Predicting diurnal outdoor performance and degradation of organic photovoltaics via machine learning; relating degradation to outdoor stress conditions

Abstract

Accurate prediction of the future performance and remaining useful lifetime of next-generation solar cells such as organic photovoltaics (OPVs) is necessary to drive better designs of materials and ensure reliable system operation. Degradation is multifactorial and difficult to model deterministically; however, with the advent of machine learning, data from outdoor performance monitoring can be used for understanding the relative impact of stress factors and could provide a powerful method to interpret large quantities of outdoor data automatically. Here, we propose the use of artificial neural networks and regression models for forecasting OPV module performance and their degradation as a function of climatic conditions. We demonstrate their predictive capability for short-term energy forecasting of OPV modules, showing that energy yield can be predicted if climatic conditions are known. In addition, the model has been extended so that the impact of climatic conditions on degradation can be predicted. The combined model has been validated on unseen OPV module data and is able to predict energy yield to within 4% accuracy.

Analyzing the outdoor degradation behavior of organic solar modules in North China

“…41 However, in previous studies, the methods of data ltration applied to the analysis of outdoor degradation of OSMs were neither rigorous nor consistent; the lter criteria varied across different studies. 18,45 Inadequate ltration introduces the impact of the testing environment on OSMs' properties and increases errors. An excessive screening method leads to the wastage of collected data.…”

“…Machine learning is a powerful data-driven method that has been effectively applied in evaluating materials' outdoor behaviors. [43][44][45] The ability to derive rules from data through the training process, rather than relying on predetermined equations, makes machine learning a compelling approach for developing models that handle diverse data sets and complex interactions, characteristics that are typical of data in outdoor degradation tests. For example, Wu et al used an articial neural network model to predict the outdoor degradation process of polycarbonate.…”

Accelerated exploration of efficient ternary solar cells with PTB7:PC71BM:SMPV1 using machine-learning methods

“…Moreover, ML can discover hidden laws while building models with predictive power. [1][2][3][4][5] Nowadays, ML has also been applied in the field of photovoltaics, such as the research and development of organic photovoltaic materials, [6][7][8] the screening of photovoltaic materials, [9][10][11][12] the optimization of solar cell stability, [13][14][15][16] and the preparation of high-performance solar cells. 17 Qi Zhang et al successfully screened 22 new photovoltaic materials with high potential using ML, which provided reasonable design guidance for the synthesis of materials for new high-performance OSCs.…”

Geração E Degradação De Módulos Fotovoltaicos Orgânicos Em Instalações Verticais E Horizontais

“…Para isso, testes outdoor, que são realizados próximos às condições reais, ainda são a melhor a opção. Apesar de longos, uma vez que acontecem em tempo real, são os mais confiáveis, uma vez que contam com a dinâmica ambiental que não pode ser simulada no ambiente de laboratório (David et al, 2021).…”