Capacity Change

Capacity Change Algorithm Module

This module the algorithm for detecting capacity changes in an unlabeled PV power production data sets. The algorithm works as follows:

• Run daily quantile statistic on cleaned data

• Fit a signal demixing model, assuming a seasonal component and a piecewise constant component

• Polish the L1 heuristic used to estimate piecewise constant component using iterative reweighting

• Assign daily cluster labels by rounding

class solardatatools.algorithms.capacity_change.CapacityChange

Bases: object

optimize_weight(metric, filter, weights, solver=None)

plot_weight_optimization(figsize=(10, 5))

A function for plotting plotting the three weight selection criteria

Parameters:

figsize – a 2-tuple of the figure size to plot

Returns:

matplotlib figure

run(data, metric=None, weight=None, filter=None, quantile=1.0, solver=None)

solve_sd(metric, filter, weight, w3=1, w4=10.0, solver=None, verbose=False)

solardatatools.algorithms.capacity_change.custom_round(x, base=0.05)