Search

The automated identification and localisation of grid disturbances is a major research area and key technology for the monitoring and control of future power systems. Current recognition systems rely on sufficient training data and are very error‐prone to disturbance events, which are unseen during training. This study introduces a robust Siamese recurrent neural network using attention‐based embedding functions to simultaneously identify and locate disturbances from synchrophasor data. Additionally, a novel double‐sigmoid classifier is introduced for reliable differentiation between known and unknown disturbance types and locations. Different models are evaluated within an open‐set classification problem for a generic power transmission system considering different unknown disturbance events. A detailed analysis of the results is provided and classification results are compared with a state‐of‐the‐art open‐set classifier.

Due to increasing contribution of renewable energy sources to the overall energy production, future control of energy consumption should achieve the principle 'generation following demand'. Within this approach, also known as demand side management, consumers are prompted to alter demands through an incentive signal. This work addresses the use of variable price as such incentive signal to influence power consumption of private households in a controllable manner. The mathematical modelling is based on simulations of optimal power flow and includes several optimisation constraints and criteria, according to which both direct and inverse models are constructed. Therefore, the problem of power signals and price signals is considered as fully-coupled. The analysis is performed for a model, representing typical conditions and scenarios of a residential network with household customers, including solar and wind power plants. The optimisation criteria are constructed with the emphasis on distribution system operators. The results of computations, performed with simplified and extended optimisation models, show a pronounced effect on the overall power consumption, reduction of the extreme values and minimisation of the peaks. Finally, further steps are proposed to extend the model to target various optimisation constraints.