Application of photovoltaic power generation in rail transit power supply system under the background of energy low carbon transformation

• Main Authors: Lixia Tian, Yuansheng Huang, Shuang Liu, Shize Sun, Jiajia Deng, Hengfeng Zhao
• Format: Article
• Language: English
• Published: Elsevier 2021-12-01
• Series: Alexandria Engineering Journal
• Subjects: Energy low carbon transformation; Photovoltaic power generation; Rail transit; Long short term memory (LSTM) neural network
• Online Access: http://www.sciencedirect.com/science/article/pii/S1110016821002519

Low carbon economy, energy conservation and environmental protection is one of the important tasks of current and future economic and social development. The large-scale development and utilization of all kinds of clean energy has accelerated the speed of China’s energy transformation. Rail transit system is a large power consumer. In recent years, the transportation system has been facing the triangle contradiction of new energy, cost and environmental protection. Connecting photovoltaic power generation to rail transit power supply system has many advantages: (1) it can reduce the operation cost of transportation system; (2) it can reduce the use of traditional thermal power; (3) it can reduce carbon emissions and protect the environment; (4) it can also promote the application of new energy. It makes a lot of sense. However, due to the randomness and uncertainty of photovoltaic power generation, the direct access of photovoltaic power generation to rail transit power supply system will bring a certain impact on rail transit power supply system. In this paper, the LSTM neural network is used to predict the load of photovoltaic power generation, which effectively ensures the accuracy of prediction, and then improves the stability of photovoltaic power generation when connected to the rail transit power supply system.