Til hovedinnhold

Markus Löschenbrand

Forsker

Markus Löschenbrand

Forsker

Markus Löschenbrand
Telefon: 948 60 561
E-post:
Avdeling: Energisystemer
Kontorsted: Trondheim

Publikasjoner og ansvarsområder

Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/1949485/

Probabilistic forecasts of electrical loads and photovoltaic generation provide a family of methods able to incorporate uncertainty estimations in predictions. This paper aims to extend the literature on these methods by proposing a novel deep-learning model based on a mixture of convolutional...

År 2021
Type Vitenskapelig artikkel
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/1947738/

Due to the absence of well documented experiences from implementations of Local Energy Communities (LECs), it is very difficult to infer implications of increased LEC integrations for the distribution network as well as for the wider society. To conduct quantifiable assessment of different control...

Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/1939861/

In this paper we present a simple and intuitive method for fitting a non-linear Bayesian regression model on short-term load forecasts. Such models have been implemented via Bayesian neural networks, which are known for their hyper-parameter sensitivity. We instead show a more general method to fit...

År 2021
Type Vitenskapelig Kapittel/Artikkel/Konferanseartikkel
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/1924931/

This paper applies a generative deep learning model, namely a Variational Autoencoder, on probabilistic optimal power flows. The model utilizes Gaussian approximations in order to adequately represent the distributions of the results of a system under uncertainty. These approximations are realized...

År 2021
Type Vitenskapelig artikkel
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/1904529/

In recent years, power systems have undergone changes in technology and definition of the associated stakeholders. With the increase in distributed renewable generation and small- to medium-sized consumers starting to actively participate on the supply side, a suitable incorporation of decentralized...

Forfattere Sigurd Bjarghov Markus Löschenbrand A.U.N. Ibn Saif Raquel Alonso Pedrero Christian Pfeiffer Shafiuzzaman K. Khadem Marion Rabelhofer Frida Huglen Revheim Hossein Farahmand
År 2021
Type Vitenskapelig artikkel
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/1821240/

This paper proposes a model to include investments in demand flexibility into traditional transmission expansion problems under uncertainty. To do so, a dynamic power flow model is proposed. The model is solved via applying a value function approximation in form of a neural network on the...

År 2020
Type Vitenskapelig artikkel
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/1840405/

Traditionally, models pooling flexible demand and generation units into Virtual Power Plants have been solved via separated approaches, decomposing the problem into parts dedicated to market clearing and separate parts dedicated to managing the state-constraints. The reason for this is the high...

År 2020
Type Vitenskapelig artikkel
Publikasjon
https://www.sintef.no/publikasjoner/publikasjon/1617524/

Traditionally, electricity markets have been designed with the intention of disabling producer side market power or prohibiting exercising it. Nonetheless it can be assumed that players participating in pool markets and aiming to maximize their individual benefits might depart from the optimum in...

Forfattere Markus Löschenbrand Magnus Korpås Marte Fodstad
År 2018
Type Vitenskapelig Kapittel/Artikkel/Konferanseartikkel