Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Long-term load prediction method and system

A load forecasting and load technology, applied in forecasting, instrument, character and pattern recognition, etc., can solve problems such as the inability to rely on historical data, the difficulty of load forecasting, and the inability to be directly applied.

Pending Publication Date: 2022-02-18
NARI TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, for newly constructed buildings or old buildings lacking historical load data, they cannot rely on their own historical data, and traditional load forecasting models cannot be directly applied to this scenario
Due to the lack of historical load data for new construction and new integrated energy buildings, load forecasting becomes difficult

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
  • Long-term load prediction method and system
  • Long-term load prediction method and system
  • Long-term load prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to further describe the technical features and effects of the present invention, the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0038] A specific long-term load forecasting method. Long-term load forecasting methods such as Figure 1-5 As shown, including the following parts:

[0039] The load correlation factors utilized by the present invention include architectural features, spatial features, temporal features, and meteorological features.

[0040] First, these factors are preprocessed, specifically: normalize the data of load-related influencing factors by formula (1)

[0041]

[0042] Among them, the sample data of X load correlation factors, X min is the minimum value of the sample data of the factors affecting the load correlation, X max is the maximum value of the sample data of the influencing factors of load correlation, X * is the sample data of normalized X-load...

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 long-term load prediction method. The method comprises the following steps: acquiring load relevance influence factor data; preprocessing the load relevance influence factor data; fusing features of the preprocessed relevance influence factor data; and using the fused features for training a LightGBM model, and predicting the load through the trained LightGBM model. The method does not depend on historical load data, only takes load correlation factors such as buildings and meteorology as input, and predicts the load in a period of time in the future.

Description

technical field [0001] The invention belongs to the technical field of air-conditioning load forecasting, and in particular relates to a long-term load forecasting method and system. Background technique [0002] In the overall planning and operation of the integrated energy system, load forecasting is an indispensable and important link. Accurate load data is of great significance for later capacity optimization and equipment configuration. Traditional load forecasting is based on time, emphasizing the dependence on historical data, and combining some mathematical models to predict the load value in a certain period in the future. According to the forecast period, load forecasting problems can be divided into ultra-short-term, short-term, medium-term and long-term load forecasting, corresponding to hourly, daily, monthly and annual forecasting respectively. Most of them are for a specific building, based on historical data, for load forecasting. [0003] However, for new...

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): G06Q10/04G06Q50/06G06Q50/08G06K9/62
CPCG06Q10/04G06Q50/06G06Q50/08G06F18/24323G06F18/253G06F18/214
Inventor 谭瑶张超滕振山左高王志光王彬彬赵政嘉王佳伟
Owner NARI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com