Household electrical load decomposition system with solar power supply system and decomposition method

Abstract

The invention discloses a household electrical load decomposition method with a solar power supply system. The household electrical load decomposition method comprises the following steps: preprocessing data of a data set; dividing the preprocessed data into training data and test data; sending the training data to a long and short term memory-recurrent neural network, and training the long and short term memory-recurrent neural network; sending the test data into a trained long-short-term memory-recurrent neural network to obtain a test result; and evaluating the performance of the long and short term memory-recurrent neural network. According to the invention, the variable input bidirectional double-layer LSTM recurrent neural network is used to decompose the load and monitor the total power flowing into the solar energy and the power consumption and operation mode of the activated load; the method can effectively monitor the problems that the power transmission and transformation equipment cannot bear more loads and the like, can enable resident users to know the electric energy use conditions of various electric loads in different time periods, and achieves the purposes of saving energy, reducing consumption and promoting power grid construction according to corresponding policies of electric power companies.

Description

technical field [0001] The invention relates to the field of household electricity consumption, in particular to a household electricity load decomposition system and decomposition method with a solar power supply system. Background technique [0002] With the enhancement of people's awareness of environmental protection and the help and support of various government policies, the power generation of renewable energy (solar photovoltaic, and wind energy, etc.) has gradually increased, effectively promoting many applications of power demand side management (DSM). However, the output power of photovoltaic and wind power systems is easily affected by environmental factors, and large-scale grid connection will have an impact on the grid. Therefore, maintaining the second-by-second balance between power generation and load demand has become a challenging task, unless Optimal dispatch and stable operation of the grid can only be achieved using expensive power storage services. In...

AI Technical Summary

Problems solved by technology

[0005] In the current NILM field, few considerations are given to installing solar panels in residential areas, while accurately disaggregating and monitoring the operating mode and power consumption of household activation loads and solar inflow, and few models can accurately determine the load Break down and monitor the active power consumption of each load and monitor the opened devices and the operation mode and power consumption level of each opened device within a given time. If this process cannot be realized, the current DR value cannot be known, and the operator will Unable to calculate economic dispatch, provide a solution to maintain minimum energy reserve service

Images