Microgrid load prediction method based on long and short term neural network model

A neural network model, load forecasting technology, applied in biological neural network models, neural learning methods, forecasting, etc., to achieve the effect of improving convergence speed and stability, and improving forecasting accuracy

Pending Publication Date: 2022-08-09
NINGBO POLYTECHNIC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, although the existing load forecasting methods have their own advantages, the research objects are all traditional power systems, and there is a lack of targeted research on new micro-grids with a large number of new energy sources.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Microgrid load prediction method based on long and short term neural network model
  • Microgrid load prediction method based on long and short term neural network model
  • Microgrid load prediction method based on long and short term neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Research shows that the microgrid load output is not only affected by the structure and characteristics of the system itself, but also by factors outside the system. From an economic point of view, the gross regional product (GDP) is closely related to the load output. From an industrial point of view, the proportion of electricity consumed by regional factories has a greater impact on the load. From the perspective of meteorological factors, especially extreme weather has a greater impact on the load output. From a time series perspective, time, month, season, and holidays all affect the load. From a market point of view, the value of peak and valley electricity will also affect the load. From the perspective of the microgrid structure, the proportion of new energy will also affect the load. In order to further reveal the influence of different types of influencing factors on the power generation load of the microgrid, the present invention conducts a characteristic...

Embodiment 2

[0084] In order to better understand the technical content of the present invention, this embodiment briefly summarizes the present invention through a system structure diagram, such as Figure 4As shown, the improved LSTM neural network proposed by the present invention. Through clustering algorithm and feature selection, the data set of key factors that have the greatest impact on the power generation load of the microgrid is obtained as the input of the network. Feature extraction is performed through two-layer convolutional neural network channels. The two convolutional layers exchange data through cross-training and other methods to further mine the high-value information contained in the data. The output features of the convolutional neural network are then used as the input of the LSTM. Its unique 3 gates and memory unit can further filter the features. At the same time, the convolutional neural network is inversely optimized using the Lookahead optimizer. Finally, ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a microgrid load prediction method based on a long and short term neural network model, and relates to the technical field of microgrid load prediction, and the method comprises the steps: obtaining the weight of each influence factor when the clustering interval is maximum, and extracting the feature vector of each influence factor in a current group through a double-layer convolutional neural network; optimizing the long-short-term neural network through an optimizer, and carrying out feature vector screening through the optimized long-short-term neural network; weighting processing is carried out on the screened feature vectors through attention optimization, and optimized feature vectors are obtained; and connecting the optimized feature vectors through a full connection layer and obtaining the predicted load of the current group. According to the invention, the optimized feature vectors are connected through the full connection layer, the predicted load of the current group is obtained, and the long-term and short-term neural network is adopted to solve the problem of long-term dependence in the training process.

Description

technical field [0001] The invention relates to the technical field of microgrid load prediction, in particular to a microgrid load prediction method based on a long-term and short-term neural network model. Background technique [0002] With the rapid development of science and technology and economy in the world, the problem of environmental pollution caused by traditional power generation methods is becoming more and more serious. New energy technologies centered on wind power and photovoltaic power generation have become the focus of research at home and abroad. However, renewable energy itself has considerable randomness and volatility. When large-scale access to the power system, it will adversely affect the stability and reliability of the power grid. As a small-scale, decentralized independent system, microgrid has the advantages of self-control, protection and management. The rapid development of its related technologies makes it possible to promote the large-scal...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/06G06K9/62G06N3/04G06N3/08
CPCG06Q10/04G06Q50/06G06N3/049G06N3/08G06N3/045G06F18/23213G06F18/214Y04S10/50
Inventor 林贡羽黄棋悦洪成秀
Owner NINGBO POLYTECHNIC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap