Intelligent comprehensive modeling method for power load digital statistics

Abstract

The invention discloses an intelligent comprehensive modeling method for power load digital statistics. The method comprises a non-invasive load monitoring technology. According to the technology, anelectric energy metering device is used for collecting electric load information, deep learning, reinforcement learning and other technologies are used for identifying and classifying user electric loads, a load element model and parameters based on data are formed, and the proportion of energy consumed by a single load element to total consumed energy is calculated. The load element model and theenergy consumption proportion are combined into a load model and the load model is summarized to a bus node, and data such as load element types, parameters and proportions are acquired by adopting methods such as digital statistics and intelligent synthesis. Then, a deep learning algorithm framework such as a production adversarial network generates a power load model and a load discrimination model for accuracy verification of the power load model. The digital statistical intelligent comprehensive modeling method for the power load has the potential of online operation and real-time modeling.

Description

technical field [0001] The invention belongs to the field of power load modeling methods, and relates to a power load digital modeling method that combines modern power load big data and intelligent algorithms. Background technique [0002] The calculation result of power flow is the main basis for dispatching decision-making, and the calculation of power flow also provides data support for the implementation of power system planning and operation control. Power system simulation calculation is a physical coupling calculation based on the main components of the power grid. Among the four main components of the power system, the power grid components (lines and transformers), synchronous motors and their excitation and speed regulation systems, prime movers and other models have been basically perfected, only the load model of the power system due to its high randomness, Due to the diversity of load components and geographical dispersion, the accuracy of its physical model d...

AI Technical Summary

Problems solved by technology

In the current technology, there is no statistical analysis of electrical appliances using non-invasive technology; there is no automatic power load statistics function; there is no load aggregation function based on load component aggregation technology; there is no technology based entirely on measurement data and artificial intelligence The Method of Realizing Digital Modeling of Electric Load

Images