Optimizing Solar Power Using Array Topology Reconfiguration With Regularized Deep Neural Networks

Reconfiguring photovoltaic (PV) array connections among different topologies such as series-parallel, bridge-link, honeycomb, or total-cross-tied is a popular strategy to mitigate impediments in power production caused by partial shading. Conventional approaches rely on either by-passing replacing shaded modules with auxiliary panels through complex control mechanisms, optimization strategies, simulator driven obtain the best topology. However, these solutions are not scalable and incur significant installation costs computational overhead, motivating need develop ‘smart’ methods for topology reconfiguration. To this end, we propose regularized neural network based algorithm that leverages panel-level sensor data reconfigure maximizes output under arbitrary shading conditions. Based our simulations include wiring losses configurations, observe improvement of up 11% The proposed can be easily integrated any cyber-physical PV system reconfiguration capabilities scalable.