A5067308700- Energy Load and Power Forecasting
- Smart Grid Energy Management
- Electric Power System Optimization
- Forecasting Techniques and Applications
- Time Series Analysis and Forecasting
- Integrated Energy Systems Optimization
- Microgrid Control and Optimization
- Data Quality and Management
- Solar Radiation and Photovoltaics
- Power Systems and Technologies
- Parallel Computing and Optimization Techniques
- Low-power high-performance VLSI design
- Scientific Computing and Data Management
- Image and Signal Denoising Methods
- Sustainable Industrial Ecology
- Advanced Research in Systems and Signal Processing
- Research Data Management Practices
- Optimal Power Flow Distribution
- Explainable Artificial Intelligence (XAI)
- Smart Grid Security and Resilience
- Neural Networks and Applications
- Network Traffic and Congestion Control
- Power Line Communications and Noise
Fraunhofer Institute for Applied Information Technology
2023
RWTH Aachen University
2019-2022
This paper presents a real-word implementation of TSO-DSO-customer coordination framework for the use flexibility to support system operation. First, we describe general requirements coordination, including potential schemes, actors and roles required architecture. Then, particularise those real-world demonstration in Sweden, aiming avoid congestions grid during high-demand winter season. In light current congestion management rules existing markets an integration path newly defined new...
Methods to forecast electric loads and generation timeseries are widely applied in power system operation balancing. For this purpose, most sophisticated forecasting methods complex, since the net electricity consumption is not dependent on explainable by a single cause. The increasing complexity furthers trend towards machine-learning that achieve more accurate load forecasts with exogenous features. However, well-known downside of machine learning users will face non-transparent,...
Power system operators are confronted with a multitude of new forecasting tasks to ensure constant supply security despite the decreasing number fully controllable energy producers. With this paper, we aim facilitate selection suitable approaches for load problem. First, provide classification cases in two dimensions: temporal and hierarchical. Then, identify typical features models compare their applicability structured manner depending on six previously defined cases. These compared...
Forecast developers predominantly assess residuals and error statistics when tuning the targeted model’s quality. With that, eventual cost or rewards of underlying business application are typically not considered in model development phase. The analysis power system wholesale market allows us to translate a time series forecast method’s quality its respective value. For instance, near real-time capacity procurement takes place market, which is subject complex interrelations operators’ grid...
This paper presents an agent-based power scheduling framework for interconnected local energy communities (LECs) using the Nash bargaining solution (NBS) approach to offer a fair and financial reimbursement changing operation objectives of such LECs. LECs are modern form microgrids (MGs) which consist not only electrical systems but also include thermal energy. The focus is set on LEC operator needs with different operational objectives, where in classical MGs island aspect often dominates...
Recent changes in national and European-wide regulation for distribution system operator transmission (TSO–DSO) energy consumer coordination foster flexibility provision services. In this context, many existing new market participants need to adapt newly developed platform-based service provision. To facilitate communication between different stakeholders better identify future infrastructural changes, such as modern flexible electric grid components or advanced architectures, the Smart Grid...
Short-term load forecasting is typically used by electricity market participants to optimize their trading decisions and system operators ensure reliable grid operation. In particular, it allows the latter foresee potential power imbalances other critical states thereafter, enforce appropriate mitigation actions. Especially, such as congestions, plays an essential role in this context. This paper proposes a recurrent neural network that trained forecast day-ahead time-series prediction...
The integration of renewable energy sources, the decentralization system, and increasing digitization energy-related processes require a wide range data. In this context, data sharing platform can serve as hub for exchanging developing innovative solutions to improve efficiency sustainability system. However, especially because involvement industry in such poses several challenges related protection, intellectual property, business interests. This paper presents framework ensuring...
Today, the energy supply does not follow demand in a controlled manner anymore. Thus, forecasting electricity consumption became essential for operation of power systems. Already numerous open source software tools exist that provide models, which are configurable different tasks. In case electrical demand, change geographical or temporal settings, requires specific domain knowledge on relevant data and influencing factors to be considered when developing data-driven models. With ProLoaF, we...