Fachbereich Ingenieurwissenschaften und Kommunikation
Refine
H-BRS Bibliography
- yes (17)
Departments, institutes and facilities
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (17) (remove)
Document Type
- Conference Object (17) (remove)
Year of publication
- 2015 (17) (remove)
Keywords
- Competition (1)
- Engineering (1)
- Introductury project (1)
- Rube Goldberg machine (1)
- SCRUM (1)
- Study entrants (1)
- artificial neural network (1)
- boost converter (1)
- digital control system (1)
- efficiency (1)
This paper proposes a new artificial neural network-based maximum power point tracker for photovoltaic application. This tracker significantly improves efficiency of the photovoltaic system with series-connection of photovoltaic modules in non-uniform irradiance on photovoltaic array surfaces. The artificial neural network uses irradiance and temperature sensors to generate the maximum power point reference voltage and employ a classical perturb and observe searching algorithm. The structure of the artificial neural network was obtained by numerical modelling using Matlab/Simulink. The artificial neural network was trained using Bayesian regularisation back-propagation algorithms and demonstrated a good prediction of the maximum power point. Relative number of Vmpp prediction errors in range of ±0.2V is 0.05% based on validation data.
Work in progress: Starter-project for first semester students to survey their engineering studies
(2015)
Solar energy is one option to serve the rising global energy demand with low environmental Impact [1]. Building an energy system with a considerable share of solar power requires long-term investment and a careful investigation of potential sites. Therefore, understanding the impacts from varying regionally and locally determined meteorological conditions on solar energy production will influence energy yield projections. Clouds are moving on a short term timescale and have a high influence on the available solar radiation, as they absorb, reflect and scatter parts of the incoming light [2]. However, modeling photovoltaic (PV) power yields with a spectral resolution and local cloud information gives new insights on the atmospheric impact on solar energy.
Solar energy is one option to serve the rising global energy demand with low environmental impact.1 Building an energy system with a considerable share of solar power requires long-term investment and a careful investigation of potential sites. Therefore, understanding the impacts from varying regionally and locally determined meteorological conditions on solar energy production will influence energy yield projections. Clouds are moving on a short term timescale and have a high influence on the available solar radiation, as they absorb, reflect and scatter parts of the incoming light.2 However, the impact of cloudiness on photovoltaic power yields (PV) and cloud induced deviations from average yields might vary depending on the technology, location and time scale under consideration.