{"id":72,"date":"2025-02-09T00:34:22","date_gmt":"2025-02-09T00:34:22","guid":{"rendered":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s25-teamd5\/?p=72"},"modified":"2025-02-09T04:36:56","modified_gmt":"2025-02-09T04:36:56","slug":"team-status-report-for-02-08-2025","status":"publish","type":"post","link":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s25-teamd5\/2025\/02\/09\/team-status-report-for-02-08-2025\/","title":{"rendered":"Team Status Report for 02-08-2025"},"content":{"rendered":"

Presented the proposal to the class<\/h3>\n

Risks :\u00a0<\/strong><\/h3>\n
    \n
  1. Right now, our load forecasting model is trained on synthetic data. Main risk is overfitting to synthetic data. Once we switch to real-time power consumption logs from ESP32 sensors, our model may struggle to adapt to real-world variations such as sudden spikes in energy usage (a heater turning on) or unusual load drops (someone turning off all appliances).<\/li>\n<\/ol>\n

    Mitigation : Collect real IoT data logs from ESPHome devices to improve model accuracy. Implement outlier detection to ignore unusual spikes or drops in power usage. Use XGBoost & RandomForest models, which handle nonlinear patterns better. Will plan to use\u00a0multiple forecasting models (XGBoost, ARIMA, LSTMs) and use ensemble methods to combine predictions.<\/p>\n

    2.\u00a0The reliability and quality of the optimization algorithms are directly dependent on the quality of the forecast data (for load forecasting + solar power + grid prices). Lower forecast errors lead to more accurate optimization results, whereas high forecast errors can lead to bad optimization outcomes<\/p>\n

    Changes :\u00a0<\/strong><\/h3>\n

    No significant design changes have been made to the system yet.<\/p>\n

    Progress<\/strong>:<\/h3>\n