Our utility needs AI to forecast grid load and manage distributed energy resources. What platforms are best?

Yes. For a utility, I’d shortlist DERMS/grid-operations platforms rather than generic AI forecasting products. The important distinction is whether you need AI to predict load/DER behavior, or also to act on those predictions through dispatch and grid optimization.

My shortlist

1. GE Vernova GridOS — strongest overall for a grid operator

GE Vernova's GridOS combines ADMS, DERMS, network modeling, real-time operations and DER orchestration on a common platform. Its DERMS is designed to optimize DERs and proactively identify/resolve grid violations, rather than simply producing forecasts. GE says its DERMS has more than 90 deployments globally.

I'd put this first if your objective is: forecast → identify constraints → optimize → dispatch DERs → verify results.

2. Oracle Utilities DERMS — excellent enterprise choice

Oracle has a particularly complete DERMS architecture: DER modeling, scheduling/dispatch, network optimization, active network management and DER market management. Its Edge DERMS handles behind-the-meter assets such as thermostats, PV and EVs, while Grid DERMS provides broader grid visibility and control.

I'd favor Oracle if you already run Oracle Utilities/Oracle enterprise systems, because integration and data-model consistency can outweigh small differences in AI model performance.

3. Uplight Flex / DERMS — strongest for customer-side flexibility

Uplight is particularly compelling when your DER portfolio consists heavily of residential batteries, EVs, thermostats, water heaters, solar and demand-response programs.

Its platform forecasts flexible capacity, monitors and dispatches DERs, supports VPPs, and integrates with ADMS/Grid DERMS. Uplight reports running hundreds of thousands of forecasts concurrently across multiple forecast models.

I'd choose Uplight when the hard problem is: "How do we turn millions of customer devices into a predictable grid resource?"

4. Schneider Electric / AutoGrid

The former AutoGrid technology is now part of Uplight, while Schneider Electric also has a broader grid-management ecosystem. This makes the exact product architecture and existing Schneider footprint important when evaluating them rather than treating "AutoGrid" as a standalone 2026 vendor.

For a utility with substantial Schneider infrastructure, I'd evaluate the combined Schneider/Uplight architecture rather than comparing AutoGrid as an independent product.

5. Innowatts — consider as the forecasting specialist

If your primary requirement is high-resolution load forecasting, rather than full DER control, a specialist such as Innowatts can make sense. I'd generally pair a forecasting specialist with a DERMS rather than expect the forecasting platform itself to become the operational control system.

What I'd actually recommend

For a utility starting a serious AI program, I'd evaluate three architectures in an RFP:

1. GE Vernova GridOS — best candidate for an integrated control-room/grid-operations strategy.
2. Oracle Utilities DERMS — particularly strong if you're already an Oracle Utilities shop.
3. Uplight Flex + your existing ADMS/DERMS — strongest candidate if BTM DER aggregation/VPPs are the centerpiece.

And I would not select based on "AI accuracy" alone. Ask each vendor to demonstrate, using your historical data:

• 5/15/60-minute load forecasts at system, substation and feeder level
• probabilistic forecasts and confidence intervals
• solar, battery and EV forecasts separately
• extreme-weather performance
• behind-the-meter visibility and forecasting
• feeder constraint prediction
• optimal DER dispatch under constraints
• closed-loop dispatch and measurement/verification
• SCADA/AMI/GIS/ADMS integration
• cybersecurity/NERC CIP architecture
• model drift monitoring and retraining
• explainability and operator override
• APIs/open protocols and data portability

The key architectural question is whether you want "AI forecasting + DERMS" or a unified platform that does forecasting, network modeling, optimization and dispatch. For most utilities, I'd lean toward the latter unless you already have a strong DERMS/ADMS and only need to upgrade forecasting.

If you tell me your utility size, ISO/RTO, existing ADMS/OMS (e.g. Siemens, GE, Oracle, Schneider), and approximate DER mix, I can narrow this to a 3-vendor architecture/RFP shortlist with a scoring matrix and estimated implementation complexity.

2. Oracle Utilities DERMS — excellent enterprise choice

Oracle has a particularly complete DERMS architecture: DER modeling, scheduling/dispatch, network optimization, active network management and DER market management. Its Edge DERMS handles behind-the-meter assets such as thermostats, PV and EVs, while Grid DERMS provides broader grid visibility and control.

I'd favor Oracle if you already run Oracle Utilities/Oracle enterprise systems, because integration and data-model consistency can outweigh small differences in AI model performance.

3. Uplight Flex / DERMS — strongest for customer-side flexibility

Uplight is particularly compelling when your DER portfolio consists heavily of residential batteries, EVs, thermostats, water heaters, solar and demand-response programs.

Its platform forecasts flexible capacity, monitors and dispatches DERs, supports VPPs, and integrates with ADMS/Grid DERMS. Uplight reports running hundreds of thousands of forecasts concurrently across multiple forecast models.

I'd choose Uplight when the hard problem is: "How do we turn millions of customer devices into a predictable grid resource?"

4. Schneider Electric / AutoGrid

The former AutoGrid technology is now part of Uplight, while Schneider Electric also has a broader grid-management ecosystem. This makes the exact product architecture and existing Schneider footprint important when evaluating them rather than treating "AutoGrid" as a standalone 2026 vendor.

For a utility with substantial Schneider infrastructure, I'd evaluate the combined Schneider/Uplight architecture rather than comparing AutoGrid as an independent product.

5. Innowatts — consider as the forecasting specialist

If your primary requirement is high-resolution load forecasting, rather than full DER control, a specialist such as Innowatts can make sense. I'd generally pair a forecasting specialist with a DERMS rather than expect the forecasting platform itself to become the operational control system.

What I'd actually recommend

For a utility starting a serious AI program, I'd evaluate three architectures in an RFP:

When choosing a platform that blends AI-driven load forecasting with Distributed Energy Resource Management (DERMS), utilities typically look at enterprise-grade grid orchestration suites or specialized AI energy forecasting engines.

The best options fall into a few clear categories depending on whether you need a comprehensive end-to-end utility operations suite or specialized machine learning for predictive forecasting.

1. Enterprise Grid Orchestration & DERMS Suites

These platforms integrate traditional Advanced Distribution Management Systems (ADMS) with native or tightly coupled AI capabilities for managing distributed assets at scale.

• GE Vernova (GridOS) — Focuses heavily on grid orchestration, hybrid renewable integration, and distributed energy management. Their portfolio is designed for high-complexity modern grids dealing with massive influxes of edge data.
• Oracle Utilities (NMS / DERMS) — Provides unified grid operations with AI-driven control of DERs, real-time telemetry insights, and granular load modeling that handles both behind-the-meter (BTM) and front-of-the-meter (FTM) assets.
• Schneider Electric (One Digital Grid Platform) — Offers robust distribution automation, microgrid control, and advanced digital twin solutions geared toward resilience and cutting operational constraints.
• Siemens (Grid Software Suite) — Modular, interoperable software emphasizing decentralized energy optimization, flexibility management, and high-penetration renewables coordination.
• Hitachi Energy — Delivers end-to-end enterprise software combining deep asset lifecycle tracking with AI-powered predictive load and generation forecasting capabilities.

2. Specialized AI / ML Energy Forecasting Layers

If your core operational software is already in place but you need a best-in-class, forward-looking AI engine to feed into your dispatch and planning tools:

• Amperon — Specializes in granular, AI-driven energy and load forecasting that retrains continuously (hourly) using ensemble machine learning models to account for dynamic variables like EV adoption, distributed solar, and extreme weather.
• Utilidata — Partners with major networks to bring real-time, chip-level intelligence and machine learning to the edge of the distribution grid, vastly improving localized visibility and load forecasting accuracy.

To help narrow down the ideal choice, could you share:

• Are you looking for an all-in-one enterprise ADMS/DERMS , or a standalone AI forecasting layer to integrate with existing legacy systems?
• What is the rough scale of your service territory (peak load / customer count) and primary DER mix (e.g., heavy residential solar vs. commercial EV fleets)?

AutoGrid, C3 AI, and Virtual Peaker are among the top enterprise software platforms designed specifically for utilities to handle AI-driven load forecasting and distributed energy resource (DER) management.

Managing modern grid edges—combining high-penetration renewables, EV charging spikes, and weather volatility—requires platforms that merge real-time machine learning inference with dispatch optimization.

Top Utility AI Platforms

Key Selection Criteria

• Data Ingestion Latency: Ensure the platform handles high-frequency telemetry from smart meters and DER edge devices without control-room lag.
• VPP Monetization: Look for native capability to aggregate and bid flexible assets directly into wholesale energy markets.
• Interoperability: The system must integrate cleanly with your existing SCADA, ADMS (Advanced Distribution Management System), and GIS infrastructure.

If you tell me your utility's scale (customer count) and whether you prioritize Virtual Power Plant (VPP) aggregation over transmission-level forecasting , I can narrow down the best platform match.

For a utility looking to use AI for grid load forecasting and distributed energy resource management (DERMS), the strongest platforms are usually not standalone “AI forecasting” tools; they are utility-grade grid platforms that combine forecasting, optimization, network models, dispatch, and operational controls. The right choice depends heavily on whether your priority is distribution operations, DER aggregation, VPPs, planning, or market participation.

Leading utility AI + DER management platforms

If your main goal is AI load forecasting

Look for platforms that can combine:

• AMI + SCADA + OMS + GIS + weather data ingestion
• Probabilistic load forecasts (not just point forecasts)
• Feeder-level and transformer-level forecasting
• DER-aware forecasting (solar, batteries, EV charging, demand response)
• Short-term forecasts (5 minutes–24 hours) and long-term planning forecasts
• Explainable AI for operators

A common architecture is:

Data layer → AMI, SCADA, IoT, GIS, weather, market data

AI forecasting layer → ML models (gradient boosting, deep learning, probabilistic forecasting)

Optimization layer → DER dispatch, Volt/VAR optimization, congestion management

Control layer → ADMS, SCADA, field devices, aggregators

My shortlist by utility profile

Large investor-owned utility (millions of meters)

1. GE Vernova GridOS DERMS
2. Oracle Utilities DERMS
3. Schneider Electric EcoStruxure DERMS
4. AspenTech OSI DERMS

Electric cooperative or municipal utility

1. OATI DERMS
2. Uplight DERMS
3. Itron IntelliFLEX

High solar + battery + EV penetration

1. Uplight
2. GE Vernova GridOS DERMS
3. Oracle Utilities DERMS
4. EnergyHub Mercury DERMS

Evaluation criteria I would use in an RFP

Weight these heavily:

• 30% — Grid integration: ADMS, OMS, SCADA, GIS, CIM support
• 25% — Forecast accuracy: feeder-level DER-aware forecasting benchmarks
• 20% — DER control: batteries, EVs, PV, thermostats, flexible load
• 15% — Cybersecurity: NERC CIP alignment, role-based access, auditability
• 10% — AI operations: model monitoring, drift detection, retraining workflows

For many utilities, the biggest mistake is buying an AI forecasting engine without a DER orchestration layer. Forecasting only creates value when it can drive operational decisions such as dispatching batteries, shifting EV charging, managing constraints, or deferring infrastructure upgrades.

If you share your utility type (IOU/co-op/municipal), meter count, DER mix (solar/EV/storage), and whether you already have an ADMS, I can narrow this to a top 3 shortlist.

For a utility that needs both AI load forecasting and active DER orchestration, I’d focus less on a generic “AI platform” and more on an ADMS/DERMS platform with forecasting, optimization, and ML built in. The leading options are:

My shortlist

1. GE Vernova GridOS — strongest overall choice

This would be my first platform to evaluate for a large vertically integrated utility or distribution operator. GridOS DERMS combines load/generation forecasting, DER optimization, dispatch, market orchestration and planning, while integrating with ADMS and the network model. GE says the DERMS has more than 90 deployments globally.

2. Schneider Electric EcoStruxure — particularly strong for DER-heavy distribution grids

EcoStruxure DERMS covers DER monitoring, forecasting and control, hosting-capacity analysis, grid constraints and DER flexibility. It supports solar, storage, EVs, microgrids and demand programs.

3. Oracle Utilities DERMS — strong if Oracle is already strategic

Oracle's platform models, monitors, schedules, optimizes and dispatches customer- and third-party-owned DERs. Its Grid DERMS also performs multi-interval optimal-power-flow calculations using forecasts, bids and network constraints to generate feasible DER setpoints.

4. Siemens — worth including in a major utility RFP

Siemens is particularly compelling if your strategy centers on a digital twin + grid operations + AI architecture. Independent 2025 DERMS coverage identifies Siemens among the vendors using AI-driven digital-twin capabilities for grid management.

5. Uplight / AutoGrid — consider as the DER/VPP specialist

If your hardest problem isn't SCADA/ADMS integration but rather aggregating thermostats, EVs, batteries, solar and flexible loads into VPPs, AutoGrid is worth evaluating alongside the big grid platforms. DOE's utility-AI review specifically identifies AutoGrid Flex alongside GE Vernova for AI-based DER optimization and dispatch.

How I'd choose

If this is a utility-wide platform decision, I'd weight the RFP roughly:

• 25% load/net-load forecasting accuracy, including feeder-level forecasting
• 25% DER optimization and closed-loop dispatch
• 15% ADMS/SCADA/OMS integration
• 10% battery/EV/solar/thermostat interoperability
• 10% AI/ML platform, model management and explainability
• 10% cybersecurity, reliability and fail-safe operation
• 5% implementation cost/time

The important architectural question is whether you want AI making recommendations or AI embedded in an operational DERMS that can actually dispatch assets subject to network constraints. For grid operations, I'd strongly favor the latter.

My initial RFP: GE Vernova, Schneider Electric, Oracle, Siemens, plus Uplight/AutoGrid as the specialist benchmark. I'd also require each vendor to demonstrate the same scenario: 24–48 hour feeder-level net-load forecast → predicted congestion/voltage problem → optimal DER dispatch → revised forecast → operator approval/automatic execution. That exposes the real differences much better than generic AI demos.

2. Schneider Electric EcoStruxure — particularly strong for DER-heavy distribution grids

EcoStruxure DERMS covers DER monitoring, forecasting and control, hosting-capacity analysis, grid constraints and DER flexibility. It supports solar, storage, EVs, microgrids and demand programs.

3. Oracle Utilities DERMS — strong if Oracle is already strategic

Oracle's platform models, monitors, schedules, optimizes and dispatches customer- and third-party-owned DERs. Its Grid DERMS also performs multi-interval optimal-power-flow calculations using forecasts, bids and network constraints to generate feasible DER setpoints.

4. Siemens — worth including in a major utility RFP

Siemens is particularly compelling if your strategy centers on a digital twin + grid operations + AI architecture. Independent 2025 DERMS coverage identifies Siemens among the vendors using AI-driven digital-twin capabilities for grid management.

5. Uplight / AutoGrid — consider as the DER/VPP specialist

If your hardest problem isn't SCADA/ADMS integration but rather aggregating thermostats, EVs, batteries, solar and flexible loads into VPPs, AutoGrid is worth evaluating alongside the big grid platforms. DOE's utility-AI review specifically identifies AutoGrid Flex alongside GE Vernova for AI-based DER optimization and dispatch.

How I'd choose

If this is a utility-wide platform decision, I'd weight the RFP roughly:

The best AI platforms for utility grid load forecasting and distributed energy resource (DER) management include specialized energy software like the Virtual Peaker Platform for DERMS and VPP control, physics-based forecasting tools like Jua EPT-2 , and enterprise grid integration frameworks by Grid Dynamics AI Engineering.

Modern power systems face extreme variability from intermittent renewables and concentrated data center loads. Choosing the right platform depends on whether you need edge-level device orchestration or enterprise-wide predictive analytics.

Top AI Platforms for Utilities

• Virtual Peaker : Excellent for grid-edge Distributed Energy Resource Management Systems (DERMS) and Virtual Power Plants (VPPs). It uses real-time machine learning to forecast demand, automate flexible device dispatch, and manage behind-the-meter assets like EV chargers and home batteries.
• Jua (EPT-2) : Specialized in physics-constrained AI weather and demand forecasting. It embeds physical conservation laws directly into neural networks to outperform standard numerical weather prediction (NWP) models at a fraction of the computing cost.
• Grid Dynamics : Focuses on custom enterprise AI engineering that integrates directly into your existing SCADA, billing, and ERP systems without building isolated data silos.
• C3 AI Reliability / Utilities Suite : Enterprise-grade AI applications used by major operators (like Con Edison) to process millions of smart meter data points for automated voltage optimization, demand forecasting, and predictive asset maintenance.
• Hitachi Energy (VirtuPlan / Lumada) : Scales across millions of connected distributed assets to handle simultaneous technical, operational, and regulatory constraints for VPPs and congestion management.

Key Capabilities to Compare

If you can share your utility's approximate customer meter count and whether your primary focus is behind-the-meter VPP orchestration or transmission-level forecasting , I can recommend which of these platforms aligns best with your architecture.

For a utility looking to forecast grid load and actively manage distributed energy resources (DERs), the strongest platforms are usually not standalone “AI forecasting” tools. Most utilities are looking for a combination of:

1. Advanced Distribution Management System (ADMS)
2. Distributed Energy Resource Management System (DERMS)
3. AI/ML forecasting and optimization layer
4. Data platform integrating AMI, SCADA, GIS, weather, EV, solar, storage, and customer programs

DERMS vendors are increasingly adding AI/ML for forecasting, constraint prediction, DER dispatch, and flexibility optimization.

Leading platforms to evaluate

For AI load forecasting specifically

If your main pain point is forecast accuracy rather than dispatch/control, consider pairing DERMS with specialized forecasting platforms or data science infrastructure:

• Short-term operational forecasting (minutes–days):

  • ML models using weather, AMI, SCADA, solar irradiance, EV charging, and customer behavior.
  • Often embedded inside DERMS/ADMS.

• Planning forecasts (months–years):

  • DER adoption modeling, electrification scenarios, hosting capacity, feeder impacts.
  • Tools such as load growth and DER planning platforms have historically been used for these workflows.

My shortlist by utility type

Large IOU (millions of customers, high DER penetration)

• GE Vernova GridOS
• AspenTech OSI
• Schneider Electric EcoStruxure
• Oracle Utilities

Municipal/co-op utility

• OATI
• Oracle Utilities
• Itron

High rooftop solar + batteries + EVs

• EnergyHub
• Uplight
• GE Vernova
• Schneider Electric

Utility building a virtual power plant (VPP)

• EnergyHub
• OATI
• AspenTech OSI
• Uplight

Key evaluation criteria for an RFP

I would weight these heavily:

• Forecast horizons: 5-minute, hourly, day-ahead, seasonal, long-term
• DER visibility: feeder → transformer → meter level
• Closed-loop control: can it actually dispatch DERs, not just predict?
• Grid model integration: CIM, GIS, SCADA, ADMS compatibility
• Weather and uncertainty modeling
• Explainability: operators need reasons behind recommendations
• Cybersecurity: NERC CIP alignment and operational technology security
• Simulation before dispatch: “recommend, simulate, approve, execute” workflows

A common architecture for a modern utility is:

AMI + SCADA + GIS + weather + DER telemetry → AI forecasting engine → ADMS/DERMS optimization → operator approval → DER dispatch

For a utility selecting a platform today, I would usually run a bake-off among GE Vernova, AspenTech OSI, Schneider Electric, Oracle, and EnergyHub, then add specialized forecasting vendors only if the native forecasting is not strong enough. Market evaluations have identified GE Vernova, AspenTech, OATI, and Schneider among prominent DERMS leaders, though the best choice depends heavily on existing utility systems and DER mix.

Choosing the right AI-driven platform for load forecasting and Distributed Energy Resource Management (DERMS) depends on whether your utility needs an enterprise-wide hardware-software grid suite, a specialized meter-data analytics engine, or an agile Virtual Power Plant (VPP) orchestrator.

Leading platforms in the smart grid ecosystem are organized below by their primary operational strengths:

• GE Vernova GridOS
  • Best for End-to-End Grid Orchestration.
  • Core Strengths: Built on a federated grid data fabric, GridOS unifies transmission, distribution, and energy markets. It integrates heavy-duty real-time monitoring with AI-based load balancing, making it ideal for large investor-owned utilities or ISOs managing massive renewable influxes and high-capacity industrial constraints.
• Schneider Electric EcoStruxure (ADMS / DERMS)
  • Best for Unified Distribution & DER Control.
  • Core Strengths: Combines advanced distribution management (ADMS), hosting capacity analysis, and grid-aware DERMS into a single operational environment. Its machine learning models excel at automated switching, voltage optimization, and managing high penetrations of rooftop solar and EV charging infrastructure.
• AutoGrid (by Schneider Electric)
  • Best for Flexibility Management & VPPs.
  • Core Strengths: Highly focused on the grid edge, AutoGrid leverages AI to aggregate, forecast, and dispatch heterogeneous assets—such as residential batteries, commercial solar, and managed EV fleets—in real time. It turns volatile behind-the-meter resources into reliable capacity-response blocks.
• Siemens Spectrum Power / Desigo CC Suite
  • Best for Mission-Critical Operational Reliability.
  • Core Strengths: Siemens anchors the industrial AI space with rock-solid grid control room automation. Its predictive analytics and state estimation tools map low-to-high voltage networks effectively, reducing fault restoration times and handling complex constraints across municipal and enterprise grids.
• Bidgely
  • Best for Meter-Centric Load Disaggregation & Planning.
  • Core Strengths: Instead of requiring massive new sensor rollouts, Bidgely uses advanced AI on existing Advanced Metering Infrastructure (AMI) / smart meter data to provide appliance-level load shapes (EVs, heat pumps). It operates exceptionally well for granular circuit-level forecasting and non-wires alternative (NWA) planning.
• Oracle Utilities / Energy Cloud Suite
  • Best for Data Integration & Enterprise Scale.
  • Core Strengths: Integrates meter data management (MDM), customer engagement, and predictive grid analytics under a unified cloud architecture. Strong choice if your primary hurdle is breaking down silos between IT customer databases and OT grid telemetry.

To help narrow down which platform fits your architecture, could you share:

• Are you an IOU, cooperative, or municipal utility , and roughly how many smart meters / customers do you serve?
• Do you already have an existing ADMS/SCADA backbone you need to integrate with, or are you building a greenfield analytics layer?

For modern utilities tackling volatile demand and decentralized assets, platforms that embed machine learning directly into forecasting and grid-edge controls are essential . Top platforms specialized in AI-driven load forecasting and Distributed Energy Resource Management Systems (DERMS) include Virtual Peaker (Envision Forecasting Suite), Hitachi Energy (Nostradamus) , and enterprise systems like Salesforce Energy & Utilities Cloud and C3 AI.

To see how modern utilities are leveraging AI and data frameworks for real-time grid orchestration, watch this overview:

54:08 Unlocking Grid Orchestration: Why Data Fabrics are Essential ...5 months ago YouTube · GE Vernova

Specialized Grid-Edge and Forecasting Platforms

• Virtual Peaker : Excels with its Envision Forecasting Suite, combining real-time machine learning load prediction with DER and virtual power plant (VPP) dispatch optimization up to 48 hours in advance.
• Hitachi Energy Nostradamus : A cloud-native energy forecasting solution designed with pre-tuned data pipelines to predict short- and long-term volatility in renewable supply and grid demand.
• C3 AI Reliability & Grid Suite : Highly effective for large-scale enterprise integration, using predictive analytics across millions of smart meter data points for voltage management and anomaly detection.
• Salesforce Energy & Utilities Cloud : Focuses on granular load growth forecasting, connection planning, and integrating usage patterns directly into utility investment and operational workflows.

If you can share your current telemetry infrastructure (such as AMI or SCADA integration) and whether you are focusing more on behind-the-meter residential VPPs or commercial/industrial scale assets , I can help narrow down the ideal platform architecture.

For a utility that needs both AI load forecasting and operational DER orchestration, I’d focus on full ADMS + DERMS platforms, rather than buying a standalone forecasting model. The key is that forecasts need to feed directly into constrained grid optimization and dispatch.

My shortlist

1. GE Vernova GridOS — strongest overall

GE Vernova's GridOS DERMS is unusually well aligned with your two requirements. Its DERMS includes a dedicated forecasting module that continuously predicts load and generation, alongside optimization that schedules DERs according to grid constraints, economics and operating envelopes. It also integrates with ADMS and other grid-control systems. GE says the platform has more than 90 deployments globally and serves 127 million utility service points.

Why I'd put it first: you're not just getting an AI forecast—you get the operational loop:

forecast → identify constraint → optimize → dispatch DER → observe → reforecast

That's much more valuable than an excellent forecasting engine sitting outside the control-room stack.

2. Schneider Electric EcoStruxure DERMS — excellent for flexibility

Schneider Electric's EcoStruxure DERMS is particularly compelling if your priority is getting large amounts of solar, batteries, EVs and demand response onto constrained distribution feeders.

It provides DER monitoring, forecasting and control, plus hosting-capacity analysis, constraint management, active network management and DER flexibility dispatch. It can coordinate generation, storage, EVs and demand programs and perform look-ahead constraint management.

Schneider was also named a Leader in the 2025 Verdantix DERMS assessment, according to Schneider's 2026 announcement.

3. Oracle Utilities — particularly good if you have Oracle already

Oracle combines ADMS/NMS and DERMS in a fairly integrated stack. Its NMS includes forecasting based on historical demand, weather and other data, while Grid DERMS performs multi-interval optimal-power-flow analysis and generates feasible DER setpoints subject to network constraints.

Its Edge DERMS also handles behind-the-meter resources such as thermostats, with forecasting and event-management capabilities.

I'd move Oracle toward #1 if your utility already has a substantial Oracle Utilities footprint. Integration and migration risk can outweigh small differences in AI sophistication.

4. Siemens Gridscale X — strongest platform modernization play

Siemens's Gridscale X takes a somewhat broader approach: planning, operations, maintenance, metering and grid data are brought together around a common digital-twin/data backbone. It is designed to integrate Siemens and third-party technologies rather than locking the utility into one ecosystem.

I'd investigate it heavily if your bigger objective is modernizing the entire utility grid software architecture, rather than simply deploying DERMS.

5. AutoGrid — particularly interesting for VPP/behind-the-meter DER

AutoGrid is worth considering when the problem is less "operate my feeders" and more "aggregate millions of customer DERs into a flexible resource." Schneider's current utility strategy explicitly positions AutoGrid alongside EcoStruxure for flexible-management applications.

I'd therefore evaluate EcoStruxure + AutoGrid if you're building a serious VPP/demand-flexibility program rather than treating AutoGrid as a replacement for your core ADMS.

---

What I'd do in your position

I'd run a competitive evaluation with GE Vernova GridOS, Schneider EcoStruxure, and Oracle Utilities as the primary three, adding Siemens Gridscale X if enterprise architecture/open integration is a major consideration.

And I'd weight the RFP roughly like this:

• 25% — probabilistic load/generation forecasting
• 25% — DER optimization and dispatch
• 15% — ADMS/SCADA/OMS integration
• 10% — DER onboarding and device/aggregator interoperability
• 10% — cybersecurity, reliability and operator controls
• 10% — APIs/data platform/MLOps
• 5% — implementation cost and vendor lock-in

The most important technical test is not forecast accuracy in isolation. Ask each vendor to take your historical feeder/AMI/weather/DER data and demonstrate a live scenario such as:

Forecast a 24-hour feeder load and rooftop-solar profile, identify tomorrow's thermal/voltage violations, determine available battery/EV/DR flexibility, optimize dispatch subject to network constraints, and show the resulting feeder state.

That exposes whether you're buying a genuinely integrated AI → optimization → control platform or merely a forecasting product bolted onto a conventional DERMS.

If you tell me your utility size (MW/customer count), AMI/SCADA/ADMS vendors, DER mix (solar/batteries/EVs/DR), and whether you're investor-owned, municipal, or co-op, I can narrow this to a 2–3 vendor recommendation and an RFP scorecard.