Table 2

Dataset and parameters used for ANN modelling and OPTICS clustering.

Step Dataset Parameter
ANN modelling Input: Hyperparameter:
– GPOA – Batch sise 128
– Tamb – Activation function: ReLU
– sun position (azimuth, elevation) – Optimiser ADAM
Output: – Loss function: Huber
– PDC – Epochs: 200
– PAC
Time frame: one year (10 min interval); 2021
1st clustering GPOA – metric: Mahalanobis
Sun position (azimuth, elevation) – minPts: 3,000
Tamb ξ: 0.001
QAC
PAC
IAC L1
IAC L2
IAC L3
VDC
PDC
IDC
TMatrix
PDC predicted (from ANN)
PAC predicted (from ANN)
Time frame: 1 year (10 min interval); 2022
2nd clustering GPOA – metric: Mahalanobis
Tamb – minPts: 30
VDC ξ: 0.01
IDC
PDC
TMatrix
Time frame: noise cluster (-1) of first clustering

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.