Search

• A quad-kernel convolutional neural network model for PV power forecasting. • Sequence-to-sequence learning method to capture timing-dependent features. • Multiple global-max-pooling algorithms to improve the learning efficiency. • The effect of dataset resolution on the model performance is studied. • Operation data prove the higher forecasting accuracy of the proposed model. Photovoltaic (PV) power is highly stochastic and volatile, and PV power forecasting is a key technology to guarantee the safe and economic operation of high-penetration renewable power systems. To improve the accuracy of PV power forecasting, a quad-kernel deep convolutional neural network (QK_CNN) model is proposed to perform intra-hour PV power forecasting for the next four timesteps: four CNNs with different kernel sizes are used to extract different local cross features between sequence elements of four timesteps; a single-kernel CNN is used to further feature extraction of these features, and then the target sequence forecasting results are obtained; global maximum pooling method is used to simplify the feature extraction process and improve model learning efficiency. Operation data from a 26.52 kW PV plant in Central Australia is selected as the experimental data. Compared with single-kernel CNN and hybrid models (CNN_LSTM) on 5, 10, and 15 min of resolution data, respectively, the proposed model shows better forecasting performance and is able to explain 96 % to 98 % of the total variation of the forecasted PV power. All these demonstrates that the CNNs with specific design have great potential to handle the task of PV power forecasting as well. [ABSTRACT FROM AUTHOR]

DNA profiles are generated in forensic biology laboratories around the world. It is possible that these profiles are assessed by two independent people in order for the profiles to be 'read'. Recent work has been carried out to develop a neural network model to classify fluorescence in a DNA profile electropherogram and potentially replace one, or both human readers. The ability to use neural networks for this function has been programmed into the software FaSTR™ DNA, which has been validated for use in at least one laboratory in Australia. The work that previously developed a neural network system had a number of limitations, specifically it was computer intensive, did not make the best use of available data, and consequently the performance of this model was sub-optimal in some conditions (particularly for low-intensity peaks). In the current work a new neural network model is developed that makes various improvements on the old model, by using convolutional layers, a multi-head architecture and data augmentation. Results indicate that an improved performance can be expected for low-intensity profiles. • Previous work showed Neural Networks identifying DNA profile features. • These 10 NNs, in FaSTR DNA, performed well over a range of profiles. • The NNs would sometimes mis-classify low level peaks as baseline. • A single model, using multi-head NN is developed to classify an entire profile. • The training data is also expanded using data augmentation using existing profile. [ABSTRACT FROM AUTHOR]