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.

Clean energy will account for a lot in the future energy structure with the emergence of Urban Regional Energy Internet. However, because of the intermittent and volatility of clean energy like wind energy, its main role in energy supply has restricted. Therefore, predicting wind power accurately is of great significance in the safe operation of the power system. In response to the above problems, this paper proposed a time series forecasting model of wind power based on BiLSTM, and analyzes the actual wind data in Urban Regional Energy Internet.

No abstract

No abstract

Blockchain technology is a kind of decentralized transaction and data management technology, which has been extended to many economic and social fields, such as digital finance, Internet of things, intelligent manufacturing, supply chain management, digital asset trading and other economic and social fields, but the application of statistical work is still less. The current investment statistics business of Power Grid Companies involves multi-department collaboration and multi-level interactions. There are uneven data maintenance and low data quality among various business departments. The statistics majors and the basic data providing departments and the statistical data reporting units are both at the upper and lower levels. There are varying degrees of “mutual trust issues”. According to the characteristics of blockchain Smart Contract, consensus mechanism and linked storage structure, multi-party sharing of data on the chain and higher credibility, this paper explores how to integrate the technical characteristics of blockchain with the investment statistics business, and change the business model of investment statistics.