Reconstructing Missing Data in State Estimation With Autoencoders
- 8 December 2011
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 27 (2) , 604-611
Abstract
This paper presents the proof of concept for a new solution to the problem of recomposing missing information at the SCADA of energy/distribution management systems (EMS/DMS), through the use of offline trained autoencoders. These are neural networks with a special architecture, which allows them to store knowledge about a system in a nonlinear manifold characterized by their weights. Suitable algorithms may then recompose missing inputs (measurements). The paper shows that, trained with adequate information, autoencoders perform well in recomposing missing voltage and power values, and focuses on the particularly important application of inferring the topology of the network when information about switch status is absent. Examples with the IEEE RTS 24-bus network are presented to illustrate the concept and technique.Keywords
This publication has 17 references indexed in Scilit:
- Robust neuro-identification of nonlinear plants in electric power systems with missing sensor measurementsEngineering Applications of Artificial Intelligence, 2007
- Optimal Wide Area Controller and State Predictor for a Power SystemIEEE Transactions on Power Systems, 2007
- The use of genetic algorithms and neural networks to approximate missing data in database2006
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Bayesian-Based Hypothesis Testing for Topology Error Identification in Generalized State EstimationIEEE Transactions on Power Systems, 2004
- EPSO - best-of-two-worlds meta-heuristic applied to power system problems2003
- Nonlinear Autoassociation Is Not Equivalent to PCANeural Computation, 2000
- Categorization of faces using unsupervised feature extraction1990
- Detection of topology errors by state estimation (power systems)IEEE Transactions on Power Systems, 1989
- IEEE Reliability Test SystemIEEE Transactions on Power Apparatus and Systems, 1979