Project description
Novel tools help distribution system operators optimally manage multi-energy systems
Ensuring the world has a reliable supply of energy to heat its homes and buildings, power a new generation of electric vehicles and provide electricity to the grid is a complicated task. Multi-energy systems that interact with each other optimally for enhanced services and energy efficiency will play a key role in future emissions reductions. The EU-funded MNRG project is developing algorithms and technologies for these systems leading to digital, distributed and real-time monitoring of heat, mobility and electricity. The new solutions will support distribution system operators in finding the best network topologies as well as in forecasting loads and implementing real-time solutions to problems.
Objective
To achieve deep emission reductions in the European energy sector and in the heating sector in particular, stronger cross-sectoral linkages among the different energy carriers are needed. The main objective of proposed MNRG is improving operational flexibility by presenting a comprehensive digitalized, distributed and real-time monitoring of heat, mobility and electricity energy sectors which is required to deal with the uncertainty and variability of growing renewable resources and mobility. The main novelties of this project are: 1) MNRG provides an easy deployment and paired with unprecedented modularity for interconnected multi-energy systems by using GridEye's edge computing capabilities. 2) MNRG introduces a more practical way to manage and respond to the complex needs of the multi-energy systems in the presence of numerous energy components and devices. 3) The impact of DERs and EVs on the quality of energy sectors will be monitored in real-time and the flexibility in the operation of CHPs, use of reactive power controlling devices such as SVR and storage capacity of heat network will be considered as alternatives for technical challenges. 4) Real-time preventive and corrective actions based on dynamic feeder reconfiguration against over-voltage and congestion in the grid will be addressed. To determine network topologies optimally, methods based on machine learning or mathematical techniques will be implemented. 5) By MNRG, the behavior of feeders and transformers that are utilized by DERs and EVs will be predicted for DSO’s usage. In this regard, MNRG feeding by updated forecasts based on mathematical methods, like, ARIMA and deep learning methods, such as DRL and LSTM, will provide corrective and preventive actions. 6) MNRG can provide robust strategies for DSOs by using uncertainty modelling techniques such as robust optimization to tackle the volatility of uncertain parameters.
Fields of science
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectrical engineeringpower engineeringelectric power distribution
- natural sciencesmathematicsapplied mathematicsdynamical systems
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- natural sciencesmathematicsapplied mathematicsstatistics and probability
- natural sciencesmathematicsapplied mathematicsmathematical model
Programme(s)
Funding Scheme
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Coordinator
1070 Puidoux
Switzerland
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.