Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
forecasting:meeting_minutes_september_13_2016 [2016/09/14 02:52] jobatake |
forecasting:meeting_minutes_september_13_2016 [2021/09/19 21:59] (current) |
||
|---|---|---|---|
| Line 11: | Line 11: | ||
| * Produce: | * Produce: | ||
| * Well-written code | * Well-written code | ||
| - | * New python libraries | + | * New python libraries to pull off of |
| - | * | + | * Build library of functions other groups can use |
| + | * Solar Industry | ||
| + | * Calibrate Data | ||
| * Decisions: | * Decisions: | ||
| - | * Normalization | + | * Normalization Method (Zenith Angle?) |
| - | * Prediction time | + | * Prediction time (1 hr?) |
| * Solar Irradiance doesn't need to be sampled too quickly (1-2 mins ok) | * Solar Irradiance doesn't need to be sampled too quickly (1-2 mins ok) | ||
| * Understanding PV: | * Understanding PV: | ||
| Line 21: | Line 23: | ||
| * Commercial and residential | * Commercial and residential | ||
| * Projection of these | * Projection of these | ||
| - | * Solar Thermal | + | * Solar Thermal |
| - | * Solar Farms | + | * Solar Farms |
| - | * Concentrated Solar | + | * Concentrated Solar |
| - | * Energy Production | + | * Energy Production |
| - | * PV Data Sheets | + | * PV Data Sheets |
| - | * 10-15% efficiency w/ lower cost panels | + | * 10-15% efficiency w/ lower cost panels |
| - | * 40% efficiency w/ increase in efficiencies, cost, etc. | + | * 40% efficiency w/ increase in efficiencies, cost, etc. |
| - | * Breaks for Federal and State and HECO | + | * Breaks for Federal and State and HECO |
| - | * Larger contracts (PPA) | + | * Larger contracts (PPA) |
| * Forecasting: | * Forecasting: | ||
| * Weather and time series prediction | * Weather and time series prediction | ||
| Line 36: | Line 38: | ||
| * Depends on normalization (ex. subtract mean of specific time of day/std, or zenith angle) | * Depends on normalization (ex. subtract mean of specific time of day/std, or zenith angle) | ||
| * Take **zenith angle**: Time of day and day of year in account | * Take **zenith angle**: Time of day and day of year in account | ||
| - | * Depends on first and second order (mean and covariance matrixes) | ||
| * Window (FIR filters) | * Window (FIR filters) | ||
| * Straight average of data over time | * Straight average of data over time | ||
| Line 43: | Line 44: | ||
| * New linear estimate | * New linear estimate | ||
| * Recursive Least Squares (RLS) | * Recursive Least Squares (RLS) | ||
| + | * Depends on first and second order (mean and covariance matrixes) | ||
| * Least Mean Squares (LMS) | * Least Mean Squares (LMS) | ||
| * Won't perform as well | * Won't perform as well | ||
| - | + | * Supervised and Unsupervised Learning: | |
| - | Thursday, September 15, 2016 | + | * Nearest Neighbor (supervised) |
| - | * | + | * Support Vector Machine Kernels () |
| + | * Deep Learning () | ||
| + | * Clustering used for large dimensional data (unsupervised, Lots of factors) | ||
| + | * Estimation (regression) and Detection (classification) | ||
| ===== Reminders ===== | ===== Reminders ===== | ||
| - | * | + | * Weekly REIS Thursday Seminar 4:30-5:30 |