CN116071099A - Heat supply demand prediction method and system - Google Patents
Heat supply demand prediction method and system Download PDFInfo
- Publication number
- CN116071099A CN116071099A CN202310090327.1A CN202310090327A CN116071099A CN 116071099 A CN116071099 A CN 116071099A CN 202310090327 A CN202310090327 A CN 202310090327A CN 116071099 A CN116071099 A CN 116071099A
- Authority
- CN
- China
- Prior art keywords
- heat supply
- demand prediction
- data
- historical
- operation data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000010438 heat treatment Methods 0.000 claims description 23
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 2
- 238000010219 correlation analysis Methods 0.000 claims description 2
- 238000007637 random forest analysis Methods 0.000 claims description 2
- 238000000611 regression analysis Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Game Theory and Decision Science (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Water Supply & Treatment (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a heat supply demand prediction algorithm and a heat supply demand prediction system, wherein the heat supply demand prediction algorithm comprises the following steps: acquiring real-time operation data and real-time environment parameter data; and obtaining a heat supply demand prediction result through the real-time operation data, the real-time environment parameter data and the trained heat supply demand prediction model, wherein the history operation data with the similarity of the real-time operation data being more than or equal to a set value and the environment parameter data corresponding to the history operation data are selected as training samples to train the constructed heat supply demand prediction model, and the trained heat supply demand prediction model is obtained. Accurate prediction of heat supply demand is achieved.
Description
Technical Field
The invention relates to the technical field of new energy and energy conservation, in particular to a heat supply demand prediction method and a heat supply demand prediction system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The heat supply has great delay, and the heat supply requirement of a user is met mainly by predicting the requirement of the user at the end in advance, however, the fluctuation of the requirement of the user and weather conditions causes the difference between the predicted value in advance and the real requirement of the end.
The scheme adopted in the heat load prediction is usually lstm regression analysis, but the inventor finds that when the conventional method utilizes the lstm regression analysis to predict the user demand, the lstm model is trained by acquiring training data, and the trained model is utilized to predict the user demand, but the fluctuation of the operation working condition is not considered, so that the influence on the user demand prediction is caused, and the result of the demand prediction is inaccurate.
Disclosure of Invention
In order to solve the problems, the invention provides a heat supply demand prediction method and a heat supply demand prediction system, wherein historical data conforming to the operation conditions of real-time operation data are used as training samples, and when a heat supply demand prediction model trained by the training samples is used for heat supply demand prediction, the accuracy of heat supply demand prediction is improved.
In order to achieve the above purpose, the invention adopts the following technical scheme:
in a first aspect, a heat supply demand prediction algorithm is provided, including:
acquiring real-time operation data and real-time environment parameter data;
and obtaining a heat supply demand prediction result through the real-time operation data, the real-time environment parameter data and the trained heat supply demand prediction model, wherein the history operation data with the similarity of the real-time operation data being more than or equal to a set value and the environment parameter data corresponding to the history operation data are selected as training samples to train the constructed heat supply demand prediction model, and the trained heat supply demand prediction model is obtained.
In a second aspect, a heat supply demand prediction system is provided, including:
the data acquisition module is used for acquiring real-time operation data and real-time environment parameter data;
the heat supply demand prediction module is used for obtaining a heat supply demand prediction result through real-time operation data, real-time environment parameter data and a trained heat supply demand prediction model, wherein historical operation data with similarity greater than or equal to a set value and environment parameter data corresponding to the historical operation data are selected as training samples to train the constructed heat supply demand prediction model, and the trained heat supply demand prediction model is obtained.
In a third aspect, an electronic device is provided comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the steps of a heat supply demand prediction method.
In a fourth aspect, a computer readable storage medium is provided for storing computer instructions which, when executed by a processor, perform the steps of a method for predicting heating demand.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, when the training sample of the heat supply demand prediction model is selected, the operation condition of the real-time operation data is considered, the similarity of the real-time operation data and the historical operation data is calculated, the historical operation data with the similarity greater than or equal to the set value is selected as the training sample, the training sample is identical to the real-time operation data in operation condition, and when the heat supply demand prediction model trained by the training sample is used for carrying out the user demand prediction, the accuracy of the user demand prediction is improved.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application.
Fig. 1 is a flow chart of the method disclosed in example 1.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
Example 1
In order to achieve accurate prediction of the heat supply demand of a user, in this embodiment a heat supply demand prediction algorithm is disclosed comprising:
s1: and acquiring real-time operation data and real-time environment parameter data.
The acquired real-time operation data comprise the flow rate of the hot water output by the heating system, the temperature of the hot water and the like.
The environmental parameter data includes data such as room temperature and illumination intensity.
Specific operational data and environmental parameters may be selected based on real-time requirements, including but not limited to the above parameter data.
S2: and obtaining a heat supply demand prediction result through the real-time operation data, the real-time environment parameter data and the trained heat supply demand prediction model, wherein the history operation data with the similarity of the real-time operation data being more than or equal to a set value and the environment parameter data corresponding to the history operation data are selected as training samples to train the constructed heat supply demand prediction model, and the trained heat supply demand prediction model is obtained.
The heat supply demand prediction model takes operation data and environmental parameter data as input, takes a heat supply demand temperature prediction result as output, and is obtained by adopting LSTM construction.
In order to ensure accurate prediction of heat supply demand, the embodiment selects the historical data of the same operation condition as the real-time operation data as a training sample, and trains a heat supply demand prediction model.
The process of obtaining the training sample of the same operation condition to which the real-time operation data belongs is as follows:
acquiring historical operation data, historical environment parameter data and corresponding historical heating temperature of a heating system;
calculating the similarity of the real-time operation data and the historical operation data;
when the similarity is greater than or equal to a set value, a training sample is constructed through the acquired historical operation data, the historical environment parameter data and the corresponding historical heat supply temperature;
when the similarity is smaller than a set value, acquiring new historical operation data, historical environment parameter data and corresponding historical heat supply temperature, and adding the new historical operation data, the historical environment parameter data and the corresponding historical heat supply temperature into the existing historical data;
and calculating the similarity between the real-time operation data and all the history operation data added with the new history operation data, and constructing a training sample through all the history data added with the new history data when the similarity is greater than or equal to a set value.
Specific: acquiring historical operation data, historical environmental parameter data and corresponding historical heating temperatures of a system;
and performing correlation analysis on the historical operation data, the historical environment parameter data and the corresponding historical heat supply temperature by a Pearson correlation coefficient method, selecting the historical operation data and the historical environment parameter data which are related to the historical heat supply temperature, and training a heat supply demand prediction model by taking the selected data as a training sample.
And because the acquired various historical data have the problems of missing values, dirty data, different dimension data sizes and the like, the acquired data are required to be preprocessed, common methods include mean filling and kmeans outlier identification, and the input data with different dimensions are normalized.
And constructing a heat supply demand prediction model which takes operation data and environmental parameter data as input and a heat supply demand prediction result as output through the LSTM, and training the heat supply demand prediction model through a training sample to obtain a trained heat supply demand prediction model.
Calculating the similarity of the real-time operation data and the historical operation data in the training samples through a random forest algorithm, namely, for the current data samples, voting for all trees for all types/the number of all trees, and if the similarity is greater than or equal to a set value of 0.8, using a trained heat supply demand prediction model to predict the heat supply demand; if the similarity is smaller than the set value of 0.8, the fact that the similarity of the current operation data and the historical operation data in the training data is lower is indicated that the heat supply system working condition has a certain probability of being changed, in order to ensure the accuracy of prediction of the heat supply demand prediction model, new historical sample data are added on the basis of the original training samples, the heat supply demand prediction model is updated again through all samples, real-time operation data and environmental parameter data are analyzed after updating, a heat supply demand prediction result is obtained, and similarity calculation is carried out on the heat supply demand prediction result and all the historical operation data in the samples until the similarity is larger than or equal to the set value of 0.8, and a final heat supply demand prediction result is obtained.
The embodiment also sets a safety strategy for the obtained heat supply demand prediction result, when the heat supply demand temperature prediction result is smaller than a first threshold value or larger than a second threshold value, triggers an alarm, enters a safety mode after triggering the alarm, marks and stores the obtained real-time operation data, environment parameter data and the obtained heat supply demand prediction result, then trains the heat supply demand prediction model as a training sample, or loads a default safety mode to ensure heat supply safety, and exits the safety strategy after the abnormal condition is processed.
The method disclosed by the embodiment can realize regression modeling of multidimensional variables, and can sense whether a new working condition appears in the heating system, so that a trained heating demand prediction model is consistent with the system operation working condition, and secondly, the LSTM is sensitive to long-time sequence data, and the problem of heating demands of the heating system can be effectively solved.
The method disclosed by the embodiment can realize real-time prediction of the heating system and effectively solve the defect of long delay of the heating system.
Example 2
In this embodiment, a heating demand prediction system is disclosed, comprising:
the data acquisition module is used for acquiring real-time operation data and real-time environment parameter data;
the heat supply demand prediction module is used for obtaining a heat supply demand prediction result through real-time operation data, real-time environment parameter data and a trained heat supply demand prediction model, wherein historical operation data with similarity greater than or equal to a set value and environment parameter data corresponding to the historical operation data are selected as training samples to train the constructed heat supply demand prediction model, and the trained heat supply demand prediction model is obtained.
Example 3
In this embodiment, an electronic device is disclosed that includes a memory and a processor, and computer instructions stored on the memory and running on the processor that, when executed by the processor, perform the steps of a heat supply demand prediction method disclosed in embodiment 1.
Example 4
In this embodiment, a computer readable storage medium is disclosed for storing computer instructions that, when executed by a processor, perform the steps of a heat supply demand prediction method disclosed in embodiment 1.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. A heating demand prediction algorithm, comprising:
acquiring real-time operation data and real-time environment parameter data;
and obtaining a heat supply demand prediction result through the real-time operation data, the real-time environment parameter data and the trained heat supply demand prediction model, wherein the history operation data with the similarity of the real-time operation data being more than or equal to a set value and the environment parameter data corresponding to the history operation data are selected as training samples to train the constructed heat supply demand prediction model, and the trained heat supply demand prediction model is obtained.
2. A heating demand prediction algorithm as claimed in claim 1, wherein a random forest algorithm is used to calculate the similarity of real-time operational data to historical operational data.
3. A heating demand prediction algorithm as claimed in claim 1, wherein the specific process of obtaining training samples is:
acquiring historical operation data, historical environment parameter data and corresponding historical heating temperature of a heating system;
calculating the similarity of the real-time operation data and the historical operation data;
when the similarity is greater than or equal to a set value, a training sample is constructed through the acquired historical operation data, the historical environment parameter data and the corresponding historical heat supply temperature;
when the similarity is smaller than a set value, acquiring new historical operation data, historical environment parameter data and corresponding historical heat supply temperature, and adding the new historical operation data, the historical environment parameter data and the corresponding historical heat supply temperature into the existing historical data;
and calculating the similarity between the real-time operation data and all the history operation data added with the new history operation data, and constructing a training sample through all the history data added with the new history data when the similarity is greater than or equal to a set value.
4. A heat supply demand prediction algorithm as claimed in claim 1, wherein the historical operating data, the historical environmental parameter data and the corresponding historical heat supply temperatures are subjected to correlation analysis by pearson correlation coefficient method, the historical operating data and the historical environmental parameter data related to the historical heat supply temperatures are selected, and the constructed heat supply demand prediction model is trained by the selected data.
5. A heating demand prediction algorithm as claimed in claim 1, wherein the heating demand prediction model is obtained by LSTM construction with the operation data and the environmental parameter data as inputs and the heating demand temperature prediction result as output.
6. A heat supply demand prediction algorithm as claimed in claim 1, wherein the acquired real-time operation data, the environmental parameter data and the acquired heat supply demand prediction result are stored when the heat supply demand temperature prediction result is smaller than a set first threshold value or larger than a set second threshold value, and the heat supply demand prediction model is trained as a training sample.
7. A heating demand prediction algorithm as claimed in claim 1, wherein the heating system is operated in a safe operating mode when the heating demand temperature prediction result is less than a set first threshold value or greater than a set second threshold value.
8. A heat supply demand prediction system, comprising:
the data acquisition module is used for acquiring real-time operation data and real-time environment parameter data;
the heat supply demand prediction module is used for obtaining a heat supply demand prediction result through real-time operation data, real-time environment parameter data and a trained heat supply demand prediction model, wherein historical operation data with similarity greater than or equal to a set value and environment parameter data corresponding to the historical operation data are selected as training samples to train the constructed heat supply demand prediction model, and the trained heat supply demand prediction model is obtained.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the steps of a heat supply demand prediction method as claimed in any one of claims 1 to 7.
10. A computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of a heat supply demand prediction method as claimed in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310090327.1A CN116071099A (en) | 2023-01-31 | 2023-01-31 | Heat supply demand prediction method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310090327.1A CN116071099A (en) | 2023-01-31 | 2023-01-31 | Heat supply demand prediction method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116071099A true CN116071099A (en) | 2023-05-05 |
Family
ID=86179852
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310090327.1A Pending CN116071099A (en) | 2023-01-31 | 2023-01-31 | Heat supply demand prediction method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116071099A (en) |
-
2023
- 2023-01-31 CN CN202310090327.1A patent/CN116071099A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Li et al. | Attention-based interpretable neural network for building cooling load prediction | |
CN109035067A (en) | Building energy consumption processing method and processing device based on RF and ARMA algorithm | |
KR102103006B1 (en) | Method and Apparatus for Operating Optimal of Equipment based on Machine Learning Model | |
CN112283876A (en) | Air conditioner fault prediction method and air conditioner | |
CN115827411A (en) | Online monitoring and operation and maintenance evaluation system and method for automation equipment | |
CN116700193A (en) | Factory workshop intelligent monitoring management system and method thereof | |
CN113868953A (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
Dong et al. | Real-time detection of wind power abnormal data based on semi-supervised learning Robust Random Cut Forest | |
CN117213143B (en) | Energy-conserving and evaluation system of freezer based on AI intelligent regulation | |
CN116071099A (en) | Heat supply demand prediction method and system | |
CN117034169A (en) | Power grid main transformer equipment abnormal state prediction method based on time sequence causality network | |
CN116306240A (en) | Device health and life prediction method and device, computer device and storage medium | |
CN114254904B (en) | Method and device for evaluating operation health degree of engine room of wind turbine generator | |
CN115358320A (en) | Fault diagnosis method and system for heating, ventilating and air conditioning system | |
CN111931798B (en) | Method for classifying and detecting cold head state and predicting service life | |
KR102311857B1 (en) | Prediction System for preheating time of gas turbine | |
CN118035731B (en) | Electricity safety monitoring and early warning method and service system | |
CN117951628B (en) | Abnormal data monitoring method and system for heating system | |
CN117592571B (en) | Air conditioning unit fault type diagnosis method and system based on big data | |
CN116760033B (en) | Real-time power demand prediction system based on artificial intelligence | |
CN116594833A (en) | Equipment detection and evaluation method and device, computer equipment and storage medium | |
Jiang | A novel approach for selecting underlying variables of a stochastic degradation process | |
CN117745164A (en) | Cold chain cargo temperature early warning method and system based on LSTM model | |
CN115774958A (en) | Data center refrigerating system prediction and shutdown temperature setting optimization method | |
CN117829816A (en) | Intelligent equipment maintenance guiding method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |