Abstract
Photovoltaic (PV) power generation is greatly affected by meteorological environmental factors, with obvious fluctuations and intermittencies. The large-scale PV power generation grid connection has an impact on the source-load stability of the large power grid. To scientifically and rationally formulate the power dispatching plan, it is necessary to realize the PV output prediction. The output prediction of single power plants is no longer applicable to large-scale power dispatching. Therefore, the demand for the PV output prediction of multiple power plants in an entire region is becoming increasingly important. In view of the drawbacks of the traditional regional PV output prediction methods, which divide a region into sub-regions based on geographical locations and determine representative power plants according to the correlation coefficient, this paper proposes a multilevel spatial upscaling regional PV output prediction algorithm. Firstly, the sub-region division is realized by an empirical orthogonal function (EOF) decomposition and hierarchical clustering. Secondly, a representative power plant selection model is established based on the minimum redundancy maximum relevance (mRMR) criterion. Finally, the PV output prediction for the entire region is achieved through the output prediction of representative power plants of the sub-regions by utilizing the Elman neural network. The results from a case study show that, compared with traditional methods, the proposed prediction method reduces the normalized mean absolute error (nMAE) by 4.68% and the normalized root mean square error (nRMSE) by 5.65%, thereby effectively improving the prediction accuracy.
Highlights
The proportion of photovoltaic (PV) power generation in the power grid continues to increase, but its intermittency and high fluctuation in output power pose a serious threat to the stable operation of the grid-connected power system
This paper presents a new prediction method for the entire region’s PV power generation, which aims to provide a power dispatching strategy for a wide region
Considering the incomplete power data for some PV plants, a sub-region division model is proposed based on empirical orthogonal function (EOF) decomposition and hierarchical clustering, which is fully represented by the time–space characteristics of the PV power
Summary
The proportion of photovoltaic (PV) power generation in the power grid continues to increase, but its intermittency and high fluctuation in output power pose a serious threat to the stable operation of the grid-connected power system. The accurate prediction of single power plants can no longer meet the scheduling and safe operation of large-scale power systems [1]. The prediction of a single power plant can be divided into direct prediction and indirect prediction. Direct prediction is based on the historical power output data of PV power plants. Indirect prediction generally predicts the solar irradiance first and calculates the output value of the PV power plant through relevant formulas. Used methods for indirect prediction include Kalman filters [11], wavelet analysis, and the sky image method [12]. In [14], a recursive wavelet neural network was used to establish a day-by-day and time-by-time irradiance prediction model. In [15], the solar irradiance was used as the output variable to establish the state space model, and irradiance prediction was achieved via Kalman filtering
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
