@article{cai_chow_2011, title={Cause-Effect Modeling and Spatial-Temporal Simulation of Power Distribution Fault Events}, volume={26}, ISSN={["1558-0679"]}, DOI={10.1109/tpwrs.2010.2055899}, abstractNote={Modeling and simulation are important tools in the study of power distribution faults due to the limited amount of actual data and the high cost of experimentation. Although a number of software packages are available to simulate the electrical signals, approaches for simulating fault events in different environments have not been well developed. In this paper, we propose a framework for modeling and simulating fault events in power distribution systems based on environmental factors and the cause-effect relationships among them. The spatial and temporal aspects of significant environmental factors leading to various faults are modeled as raster maps and probability functions, respectively. The cause-effect relationships are expressed as fuzzy rules and a hierarchical fuzzy inference system is built to infer the probability of faults in the simulated environments. A test case simulating a part of a typical city's power distribution systems demonstrates the effectiveness of the framework in generating realistic distribution faults. This work is helpful in fault diagnosis for different local systems and provides a configurable data source to other researchers and engineers in similar areas as well.}, number={2}, journal={IEEE TRANSACTIONS ON POWER SYSTEMS}, author={Cai, Yixin and Chow, Mo-Yuen}, year={2011}, month={May}, pages={794–801} }
 @inproceedings{cai_chow_lu_li_2010, title={Evaluation of distribution fault diagnosis algorithms using ROC curves}, DOI={10.1109/pes.2010.5588154}, abstractNote={In power distribution fault data, the percentage of faults with different causes could be very different and varies from region to region. This data imbalance issue seriously affects the performance evaluation of fault diagnosis algorithms. Due to the limitations of conventional accuracy (ACC) and geometric mean (G-mean) measures, this paper discusses the application of Receiver Operating Characteristic (ROC) curves in evaluating distribution fault diagnosis performance. After introducing how to obtain ROC curves, Artificial Neural Networks (ANN), Logistic Regression (LR), Support Vector Machines (SVM), Artificial Immune Recognition Systems (AIRS), and K-Nearest Neighbor (KNN) algorithm are compared using ROC curves and Area Under the Curve (AUC) on real-world fault datasets from Progress Energy Carolinas. Experimental results show that AIRS performs best most of the time and ANN is potentially a good algorithm with a proper decision threshold.}, booktitle={Ieee power and energy soceity general meeting 2010}, author={Cai, Y. X. and Chow, M. Y. and Lu, W. B. and Li, L. X.}, year={2010} }
 @inproceedings{cai_chow_2009, title={Exploratory analysis of massive data for distribution fault diagnosis in smart grids}, booktitle={2009 ieee power & energy society general meeting, vols 1-8}, author={Cai, Y. X. and Chow, M. Y.}, year={2009}, pages={2131–2136} }