Energiedaten wie Anlageninformationen und Energieverträge sind oft nicht-digitalisiert oder unstrukturiert abgelegt. Gleichzeitig sind sie über verschiedene Abteilungen, IT-Systeme und Excel-Tabellen verstreut – das erschwert Transparenz, kollaborative Entscheidungen und den Einsatz von AI-Agents.
Optimize Costs
Reduce energy cost per unit through data-driven decisions and load management.
Improve Energy Management
Create a single source of truth for all energy-relevant data – usable across departments.
AI-Ready Data Foundation
Structured, validated energy data as the foundation for AI agents and automated optimization.
Used by industry leaders
The Building Blocks of the Digital Twin
All the features you need to fully understand and optimize your energy system.
Request DemoUnified modeling of all energy carriers: electricity, gas, heat, cold, compressed air, and steam. Cross-carrier optimization for holistic energy cost analysis – from spot market arbitrage to heat planning law compliance.
Portfolio-compliant storage of trading products: futures, PPAs, spot market contracts. All procurement contracts structured for day-ahead, intraday, and long-term hedging. Integration of PPA options and flexibility marketing.
Complete modeling of your grid connections with capacity limits, grid fees, and surcharges. Separation of energy trading prices and grid costs for precise scenario analysis – including grid expansion or transformer upgrades.
Detailed modeling of all energy generators: CHP plants, PV, heat pumps, e-boilers, gas turbines. Including efficiencies, operating points, and availabilities for optimal dispatch planning.
Detaillierte Modellierung von Produktionsmaschinen und -bedarfen, um genauere Bedarfsprognosen machen zu können und das Potential von Production Scheduling analysieren zu können.
Automatic detection and correction of outliers, data gaps, and measurement errors. Plausibility checks against physical limits. Continuous data validation from day 1.
Complete traceability of all changes to the model. Every parameter change is logged – for audit security, four-eyes principle, and efficient teamwork. All changes are logged and accessible at any time.
Configurable thresholds and automatic notifications via email or push. Automated reports for management and audits. Role-based dashboards for every target audience.
Implementation follows five phases: (1) Use Case Identification – based on the Use Case Table, we identify which data needs to be integrated to reduce your energy cost per unit. (2) Data Collection – targeted data collection for the identified use cases. (3) Model Setup – building the energy model with information from the real system. (4) Validation – testing based on data the model hasn't seen, until historical performance is accurately reflected. (5) Go-Live – after successful validation, connection to control systems and activation. Typical go-live time: 4–6 weeks.
Our baseline data can be used as a foundation for missing data such as investment costs for certain components. In addition, our solution engineering team can help supplement missing data with other internal models, for example for heating requirements, combined with practical experience.
The scalable solution complements existing IT systems consisting of control systems, energy management, and data hubs. Standardized interfaces enable connection to ERP systems, control systems, and other data sources. The Digital Twin acts as a central data foundation that consolidates all energy-relevant information.
The Digital Twin supports various data formats for maximum flexibility. Time series data can be imported via CSV upload or live API integration. Separate CSV files can be used for different components. Important: Energy data such as natural gas must be provided in energy units (kWh or MWh), not in volume units like cubic meters.
Live data integration can be achieved in several ways: via APIs to central systems like data lakes or through edge controllers. Additionally, we support direct communication with smart meters and PLC systems using industrial protocols such as Modbus, OPC UA, and EDC. For intraday trading, we recommend 15-minute intervals. The data is used exclusively for numerical optimization of your specific energy system – not for training general AI models.
The Digital Twin offers multi-site capability and can model from nationwide aggregation down to individual assets. All energy carriers are supported: electricity, gas, heat, cold, compressed air, and steam. Additionally, production data such as shift schedules and production programs can be integrated to link energy optimization with production planning.
We offer a structured training program: self-learning videos for independent study and supervised workshops for hands-on practice. Our "train the trainer" model enables your team to independently maintain and extend the model. Regular project check-ins and a dedicated support channel ensure continuous support throughout your usage.
Data security is our highest priority. We hold relevant certifications including TISAX and ISO 27001. All data processing agreements are carefully documented. For automation, we follow a step-by-step approach with parallel operation, allowing you to build confidence in the system before critical processes are automated.
Yes, the Digital Twin is designed to complement existing IT systems – including control systems and energy management systems. Depending on your requirements, the integration can work as human-in-the-loop with recommendations or as automatic control. For the IT-OT bridge, an edge controller is available that ensures secure communication between your systems.
Yes, this is possible. The same Digital Twin can be used both for strategic design and investment planning as well as for operational use. For operator mode, the model is parameterized in more detail – for example with ramping constraints and minimum load requirements – and integrated with real-time data.
Yes, the Digital Twin enables complete modeling of your grid connections including capacity limits, grid fees, and surcharges. Grid connection capacity expansion can be parameterized, including costs per MW for expansion. This allows you to precisely analyze scenarios for transformer upgrades or grid expansion.
Yes, the Digital Twin offers holistic optimization that combines peak shaving with overall energy consumption. The system dynamically evaluates trade-offs between peak load reduction and spot market arbitrage. This way, battery storage is optimized not only for peak shaving but also for utilizing favorable electricity prices – with the goal of minimizing total energy costs.
