This work describes a new way to solve the optimal power flow problem applying typed graph neural networks. Typed graph neural networks allow the representation of different elements of transmission systems with different types of nodes, thus adding accuracy and interpretability to the solutions obtained, in comparison to results obtained with conventional feed-forward neural network models. The proposed graph neural network architecture is trained without the need of training data, through a physics informed loss function which incorporates not only the optimization objective, but also operational constraints of the physical system. Results are comparable with those obtained with the interior point method, and it is shown that the calculation time is greatly reduced.

Wind is a physical phenomenon with uncertainties in several temporal scales, in addition, measured wind time series have noise superimposed on them. These time series are the basis for forecasting methods. This paper studied the application of the wavelet transform to three forecasting methods, namely, stochastic, neural network, and fuzzy, and six wavelet families. Wind speed time series were first filtered to eliminate the high-frequency component using wavelet filters and then the different forecasting methods were applied to the filtered time series. All methods showed important improvements when the wavelet filter was applied. It is important to note that the application of the wavelet technique requires a deep study of the time series in order to select the appropriate family and filter level. The best results were obtained with an optimal filtering level and improper selection may significantly affect the accuracy of the results.

Demand-side flexibility is increasingly central to support decentralized, local, renewable energy systems. However, the practical value of flexibility depends not only on whether households have the technical means, but also how the flexibility is provided, whether manually or automated, and in what context. From a survey of approx. 1600 households in Switzerland, we investigate willingness for demand-side flexibility under three scenarios: within local energy communities, to reduce regional grid congestion, and to manage national energy security. Results show high willingness to consume flexibly, particularly in the energy security scenario where 81% of respondents would adjust their heating/cooling, 74% their hot water use, 91% their EV charging, and 90% their appliance use. However, the willingness to automate the electricity use of these technologies varies. Technology type is the strongest predictor of automation acceptance wherein heating/cooling and hot water use are most compatible with direct load control across all scenarios, while manual adjustments of appliances is strongly preferred. Scenario framing shifts the threshold at which automation is accepted but does not differentiate preferences between automation levels once crossed. Critically, the extreme event scenario, demanding the most reliable and rapid response, produces the lowest automation acceptance, revealing a systematic mismatch between technical requirements and social licence to automate. These findings underscore that effective demand-side flexibility programmes must be designed around both the technical profile of each scenario and the specific automation boundaries that households accept for different technologies.