Xinyu Guan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xinyu Guan has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Chen Ye
Ningbo Supply Company, State Grid Zhejiang Electric Power Co., Ltd, Ningbo, China
1 shared publicationChuanxun Pei
Ningbo Supply Company, State Grid Zhejiang Electric Power Co., Ltd, Ningbo, China
1 shared publication- Dongxiao Niu
School of Economics and Management, North China Electric Power University, Beijing 102206, China
1 shared publication - Dongyu Wang
School of Economics and Management, North China Electric Power University, Beijing 102206, China
1 shared publication Geping Weng
Ningbo Supply Company, State Grid Zhejiang Electric Power Co., Ltd, Ningbo, China
1 shared publicationHua Qing
Ningbo Supply Company, State Grid Zhejiang Electric Power Co., Ltd, Ningbo, China
1 shared publication
Latest Publications
- Open Access
Can China Meet Its 2030 Total Energy Consumption Target? Based on an RF-SSA-SVR-KDE Model
In order to accurately predict China’s future total energy consumption, this article constructs a random forest (RF)–sparrow search algorithm (SSA)–support vector regression machine (SVR)–kernel density estimation (KDE) model to forecast China’s future energy consumption in 2022–2030. It is explored whether China can reach the relevant target in 2030. This article begins by using a random forest model to screen for influences to be used as the input set for the model. Then, the sparrow search algorithm is applied to optimize the SVR to overcome the drawback of difficult parameter setting of SVR. Finally, the model SSA-SVR is applied to forecast the future total energy consumption in China. Then, interval forecasting was performed using kernel density estimation, which enhanced the predictive significance of the model. By comparing the prediction results and error values with those of RF-PSO-SVR, RF-SVR and RF-BP, it is demonstrated that the combined model proposed in the paper is more accurate. This will have even better accuracy for future predictions.
Open AccessCan China Meet Its 2030 Total Energy Consumption Target? Based on an RF-SSA-SVR-KDE Model
In order to accurately predict China’s future total energy consumption, this article constructs a random forest (RF)–sparrow search algorithm (SSA)–support vector regression machine (SVR)–kernel density estimation (KDE) model to forecast China’s future energy consumption in 2022–2030. It is explored whether China can reach the relevant target in 2030. This article begins by using a random forest model to screen for influences to be used as the input set for the model. Then, the sparrow search algorithm is applied to optimize the SVR to overcome the drawback of difficult parameter setting of SVR. Finally, the model SSA-SVR is applied to forecast the future total energy consumption in China. Then, interval forecasting was performed using kernel density estimation, which enhanced the predictive significance of the model. By comparing the prediction results and error values with those of RF-PSO-SVR, RF-SVR and RF-BP, it is demonstrated that the combined model proposed in the paper is more accurate. This will have even better accuracy for future predictions.
- Open Access
- 1 January 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1732 (1) , 012083
Photovoltaic output prediction of regional energy Internet based on LSTM algorithm
By the huge development of large scale and modular photovoltaic power generation, accurate photovoltaic (PV) output prediction can help PV power station, scheduling department and power system operate safely and economically. In the process of PV output prediction, the data density is large, and the output data is relatively regular. Therefore, this paper considers the use of long-termed and short-termed memory neural network algorithm to optimize the problem of algorithm gradient vanishment in recurrent neural network, and complete the output prediction of PV power in the regional energy Internet on the basis of historical output data. In this paper, LSTM algorithm is used to analyze the historical output data of PV stations in an industrial zone of a certain city. It can be found that LSTM algorithm has good adaptability for short-term PV output prediction, which can meet the needs of application.
- 1 January 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1732 (1) , 012083
Open AccessPhotovoltaic output prediction of regional energy Internet based on LSTM algorithm
By the huge development of large scale and modular photovoltaic power generation, accurate photovoltaic (PV) output prediction can help PV power station, scheduling department and power system operate safely and economically. In the process of PV output prediction, the data density is large, and the output data is relatively regular. Therefore, this paper considers the use of long-termed and short-termed memory neural network algorithm to optimize the problem of algorithm gradient vanishment in recurrent neural network, and complete the output prediction of PV power in the regional energy Internet on the basis of historical output data. In this paper, LSTM algorithm is used to analyze the historical output data of PV stations in an industrial zone of a certain city. It can be found that LSTM algorithm has good adaptability for short-term PV output prediction, which can meet the needs of application.