| Margin capture potential | Baseline | 5-12% uplift |
Key players
Sunrun
900K+ residential solar+storage systems; largest distributed fleet in US.
Generac
PWRcell + Concord DERMS; residential backup becoming grid resource.
SolarEdge
Smart inverter platform; 3M+ residential systems with grid-services capability.
Sunnova
Solar+storage servicer; VPP-enrolled fleet across Texas and California.
What we have shipped in this space
Attribution — TS2Vec-Similar Day forecasting
Production system forecasting ERCOT day-ahead prices every 5 minutes. Trained on 2 years of SCED interval data, weather, and transmission constraints.
Residuals — operational telemetry to financial instruments
Battery degradation curves, solar performance decay, and generation asset condition converted from operational telemetry into residual instruments that reflect actual state.
Our systems convert operational telemetry from distributed assets into the state information that dispatch optimization requires. Combined with price forecasting, the platform determines both what the asset can do and what it should do.
Telemetry reveals capability. Price forecasting reveals opportunity. Dispatch captures both.
Ready to instrument your operations?
Map your current DERS coordination efficiency. We'll show you the specific moments where assets worked against each other and the margin recovery possible through real-time orchestration.
Schedule an auditExplore more
Related activities
Industrial load flexibility→
Industrial demand response programs pay $50-200/MWh for load curtailment during grid stress events. ...
Industrial power management→
Industrial facilities pay 60-70% of their electricity bill through demand charges, not energy consum...
Grid-scale battery dispatch→
Grid-scale batteries co-located on the same node, with identical chemistry and capacity, show 30-40%...
Common questions about AI in distributed energy resources
How much behind-the-meter solar can a utility interconnect before voltage regulation becomes a constraint?
Most distribution feeders can absorb 25–35% DER penetration before voltage regulation issues emerge; above 40%, dynamic reactive support or voltage control measures become necessary. Weak feeders (high line impedance) hit constraints at 15–20% penetration, requiring grid reinforcement.
What is the maximum instantaneous curtailment a residential DER portfolio can absorb without customer complaints?
Residential customers tolerate 5–15 minutes of generation curtailment per week without complaint; sustained curtailment beyond 20 minutes or occurring during high-bill periods triggers escalating dissatisfaction. Transparent communication of curtailment events reduces complaint thresholds by 30–40%.
How does rooftop solar and battery penetration above 30% affect feeder voltage stability?
Feeders with 30%+ solar/battery penetration experience 2–4x more voltage swings during cloud transients and evening ramp events than undeployed feeders. Voltage ride-throughs (±5% nominal) require automated reactive support or feeder sectionalizing; unmanaged feeders risk equipment damage.
What is the optimal dispatch order for mixed DER portfolios with different response times?
Battery systems (sub-100ms response) should stage first, followed by solar curtailment (5–30s), then load shifting (1–5 minutes) and generator dispatch (2–10 minutes). Optimal sequencing reduces total energy waste by 12–20% versus simultaneous dispatch across all DER types.