AI for energy and utilities: from load forecasting to smart grid optimisation
The Dutch electricity grid is at capacity. Grid congestion is blocking new connections, the balance between supply and demand shifts with every MWh of solar and wind generation, and the EPEX price curve increasingly deviates from what classic forecasting predicts. Energy companies, grid operators, ESCOs and EV charging operators that want to stay on top of this are deploying artificial intelligence for load forecasting, predictive maintenance on substations, balancing services and EV charging orchestration. We build those AI solutions, tailored to Dutch grid codes, TenneT, Stedin, Liander and Enexis protocols, and the reality of a grid that comes closer to its limits every day.
Discuss your AI case View applicationsWhy AI and energy are now inseparable
The energy sector generates measurement data every second from millions of smart meters, SCADA systems, weather stations, EV charge points and home batteries. These data volumes can only be managed with machine learning, and margins in the market can only be defended with models that forecast faster than the competition.
In 2026, the Dutch electricity grid is structurally congested in six of the seven RNB regions. Liander, Stedin and Enexis publish weekly updated capacity maps on which entire provinces show orange or red. At the same time, the share of solar and wind generation is growing at a pace that SCADA architecture designed for the coal and gas era was never built to handle. Day-ahead prices on EPEX are negative every day between 10:00 and 16:00 and spike in the evening peak well above €300/MWh. Classic forecasting models, which worked statically with seasonal patterns and historical profiles, have an unacceptable margin of error in this reality.
AI models trained on smart meter data, weather forecasts from KNMI or ECMWF, OCPP messages from charging points and order book data from EPEX and Nord Pool can forecast demand, supply and price minute by minute with solid grounding. That forecasting power is directly worth money: for a BRP (Balance Responsible Party), halving the imbalance forecast error means a correspondingly lower imbalance cost. For a grid operator, spotting a substation fault three weeks in advance means avoiding an emergency intervention. For an EV charging operator, smart orchestration of hundreds of charging sessions means the connection capacity doesn't have to be upgraded, an investment that would otherwise run into the millions.
Core areas where AI makes the difference in energy and utilities
From forecasting to fraud detection, the applications vary, but the common thread is the same everywhere: lower imbalance costs, better use of existing grid capacity and demonstrably lower downtime.
Load forecasting for BRPs and suppliers
Demand and supply forecasting at quarter-hourly resolution for the day-ahead, intraday and imbalance markets. Models combine E1/E2 meter data, ECMWF weather ensembles, calendar effects and macroeconomic indicators. The output is directly usable for your e-programme submission to TenneT, for your bidding strategy on EPEX, and for optimising your BRP portfolio across the aFRR, mFRR and FCR balancing products.
Smart grid optimisation for RNBs
Real-time congestion management at MV and HV level through DERMS and ADMS integrations. AI models forecast local congestion before it occurs, prioritise GOPACS bids and control flexible assets via OpenADR 2.0b. Includes interfaces to IEC 61850 substations and your existing SCADA environment.
Predictive maintenance for critical assets
Transformer stations, switchgear, wind turbines and solar park inverters generate vibration, temperature and current data. Anomaly detection and remaining-useful-life models predict faults weeks before they occur. Maintenance shifts from reactive to planned: fewer emergency call-outs, less unplanned downtime, and longer asset lifespans.
EV charging orchestration and V2G
Intelligent management of charging sessions via OCPP 2.0.1 and ISO 15118. Models optimise charging profiles based on dynamic tariffs, local grid congestion, behind-the-meter PV generation and user preferences. Vehicle-to-grid integration allows EV batteries to actively participate in aFRR or FCR-Day. Suitable for CPOs, fleet operators and utilities that own charging infrastructure.
AI for energy trading desks
Reinforcement learning agents for day-ahead bidding on EPEX and APX, intraday cyclic trading and cross-border arbitrage with Nord Pool. Models learn from order book dynamics, weather deviations and cross-commodity correlations. Hands-off trading within predefined risk parameters, with a full audit trail for REMIT reporting and internal compliance.
Prosumer management and HEMS
Behind the connection: coordinated control of solar panels, home batteries, heat pumps and EV chargers. Models optimise self-consumption, feed-in timing and participation in dynamic tariffs. For suppliers with dynamic contracts, it's a tool to help customers earn more from their PV installation while improving portfolio balance.
AI customer service for consumption queries
A large share of inbound tickets at energy suppliers concern annual statements, meter reading discrepancies, feed-in settlements and moving house. LLM-based assistants retrieve current consumption data from your billing system, explain discrepancies clearly and resolve routine tickets. Escalation to a human agent comes with full context handover, so customers never face frustrating transfers.
Meter reading fraud detection
Unexplained drops in consumption, reversed power flow and smart meter tampering: anomaly detection models identify suspicious patterns in smart meter data. Useful for suppliers, DSOs and metering companies to reduce grid losses and investigate non-technical losses in a targeted way.
Wind and solar yield forecasting
Probabilistic yield forecasting per asset at quarter-hourly resolution. Models combine NWP data (HARMONIE-AROME, ECMWF), turbine SCADA and historical curtailment data. Essential for BRPs with large PPA portfolios and for operators who want to optimise their day-ahead nominations within the Dutch imbalance regime.
How Appfront builds AI for energy and utilities
We don't build a generic SaaS platform that you have to configure around your grid setup. Our approach is hands-on: we dive into your SCADA architecture, energy management systems and trading stack, and build AI components that integrate directly with the reality of your operation. Whether that is a Siemens Spectrum Power installation, a GE PowerOn system, a proprietary DERMS platform, or a combination with cloud billing from a stack such as Stedin Klant or Greenchoice.
Every energy organisation starts from a different position. A large grid operator with thousands of substations and an in-house data lake has different priorities than a new ESCO rolling out a charging network on an industrial estate, or a small BRP looking to halve imbalance costs with better forecasts. We tailor the AI architecture to your specific reality: which metering and SCADA data is genuinely available and reliable, which regulatory requirements from ACM and the Netcode apply, and where the greatest impact lies in terms of imbalance costs, OPEX or customer satisfaction.
Our approach is iterative and deliberately cautious with production environments. We start with a proof of concept on a single, clearly defined use case, such as load forecasting for one BRP portfolio or predictive maintenance on one type of substation, and expand once the model results are convincing enough for production rollout. No big-bang implementation in critical infrastructure, but a validated rollout with measurable KPIs: avoided imbalance costs, avoided emergency interventions, avoided curtailment.
From first conversation to AI in production on your grid operations
Our approach to AI projects in the energy sector follows four phases. Each phase delivers a concrete result: no months of analysis without output, but interim milestones you can test against your own operational reality.
Data assessment
We inventory the available data: SCADA historian, smart meter data, OCPP logs, weather data, EPEX history. We assess quality, latency and reliability, and determine which AI application is most technically and economically feasible.
Proof of concept
Within a few weeks we build a working prototype of the chosen use case. A forecasting model trained on your own portfolio, anomaly detection on one type of substation, or an orchestration engine for one charging hub. Concrete and testable.
Integration and production
The validated model is connected to your existing systems: SCADA, ADMS, billing platform, trading stack. We build IEC 61850 or OpenADR integrations, dashboards for operators and monitoring for your data team.
Monitoring and adjustment
AI models degrade when the market or the grid shifts. We monitor model performance, detect drift, retrain on new data and adjust based on changing grid conditions, regulation and feedback from your operations team.
Test your idea first: a working prototype in 1 day
With OneDayBuild, we turn your idea into something tangible in one day for €1,150, so you can see whether further development is worth the investment. Decide to go ahead with the full build? Then we credit the full cost.
Explore OneDayBuild →Technology we deploy in energy projects
The choice of technology depends on the use case, the latency requirements and the existing IT/OT architecture. For load forecasting we work with gradient boosting (LightGBM, XGBoost) and sequence models such as N-BEATS or Temporal Fusion Transformers. For predictive maintenance we use time-series anomaly detection, autoencoders and survival models for remaining useful life. For energy trading AI we build reinforcement learning agents within pre-calibrated risk frameworks and strict safety rails.
We choose technology based on proven results in the utilities sector, not hype. Where a simple regression model suffices for day-ahead, we do not build deep transformers. Where an LLM is needed for customer service or data explainability, we ensure the model answers in a controlled way, with no hallucinations about tariffs, contract terms or meter readings. And for anything involving SCADA and critical infrastructure: strict separation between IT and OT environments, in line with IEC 62443.
Energy data, netcode and compliance: what you need to know
Working with data from the Dutch electricity grid means working within a dense body of regulation: GDPR, the Electricity Act 1998, the Netcode Electricity, the Information Code, ACM decisions and, for trading activities, REMIT and MiFID II. We build AI solutions that stay within these frameworks.
Netcode and Information Code
Access to metering and allocation data is governed by the Information Code. Our pipelines respect the roles of each market party (BRP, supplier, DSO, metering company) and the data minimisation that goes with them. No unauthorised data exchange between market roles, and no cross-pollination between regulated and commercial activities, an area on which the ACM enforces strictly.
GDPR and smart meter data
Smart meter data is personal data. We implement pseudonymisation at connection EAN level, explicit lawful bases for processing, and clear data processing agreements. Training data for portfolio-wide models is aggregated or handled with differential privacy wherever possible.
REMIT and trading transparency
Energy trading AI operates within the transparency requirements of REMIT. Model decisions are logged, including inputs, predictions and chosen actions, so that the ACM, the AFM or an internal compliance officer can always reconstruct why a particular bidding strategy was selected at a given moment.
NIS2 and OT cybersecurity
Under NIS2, energy suppliers, DSOs and large producers fall under the category of essential entities. AI models that use SCADA or ADMS data operate within IEC 62443 zoning, with audit logging, MFA access and strict separation between model training and production environments. No direct cloud uplinks from OT zones without a hardened gateway.
Hosting within the NL/EU
Sensitive metering, SCADA and trading data does not leave the Netherlands or the EU. We host AI models and data lakes with Dutch cloud providers, on-premise, or within your existing Azure/AWS tenancy in an EU region. No data export to US clouds without your explicit choice and an accompanying DPIA.
Explainable AI for regulators
A model that makes decisions about balancing, congestion management or customer invoices must be explainable. We deliver explainability through SHAP values, feature attribution and clear decision rules, useful for your audits, for ACM questions and for the confidence of your own operations team.
Concrete scenarios from Dutch energy practice
AI in energy is not science fiction. These are realistic applications that can be built for your organisation today, with the current state of the technology and data availability.
BRP portfolio with dynamic forecasting
A Balance Responsible Party with a mixed portfolio of wind, solar and gas assets uses an ensemble model that combines ECMWF weather data, turbine SCADA and historical imbalance patterns. The model delivers 192 quarter-hourly values for the next 48 hours, updated every hour. The output feeds directly into the e-programme engine, which submits nominations to TenneT and places intraday bids on EPEX. Effect: substantially lower imbalance costs and better utilisation of flexible assets.
Grid operator with predictive maintenance at MV substations
A regional grid operator collects vibration, temperature and load data from medium-voltage substations. An anomaly detection pipeline runs daily and flags deviating patterns weeks ahead of a possible fault. The maintenance team plans targeted inspections and replacements, rather than responding reactively to failures. Result: lower SAIDI/SAIFI, better asset utilisation and a more focused maintenance budget.
EV-charging operator with smart orchestration at charging hubs
A CPO with charging hubs at industrial estates uses an orchestration engine that adjusts charging curves in real time based on local grid congestion, dynamic tariffs and user preferences. Communication runs over OCPP 2.0.1, with congestion signals via OpenADR. The result: existing grid connection capacity is sufficient despite growing charging volumes, avoiding a significant investment in grid reinforcement.
Energy supplier with dynamic tariffs and HEMS integration
A supplier with a dynamic contract integrates a HEMS integration that controls a home battery, heat pump and solar panels based on hourly prices and local grid congestion signals. AI orchestration optimises self-consumption and feed-in returns for the customer, while improving the supplier's portfolio balance. Customers see lower annual bills, and the supplier sees lower imbalance costs and higher retention.
ESCO with flex aggregation for balancing services
An ESCO bundles heat pumps, cold stores and industrial batteries into a virtual power plant and offers aFRR and mFRR capacity to TenneT. Every 15 minutes, AI determines which assets are available, how much they can deliver and at what cost. Bidding on the balancing market happens automatically, within predefined risk parameters and with a complete audit trail.
Utility supplier with AI customer service for consumption queries
A supplier experiences seasonal peaks in tickets around annual settlements and balance corrections. An LLM assistant with a direct integration to billing and EDSN data answers consumption questions, explains deviating meter readings and flags possible meter faults for referral to the metering company. The result: shorter handling times, a higher first-time-fix rate and capacity freed up for more complex issues.
Frequently asked questions about AI for energy and utilities
Interested in deploying AI in your energy or utility organisation?
Discuss your case with us. We will analyse where AI delivers the most value within your grid operations or trading stack, with no obligation.
Schedule a conversation