A Sensing Method Based of Floating Photovoltaic Grids to Sudden Changes in Marine Weather

Abstract

Currently, the application of floating photovoltaics in the ocean is mainly restricted by the cost of submarine cables and special buoys. It will show a high degree of applicability if the energy is consumed by the unmanned management systems on ocean farms and in other scenarios. The grid system formed by the floating photovoltaics can satisfy the early warning requirements of the sudden weather changes on ocean farms. Due to the strong follow-up of the photovoltaic output model to random weather changes, based on the spatial-temporal correlation analysis of large-area photovoltaics, hardware, distance, time delay, and weather, a similar power station fusion estimation relationship is established. Based on the long short-term memory (LSTM) algorithm, the ultra-short-term prediction value of the time sequence tracking of similar power stations can be used to estimate the early warning of the status of target similar power stations. The city-scale data was used to verify the feasibility of the proposed idea, which shows that the framework can complement traditional research deficiencies.

Keywords

• floating photovoltaic
• marine weather
• similar power station
• long short-term memory (lstm)