Tempo di lettura ca.: 2 minuti, 18 secondi
[[{“value”:”
Scientists used a year’s worth of data from East China to analyze what weather conditions affect abnormal, high, and low PV output days. They also constructed a simple extreme output prediction model and examined the atmospheric circulation anomalies corresponding to extreme output events.
Researchers from the China Electric Power Research Institute have outlined a new classification of weather types based on abnormal PV output events and different weather types and, based on this new taxonomy, they have developed a simple extreme output prediction model.
“Currently our model is based on the East China region as an example, but we believe that the model has the potential to be applied in other regions,” corresponding author, FanYang, told pv magazine. “The model essentially finds the weather processes associated with anomalous output and tries to use them as a basis for predicting future anomalous output events. Therefore, we estimate that in different regions, the types of weather associated with anomalous output events may differ from those in the paper.
The analysis was based on output data from 76 distributed PV power stations in eastern China, coupled with meteorological data from the European Centre for Medium-Range Weather Forecast, Fifth Generation Reanalysis dataset. The data for the entire year of 2022 were used for clustering, while data from January 1, 2023, to March 31, 2023, were used for validation.
“Extreme high or low photovoltaic output events can result in significant electricity wastage or shortages, placing high demands on energy storage and backup power configurations, and even potentially posing a serious threat to the safe and stable operation of the power grid, and therefore receiving special attention from the power grid dispatch department,” the group said. “Consequently, the prediction of extreme output events has become one of the current research hotspots.”
The academics used sliding averages and standard deviations to identify anomaly events. Then, the machine learning algorithm K-means was used to cluster the different abnormal days based on meteorological variables such as temperature, downward shortwave radiation, surface pressure, 100m wind speed, relative humidity, total cloud cover, and daily precipitation. In addition, multiple variable linear regression, a statistical technique that uses several explanatory variables to predict the outcome of a response variable, was used to analyze the impact of each variable.
“Out of 121 abnormal output days, there are a total of 72 abnormal low output days and 49 abnormal high output days,” the researchers stated. “Regarding the monthly frequency distribution, the number of abnormal output days in July and August 2022 are relatively few, totaling 3 days, while abnormal output days are more frequent during the winter and spring seasons, with occurrences exceeding 10 days.”
Using the clustering of the different variables, the team also found that abnormal high output events are related to high temperature, clear weather brought by stable low-pressure systems and clear windy cooling weather processes controlled by high pressure. Abnormal low output events, on the other hand, are related to transitional weather processes, such as cold waves, cloudy and precipitation-free weather, and cloudy and rainy weather processes in low-pressure systems.
“Factors such as humidity, precipitation, and temperature changes vary in importance under different types of weather, but radiation and cloud cover are always key factors,” the team added.
The scientists also used the data to build a simple extreme output prediction model. “After inputting meteorological elements at a certain future time, the model partitions based on Euclidean distance measurement. If the meteorological elements at a certain time conform to the characteristics of meteorological elements during high and low output anomaly periods, an output anomaly event is considered to potentially occur at that time,” they explained.
To strengthen their model, they also added a subjective weather forecast method based on atmospheric circulation patterns. Tested on the first three months of 2023, the model showed 16 hits, 4 false alarms, and 4 missed alarms for abnormally low output days. For abnormally high output days, there were 12 hits, 9 false alarms, and 6 missed alarms.
“Taking a case of extremely low power event in January 2023 as an example, the photovoltaic extreme power prediction model proposed in this paper and the subjective forecasting method based on atmospheric circulation pattern are validated respectively,” the group concluded. “It is found that the above methods contribute to improving the objective and subjective forecasting of photovoltaic extreme power events, and the combination of the two can further improve the ability to predict photovoltaic power.”
Their findings were introduced in the paper “Comprehensive evaluation methods for photovoltaic output anomalies based on weather classification,” published in Renewable Energy.
“}]]