Recursive least squares algorithms to detect abnormal operation in PV systems
Scientists in Spain have implemented recursive least squares (RLS) algorithms for anomaly detection in PV systems and have found they can provide “more realistic and meaningful assessment” than traditional energy analysis.
PV string fault detection technique based on multi-layer neural network
Scientists in India have proposed using a multilayer neural network to find line-to-ground, line-to-line, and bypass diode faults in PV module strings. They tested the new approach on a 22.5 kW solar array and reportedly achieved “competitive” accuracy results.
Researchers propose new models for heat pump load forecasting in energy communities
Novel research from Germany and the USA has analyzed the impact of heat pump (HP) integration on the ability of day-ahead load forecasting in energy communities. Using different models, the scientists have also investigated whether HP loads should be forecasted separately from the rest of the household or both together.
PV module fault detection technique based on convolutional neural network
An international research team has used the convolutional neural network (CNN) deep learning algorithm to identify faults in solar panels. Its work showed the proposed technique has a high degree of accuracy, especially if combined with transfer learning models.
Solar forecasting based on all sky imaging, long short-term memory
A Dutch research team have developed a solar radiation forecasting model that uses the long short-term memory (LSTM) technique. The proposed methodology reportedly achieves better results than other forecasting approaches.
New machine learning tech for short-term PV power generation forecasting
Researchers in China have applied a machine learning technology based on temporal convolutional networks in PV power forecasting for the first time. The new model reportedly outperforms similar models during all seasons.
Robotic measurement system assesses new materials for solar cells
Researchers in Japan have developed an automated system to perform photoabsorption and photoluminescence spectroscopy, optical microscopy, and white-light flash time-resolved microwave conductivity tests.
Cloud fraction nowcasting method for PV applications
Researchers in China have developed a novel way to predict the cloud coverage of PV plants. The method uses geostationary satellite and recurrent-neural networks.
Weekend Read: Artificial opportunities
Artificial intelligence (AI) is hot right now and is finding central applications in homes and businesses as they move from simple grid connections to self-generation, energy storage, electric vehicle (EV) charging, and load-shifting revenue streams. With AI everywhere, what’s the difference between advanced control, via simple algorithms, and true intelligence?
Open-source workflow to assess rooftop PV potential
Scientists in Germany have developed a new open-access approach to assess regional rooftop PV potential. The ETHOS.PASSION approach combines two deep learning models to identify rooftops and superstructures.
