Figure - available from: International Transactions on Electrical Energy Systems
This content is subject to copyright. Terms and conditions apply.
Source publication
To address the problem of data missing caused by equipment faults, abnormal transmission, and improper storage in data acquisition systems of photovoltaic (PV) power plants, we hereby propose a method for PV power missing data filling based on multiple matching and a long short‐term memory network. First, test samples were divided into three differ...
Citations
... In short, high-precision data filling is important to improve the quality of PV data and reveal the unknown characteristics of DPVS operation data. Many current studies rely on interpolation or prediction models to fill in the missing data [105,106] that require a large amount of historical data for training. Such methods do not fully utilize the spatio-temporal correlation characteristics between different PV plants. ...
In recent years, with the rapid development of distributed photovoltaic systems (DPVS), the shortage of data monitoring devices and the difficulty of comprehensive coverage of measurement equipment has become more significant, bringing great challenges to the efficient management and maintenance of DPVS. Virtual collection is a new DPVS data collection scheme with cost-effectiveness and computational efficiency that meets the needs of distributed energy management but lacks attention and research. To fill the gap in the current research field, this paper provides a comprehensive and systematic review of DPVS virtual collection. We provide a detailed introduction to the process of DPVS virtual collection and identify the challenges faced by virtual collection through problem analogy. Furthermore, in response to the above challenges, this paper summarizes the main methods applicable to virtual collection, including similarity analysis, reference station selection, and PV data inference. Finally, this paper thoroughly discusses the diversified application scenarios of virtual collection, hoping to provide helpful information for the development of the DPVS industry.
... The forecast accuracy of PV power can be increased by improving data quality Lei et al., 2021) and prediction methods (Yang and Huang, 2018;Durrani et al., 2018;Rafati et al., 2021;Wang et al., 2021). Besides, the conversion efficiency of PV power generation can be improved by adopting new PV materials (Manokar et al., 2018;Kabeel et al., 2019;Karthick et al., 2020;Manokar et al., 2020). ...
The predictability concept of Photovoltaic (PV) power on the time series was presented and the approximate entropy algorithm and predictable coefficient were used to quantificationally analyze the predictability of PV power on time series, then the approximate entropy and predictable coefficient variation at different spatial scale were analyzed. Finally, the measured data of a PV plant in western Ningxia were used for testing and confirming the result. The results of several typical prediction methods show that the proposed method can effectively characterize the predictability of PV power on time series.
