A green energy base in Henan Province Photo: Xinhua

 After entering winter, the northern Henan Province in Central China with abundant wind and photovoltaic resources, has significantly increased new energy power generation. On the morning of November 21, Li Wenguang, the team leader of the Power Dispatch and Control Center of Power Supply Com in the county of Anyang, managed to interface power flow limitation analyses of the power grid and the balance dispatch of new energy power by using prediction results released by a new energy meteorological monitoring and power prediction platform, taking into account the actual operational capacity  of nearby  wind and photovoltaic power stations.

Since June, the State Grid Henan Electric Power Com has focused on the self-developed new energy meteorological monitoring and power prediction platform as well as related technologies to innovate the application of new energy power prediction models, and has carried out predictions in 18 cities across the province regularly. With the establishment of the new platform, the company has successfully increased the short-term and ultra-short-term prediction accuracies of new energy in the province by an average of 1.6 and 1.2 percentage points compared with the same period last year, effectively ensuring the scientific dispatch of new energy and the safety and stability of the power grid in Henan.

New energy has now become the second largest power source in Henan, with cumulative installed capacity exceeding 50 million kilowatts. Traditional new energy power prediction models, which have low levels of accuracy, a short prediction cycle and weak prediction autonomy, cannot reflect the impact of weather changes on the entire region.

Thus, the research team of State Grid Henan Electric Power Com developed a new energy meteorological monitoring and power prediction platform in February. The platform integrates rich data resources including D5000, the Central Meteorological Observatory and the Henan Provincial Meteorological Observatory. It also has six modules such as meteorological monitoring, meteorological prediction and power prediction. The improvement allows the platform to conduct longer cycle power predictions by using longer time-series meteorological predictions, and have extended the daily ultra-short-term, short-term and long-term prediction periods to 10 hours, 14 days and 45 days respectively. In this way, it has further increased the dispatch time margin and provided necessary data for a balanced dispatch of the provincial power and electricity.

The company divides 18 cities in Henan into 25 regions based on similarities in micro-meteorology, micro-terrain and other factors. Based on various meteorological prediction data and algorithms such as long-term and short-term memory neural networks in the region, the company comprehensively included the meteorological evolution processes such as gales and cloud movements into consideration, and constructed a regional new energy total power prediction model, which can offer accurate predictions for new energy power in stations, cities, regions and the whole province. Besides, the company has upgraded its prediction model for complex and ever-changing weather, which can accurately predict the impact of extreme weather, and issue new energy power generation warnings in advance.

In the near future, the State Grid Henan Electric Power Com will continuously improve the regional new energy total power prediction model, work on the distributed photovoltaic refined power prediction, further improve the accuracy of power prediction during peak load periods. It will strive to overcome difficult problems such as power prediction under extreme weather conditions and the governance and application of measured meteorological data at stations, so as to better support the scientific and efficient power dispatch, ensure the safe and reliable supply of electricity and the efficient consumption of new energy.