OEDI SI/Scenarios/AI Based Event Identification

From Open Energy Information

AI Based Event Identification​ Summary

  • Date Created: 2024/01/03
  • Organization: ORNL
  • Objective: Development of an open-source transient data library. Providing POW transient data in distribution models under multiple scenarios. Developing algorithms for event detection and classification purpose, based on the datasets in the open-source data library
  • Use Case: DER Aggregation Algorithm
  • Methodology
    • Inputs
      • Outputs
        • Configuration
          • Webinars


          Docker Container

          Download the docker container at:


          Run Locally

          http://localhost:8080/edit_scenario?AI Based Event Identification
              Run Locally


          Input Data

          Download input data at:


            Output Data

            Download output data at:

              References


                Back to DER Aggregation Algorithm


              1. Event detection algorithm is based on the periodic waveform detector. Its basic idea is to calculate the voltage magnitude difference between two adjacent cycles twice to remove the off-nominal frequency and periodic characteristics. A threshold is designed to detect the fault based on the distribution of the detector.
              2. Event identification algorithm first utilizes discrete wavelet transform to extract the features, and then use multiple machine learning algorithms to classify the events.
              3. Detection input: Measurements of feeder head voltage waveforms
              4. Detection input: Measurements of feeder head current waveforms
              5. Detection input: Pre-selected detection threshold
              6. Identification input: Detected event data period
              7. Detection output: 0 (No event) / 1 (Pass data during event period)
              8. Identification output: Identified event type as 0 (single-phase) / 1 (three-phase) / 2 (phase-to-phase)
              9. The user is not required to manipulate the internal contents of this image.
              10. To run the image, the user needs to follow the instructions.
              11. The user can test multiple identification algorithms by running different blocks of code in the Jupyter Notebook.
              12. https://hub.docker.com/r/openenergydatainitiative/oedisi-transient-demo
              13. https://github.com/openEDI/oedisi-transient/tree/main/input
              14. Measurements of feeder head voltage waveforms
              15. Measurements of feeder head current waveforms
              16. Pre-selected detection threshold
              17. Detected event data period
              18. https://github.com/openEDI/oedisi-transient/tree/main/output
              19. Isabel Dong, et. Al., “Rapid Event Detection Via Synchro-waveform based Temporal Attention Network in Distributed Grid,” IEEE Industry Applications Society Annual Meeting (IAS), Oct. 2024.
              20. Islam, Mahmudul, et al. "Artificial intelligence in photovoltaic fault identification and diagnosis: A systematic review." Energies 16.21 (2023): 7417.
              21. Abid, Anam, Muhammad Tahir Khan, and Javaid Iqbal. "A review on fault detection and diagnosis techniques: basics and beyond." Artificial Intelligence Review 54.5 (2021): 3639-3664.
              22. Masri, Bushra, et al. "A Review on Artificial Intelligence Based Strategies for Open-Circuit Switch Fault Detection in Multilevel Inverters." IECON 2021–47th Annual Conference of the IEEE Industrial Electronics Society. IEEE, 2021.
                23. Retrieved from "https://openei.org/w/index.php?title=OEDI_SI/Scenarios/AI_Based_Event_Identification&oldid=1085614"