低压分布式光伏功率预测系统
Search documents
国网山西电力上线低压分布式光伏预测系统
Zhong Guo Dian Li Bao· 2025-11-13 03:06
Core Insights - A low-pressure distributed photovoltaic power forecasting system has been launched in Shanxi Province, covering 11 cities and 115 counties, achieving over 95% accuracy in short-term forecasts [1] - As of the end of September, the installed capacity of distributed photovoltaic in Shanxi reached 14.89 million kilowatts, a 36% increase compared to the end of 2024 [1] - The new forecasting system addresses challenges posed by the variability of solar energy generation, which affects grid stability and precise scheduling [1] Technology Development - The system utilizes a time-series large model to predict low-pressure distributed photovoltaic power, analyzing historical generation data alongside various meteorological factors such as temperature, sunlight, cloud cover, and air quality [1] - It integrates meteorological data with historical generation data, allowing for multi-dimensional forecasting at provincial, municipal, and county levels [1] - The model is fine-tuned using local data from Shanxi, enhancing the specificity and accuracy of the predictions [1] Operational Efficiency - The new system enables the prediction of overall photovoltaic generation across the province, overcoming previous difficulties in accurately assessing scattered distributed photovoltaic power [1] - It provides decision-making support for optimizing grid scheduling by anticipating fluctuations in photovoltaic generation [1] - The system can complete a single forecasting task in under 20 seconds, significantly improving operational efficiency [1]
国网山西电力实现低压分布式光伏功率预测
Zhong Guo Neng Yuan Wang· 2025-11-11 09:44
Core Insights - A low-pressure distributed photovoltaic power forecasting system has been launched in Shanxi Province, covering 11 cities and 115 counties, enhancing short-term prediction accuracy to over 95% [1][2] - The system supports the construction of a new power system with a high proportion of renewable energy, addressing challenges posed by the variability of solar power generation due to weather changes [1] Group 1: System Development and Features - The system was developed by State Grid Shanxi Electric Power, utilizing historical generation data and real-time meteorological information to predict overall photovoltaic generation across the province [2] - It incorporates multiple innovations, including deep integration of weather data and historical generation, and supports multi-dimensional forecasting at provincial, city, and county levels [1][2] Group 2: Impact on Energy Management - Accurate forecasting is essential for efficient consumption of renewable energy, as the system provides decision-making support for optimizing grid dispatch by predicting peak and valley fluctuations in solar power generation [2] - The system operates efficiently, completing a single forecasting task in under 20 seconds, with plans for further enhancement in prediction accuracy during extreme weather conditions [2]
预测准确率超95%!国网山西电力上线低压分布式光伏功率预测系统
Xin Hua Cai Jing· 2025-11-11 07:42
Core Insights - A low-pressure distributed photovoltaic power forecasting system has been launched in Shanxi Province, enhancing short-term prediction accuracy to over 95% [1][2] - The installed capacity of distributed photovoltaic in Shanxi reached 14.89 million kilowatts by the end of September 2023, marking a 36% increase compared to the end of 2024 [1] Group 1: System Overview - The forecasting system covers all 11 cities and 115 counties in Shanxi, providing reliable technical support for a new power system with a high proportion of renewable energy [1] - The system utilizes historical generation data, temperature, light, cloud cover, and air quality to optimize prediction strategies through intelligent algorithms [1] Group 2: Operational Efficiency - The system can complete a single forecasting task in under 20 seconds, indicating high operational efficiency [2] - Future enhancements will focus on improving prediction accuracy under extreme weather conditions and adapting to complex meteorological scenarios [2]