Uncertainty-aware estimation of inverter field efficiency using Bayesian neural networks in solar photovoltaic plants

Special Issue on ‘EU PVSEC 2024: State of the Art and Developments in Photovoltaics’, edited by Robert Kenny and Gabriele Eder

Open Access

Table 3

Algorithm parameters.

Parameter	Value
H	[20, 200]*
σ_p	[0.1, 1]*
lr	[0.001, 1]*
Number of trials	75
Optimisation algorithm	Adam
Learning rate	0.001
Betas	0.9, 0.999
α	0.0001
Number of epochs	1500
Batch size	100

[ ] indicates range of values.

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.