Multi-generation system load prediction method based on evidence regression multiple models
A technology of system load and forecasting method, which is applied in forecasting, data processing applications, character and pattern recognition, etc., and can solve problems such as nonlinearity, large inertia uncertainty, and difficulty in realization
Inactive Publication Date: 2021-03-16
ELECTRIC POWER RES INST OF EAST INNER MONGOLIA ELECTRIC POWER +2
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Due to the diversity of load influencing factors, its nonlinearity, large inertia, uncertainty and time-varying parameters, it is difficult to establish an accurate prediction model
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment approach
[0036] refer to figure 1 , the present invention provides a specific technical implementation of the multi-generation system load forecasting method based on evidence regression multi-model, the main steps include:
[0037] S1. Data collection, that is, collecting electricity, heat and gas load operation data and performing clustering;
[0038] S2. Data preprocessing, that is, organize, screen, and clean the original data, select parameter data related to electricity, heat, and gas loads based on the clustering results, and build an offline database;
[0039] S3. Correlation analysis, that is, based on the offline database, analyze the influencing factors affecting the electricity, heat, and gas loads, and establish a correlation model to determine the factors affecting the electricity, heat, and gas loads;
[0040] S4. Evidence regression prediction, that is, based on the evidence regression method, an evidence library of electricity, heat, and gas loads and their influencin...
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
Login to View More Abstract
The invention provides a multi-generation system load prediction method based on evidence regression multiple models. The multi-generation system load prediction method mainly comprises a data acquisition module, a data management module, an offline database, a data analysis and processing module and an evidence regression prediction module. The invention provides a load prediction method based onevidence regression multiple models in a multi-generation system environment. The load prediction method is a data mining algorithm based on evidence regression and used for load prediction. According to the system, multiple uncertain attributes influencing the load and fuzziness of influencing factors are considered, and the power consumption, heat consumption and gas consumption load rules of the user can be mastered relatively completely. The prediction method mainly aims at various associated factors related to load change, finds out influence factors with high association degree, excavates user energy consumption behaviors through clustering, reflects different load prediction areas by adopting different structural parameters, and provides a new solution for high-precision uncertainty prediction of the load after large-scale renewable new energy grid connection.
Description
technical field [0001] The invention relates to the technical field of multi-generation system load forecasting, and more specifically, relates to a multi-generation system load prediction method based on evidence regression multi-model. Background technique [0002] In order to ensure the safe and economical operation of the integrated energy system under the Energy Internet, analyzing the massive historical data of electricity, heat, and gas loads, and discovering and utilizing the hidden information in the data will help to further improve the operation and management level of the integrated energy system and improve The precision of day-ahead, intra-day and real-time scheduling ensures safe, reliable and stable operation of the system. Under the Energy Internet, the randomness and uncertainty of power generation of biomass energy, wind energy, photovoltaic and other renewable energy power generation systems pose challenges to the safe and stable operation of the system. ...
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
Login to View More IPC IPC(8): G06Q10/04G06Q50/06G06K9/62
CPCG06Q10/04G06Q50/06G06F18/2135G06F18/23213
Inventor 赵鹏翔佟敏党乐王楠李振周喜超丛琳李娜
Owner ELECTRIC POWER RES INST OF EAST INNER MONGOLIA ELECTRIC POWER