Print Email Facebook Twitter Anomaly Detection and Synthetic Data Generation for Power Systems Using Autoencoder Neural Networks Title Anomaly Detection and Synthetic Data Generation for Power Systems Using Autoencoder Neural Networks Author Wang, C. (TU Delft Intelligent Electrical Power Grids) Contributor Palensky, P. (promotor) Tindemans, Simon H. (copromotor) Degree granting institution Delft University of Technology Date 2023-03-22 Abstract The scale of the power system has been significantly expanded in recent decades. To gain real-time insights into the power system, an increasing number of sensors have been deployed tomonitor grid states, resulting in a rapidly growing number of measurement points. Simultaneously, there has also been a rise in the penetration of renewable energy generation, with energy production that is highly variable and exhibits strong interdependence between different production locations. Such interdependence also applies to electricity demand at various network positions. Furthermore, new demandside response strategies and policies enhance the flexibility of the power system, leading to changes in load profiles. These developments, combined with the structure of the network itself, mean that measurements in the power system generally exhibit strong dependencies. This dependency means that if you know one or more values, you can infer information about others. This applies to time series with measurements that follow each other chronologically as well as to snapshots that show different states of the system at a particular moment in time. A large collection of such time series and snapshots can be represented as a probability distribution in a multidimensional data space. While larger numbers of measurements enable smarter grid operations, high-dimensional stochastic variables with complex univariate and multivariate distributions could also complicate tasks in modeling power system data..... Subject Anomaly DetectionSynthetic Data GenerationAutoencoderPower System Operation and PlanningMachine Learning To reference this document use: https://doi.org/10.4233/uuid:12708aca-dff2-4d59-aa0e-af5c275aa728 ISBN 978-90-833109-4-7 Part of collection Institutional Repository Document type doctoral thesis Rights © 2023 C. Wang Files PDF Dissertation_Chenguang_Wang.pdf 19.14 MB Close viewer /islandora/object/uuid:12708aca-dff2-4d59-aa0e-af5c275aa728/datastream/OBJ/view