This paper describes a new approach to online forecasting of power production from PV systems. The method is suited to online forecasting in many applications and in this paper it is used to predict hourly values of solar power for horizons of up to 36 h. The data used is 15-min observations of solar power from 21 PV systems located on rooftops in a small village in Denmark. The suggested method is a two-stage method where first a statistical normalization of the solar power is obtained using a clear sky model. The clear sky model is found using statistical smoothing techniques. Then forecasts of the normalized solar power are calculated using adaptive linear time series models. Both autoregressive (AR) and AR with exogenous input (ARX) models are evaluated, where the latter takes numerical weather predictions (NWPs) as input. The results indicate that for forecasts up to 2 h ahead the most important input is the available observations of solar power, while for longer horizons NWPs are the most important input. A root mean square error improvement of around 35% is achieved by the ARX model compared to a proposed reference model.

/pdf/online-short-term-solar-power-forecasting-1ljgpbshkb.pdf

Online Short-term Solar Power Forecasting

https://escholarship.org/content/qt5dk0b8t5/qt5dk0b8t5.pdf?t=q9piey

History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining

Smart multi-step deep learning model for wind speed forecasting based on variational mode decomposition, singular spectrum analysis, LSTM network and ELM

A Survey of Artificial Neural Network in Wind Energy Systems

Solar radiation forecasting using artificial neural network and random forest methods: Application to normal beam, horizontal diffuse and global components

Short-term wind speed forecasting using empirical mode decomposition and feature selection

3D-CNN-based feature extraction of ground-based cloud images for direct normal irradiance prediction

Wood veneer defect detection plays a vital role in the wood veneer production industry. Studies on wood veneer defect detection usually focused on detection accuracy for industrial applications but ignored algorithm execution speed; thus, their methods do not meet the required speed of online detection. In this paper, a new detection method is proposed that achieves high accuracy and a suitable speed for online production. Firstly, 2838 wood veneer images were collected using data collection equipment developed in the laboratory and labeled by experienced workers from a wood company. Then, an integrated model, glance multiple channel mask region convolution neural network (R-CNN), was constructed to detect wood veneer defects, which included a glance network and a multiple channel mask R-CNN. Neural network architect search technology was used to automatically construct the glance network with the lowest number of floating-point operations to pick out potential defect images out of numerous original wood veneer images. A genetic algorithm was used to merge the intermediate features extracted by the glance network. Multi-Channel Mask R-CNN was then used to classify and locate the defects. The experimental results show that the proposed method achieves a 98.70% overall classification accuracy and a 95.31% mean average precision, and only 2.5 s was needed to detect a batch of 50 standard images and 50 defective images. Compared with other wood veneer defect detection methods, the proposed method is more accurate and faster.

/pdf/defect-detection-of-industry-wood-veneer-based-on-nas-and-3wxjh83sjz.pdf

Defect Detection of Industry Wood Veneer Based on NAS and Multi-Channel Mask R-CNN.

Mulch film is usually mixed in with cotton during machine-harvesting and processing, which reduces the cotton quality. This paper presents a novel sorting algorithm for the online detection of film on cotton using hyperspectral imaging with a spectral region of 1000 - 2500 nm. The sorting algorithm consists of a group of stacked autoencoders, two optimization modules and an extreme learning machine (ELM) classifier. The variable-weighted stacked autoencoders (VW-SAE) are constructed to extract the features from hyperspectral images, and an artificial neural network (ANN), which is one optimization module, is applied to optimize the parameters of the VW-SAE. Then, the extracted features are input in the ELM to classify four types of objects: background, film on background, cotton and film on cotton. The ELM is optimized by a new optimizer (grey wolf optimizer), which can adjust the hidden nodes and parameters of the ELM simultaneously. A group of experiments was carried out to evaluate the performance of the proposed sorting algorithm using cotton that was provided by a Xinjiang municipality cotton ginning company. The experimental results show that the VW-SAE can improve the classification accuracies by approximately 15%. The overall recognition rate of the proposed algorithm is over 95%, and its recognition time is comparable to some state-of-the-art methods.

/pdf/online-sorting-of-the-film-on-cotton-based-on-deep-learning-2crc6t8q20.pdf

Tingting Zhu

Papers

Short-term wind speed forecasting using empirical mode decomposition and feature selection

3D-CNN-based feature extraction of ground-based cloud images for direct normal irradiance prediction

Defect Detection of Industry Wood Veneer Based on NAS and Multi-Channel Mask R-CNN.

Online Sorting of the Film on Cotton Based on Deep Learning and Hyperspectral Imaging

Clear-sky model for wavelet forecast of direct normal irradiance