CN113468157A - Similar building selection method and device based on energy consumption analysis - Google Patents
Similar building selection method and device based on energy consumption analysis Download PDFInfo
- Publication number
- CN113468157A CN113468157A CN202110786472.4A CN202110786472A CN113468157A CN 113468157 A CN113468157 A CN 113468157A CN 202110786472 A CN202110786472 A CN 202110786472A CN 113468157 A CN113468157 A CN 113468157A
- Authority
- CN
- China
- Prior art keywords
- building
- energy consumption
- target building
- target
- predicted
- 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.)
- Granted
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 120
- 238000010187 selection method Methods 0.000 title claims description 18
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000012216 screening Methods 0.000 claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- Structural Engineering (AREA)
- Mathematical Physics (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Fuzzy Systems (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
According to the method, firstly, a box line method is adopted, primary screening is carried out on a target building according to day dimension historical energy consumption data of the target building, then, according to different classification results and statistical indexes of the target building, further screening is carried out on the primarily screened target building through different screening methods, a target building candidate set is obtained, and finally, a preset judgment rule is adopted for the target building in the target building candidate set, and the similar building is screened out from the target building candidate set. According to the method, the target building is processed and screened from multiple dimensions and multiple levels, so that the obtained historical energy consumption data of similar buildings can more accurately predict the future energy consumption condition of the building to be predicted, and the prediction efficiency is improved.
Description
Technical Field
The invention relates to the technical field of similar building screening, in particular to a similar building selection method and device based on energy consumption analysis.
Background
When the existing building sets the future energy consumption quota, the energy consumption is predicted by using a regression algorithm in machine learning according to the historical energy consumption condition of the building.
However, for a building which is just put into use or has a short service time, since the historical energy consumption data of the building is not or less, the energy consumption can not be predicted through the energy consumption data of the building, so that the historical energy consumption of the building similar to the structure and the operation mode of the building is used as a reference, and the historical energy consumption data is used as training data.
The traditional similar building selection method is judged according to personal experience, has no explanation, screens out unrepresentative buildings, predicts large quota deviation by referring to historical energy consumption and has low reliability.
Disclosure of Invention
The invention provides a similar building selection method and a similar building selection device based on energy consumption analysis, aiming at solving the problem of prediction of the existing building energy consumption with short use time, the method uses a box-line graph method to remove some buildings with abnormal average energy consumption, abnormal energy consumption fluctuation and abnormal energy consumption-temperature correlation from the perspective of the whole situation and the region respectively for the existing buildings with rich historical energy consumption data, screens out a set of candidate buildings, and selects the buildings similar to the energy consumption data from the candidate set by combining the information of the structures, the geographical position information and the like of the buildings. The specific technical scheme is as follows:
the embodiment of the invention provides a similar building selection method based on energy consumption analysis, which comprises the following steps:
acquiring a target building to be screened in a certain area, and performing data cleaning on daily dimension historical energy consumption data of the target building by using a box-line graph method to remove abnormal values;
classifying the washed historical energy consumption data according to different items, and respectively calculating corresponding item statistical indexes aiming at the different items;
screening the target building by adopting a preset screening method according to different itemized statistical indexes to obtain a target building candidate set;
and screening out similar buildings from the target building candidate set according to the judgment attribute of the building to be predicted by adopting a preset judgment rule, and predicting the future energy utilization condition of the building to be predicted by using the historical energy utilization data of the similar buildings.
Further, the step of classifying the washed historical energy consumption data according to different items and respectively calculating corresponding item statistical indexes for the different items includes the steps of:
classifying the washed historical energy consumption data into rigid subentries and elastic subentries;
the rigidity index calculated for the rigidity subsection comprises: daily average fluctuation, historical energy consumption data volume and rigid single square meter energy consumption;
the elasticity index calculated for the elasticity clause includes: the maximum mutual information coefficient of the average temperature and the historical energy consumption, the historical energy consumption data volume and the elastic single square meter energy consumption.
Further, the step of screening the target building by using a preset screening method according to different itemized statistical indexes to obtain a target building candidate set includes the steps of:
acquiring a subentry statistical index of the target building, and judging whether the subentry of the target building belongs to a rigid subentry or an elastic subentry;
if the target building belongs to the rigidity subentry, judging whether the data volume of the target building meets a preset first quantity, if so, judging whether the target building is abnormal by adopting a box line method, and removing the target building with the abnormality;
if the target building belongs to the elastic subentry, judging whether the data volume of the target building meets a preset second number or not; if the target building meets the preset second number, calculating a statistical index of a maximum mutual information coefficient of the average temperature and the historical energy consumption of the target building, judging whether the maximum mutual information coefficient is smaller than a preset threshold value, and if the maximum mutual information coefficient is smaller than the preset threshold value, removing the target building to obtain a target building candidate set.
Further, the method comprises the step of removing the buildings with abnormal energy consumption within a single square meter and abnormal daily average energy consumption by using a box line method for the screened target buildings to obtain a target building candidate set.
Further, the step of screening out similar buildings from the target building candidate set according to the judgment attribute of the building to be predicted by adopting a preset judgment rule includes:
inquiring a target building which is the same as the building area to be predicted from the target building candidate set, and judging whether the target building in the target building candidate set belongs to a similar building of the building to be predicted or not by adopting the preset judgment rule;
or inquiring a target building which is the same as the climate zone and the microclimate zone of the building to be predicted from the target building candidate set, and judging whether the target building in the target building candidate set belongs to a similar building of the building to be predicted or not by adopting the preset judgment rule.
Further, whether the target building is similar to the building to be predicted or not is judged according to multiple dimensions of the starting using time of the target building, the building area grade and the energy consumption prediction characteristic of the building to be predicted.
Further, judging whether the target building is similar to the building to be predicted according to the energy consumption prediction characteristics of the building to be predicted specifically comprises:
acquiring historical energy consumption data of the building to be predicted;
processing historical energy consumption data of the building to be predicted to obtain energy consumption prediction characteristics of the building to be predicted, wherein the energy consumption prediction characteristics comprise temperature, humidity and time;
respectively calculating the feature weights of the energy consumption prediction features of the target building and the building to be predicted in a classifier;
and judging whether the sequence and the coefficient of the characteristic weights of the target building and the building to be predicted meet preset requirements, and if so, judging that the target building belongs to a similar building of the building to be predicted.
The second aspect of the present invention provides a similar building selecting apparatus based on energy consumption analysis, including:
the cleaning module is used for acquiring a target building to be screened in a certain area, and cleaning data of daily dimension historical energy consumption data of the target building by using a box line graph method to remove abnormal values;
the classification calculation module is used for classifying the cleaned historical energy consumption data according to different items and respectively calculating corresponding item statistical indexes aiming at the different items;
the screening module is used for screening the target building by adopting a preset screening method according to different itemized statistical indexes to obtain a target building candidate set;
and the similar building judgment module is used for screening out similar buildings from the target building candidate set according to the judgment attribute of the building to be predicted by adopting a preset judgment rule, and predicting the future energy utilization condition of the building to be predicted by using the historical energy utilization data of the similar buildings.
The third aspect of the present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to process the similar building selection method based on energy consumption analysis according to any one of claims 1 to 7.
A fourth aspect of the present invention provides an electronic apparatus comprising:
a processor; and the number of the first and second groups,
a memory arranged to store computer executable instructions that when executed cause the processor to perform the method of energy consumption analysis based similar building selection according to any of claims 1-7.
According to the method, firstly, a box line method is adopted, primary screening is carried out on a target building according to day dimension historical energy consumption data of the target building, then, according to different classification results and statistical indexes of the target building, further screening is carried out on the primarily screened target building through different screening methods, a target building candidate set is obtained, and finally, a preset judgment rule is adopted for the target building in the target building candidate set, and the similar building is screened out from the target building candidate set. According to the method, the target building is processed and screened from multiple dimensions and multiple levels, so that the obtained historical energy consumption data of similar buildings can more accurately predict the future energy consumption condition of the building to be predicted, and the prediction efficiency and the reliability of the prediction result are improved.
Drawings
FIG. 1 is a flow chart of a similar building selection method based on energy consumption analysis according to the present invention;
FIG. 2 is a schematic flow chart of the present invention for cleaning data and calculating and storing statistical indicators;
FIG. 3 is a flow chart of obtaining a candidate set according to an embodiment of the present invention;
fig. 4 is a flowchart of determining whether a building is similar according to an embodiment of the present invention.
Detailed Description
The present invention is described below with reference to the accompanying drawings, but the present invention is not limited thereto.
Referring to fig. 1, a flow chart of a similar building selection method based on energy consumption analysis according to the present invention includes: s1: and acquiring a target building to be screened in a certain area, and performing data cleaning on the daily dimension historical energy consumption data of the target building by using a box-line graph method to remove abnormal values.
The building to be predicted is defined as a building with small historical energy consumption data, and other similar buildings with large historical energy consumption data need to be found as references to predict the future annual energy consumption of the building.
The above target building is defined as a building that is used to screen out buildings that can be used for the purpose of prediction as a reference.
And traversing all target buildings, and performing data cleaning on daily dimension historical energy consumption data of the target buildings by using a box line method to remove abnormal values. In the embodiment of the invention, the abnormal values are data obviously not conforming to the normal distribution rule, the data can influence the whole data distribution, the box line method determines the boundary by one quarter and three quarters of digits and the range difference of 1.5 times, and the data outside the boundary is the abnormal values.
S2: and classifying the cleaned historical energy consumption data according to different items, and respectively calculating corresponding item statistical indexes aiming at the different items.
Fig. 2 is a schematic flow chart illustrating a process of cleaning data and calculating and storing a statistical indicator according to an embodiment of the present invention.
And (3) calculating various indexes of the target building by using the cleaned historical energy consumption data, and if the indexes are rigidity items, calculating: daily average fluctuation (average value of relative errors of energy consumption of one day after day-by-day energy consumption and that of the previous day), rigid historical energy consumption data volume and rigid single square meter energy consumption (total annual energy consumption is divided by building area); if the elastic component is the elastic component, calculating: the maximum mutual information coefficient of the average temperature and the historical energy consumption, the elastic historical energy consumption data volume and the elastic single square meter energy consumption.
The rigidity subsection: the temperature dependence is low, and the annual fluctuation is small, such as: elevator subentry, illumination subentry. Elastic subentry: the temperature dependence is high, and the annual fluctuation is large, such as: air conditioner terminal itemization, heating power station itemization.
And finally, storing statistical index results such as daily average fluctuation, historical energy consumption data volume, single square meter energy consumption, maximum mutual information coefficient of average temperature and historical energy consumption and the like of each target building into a database.
S3: and screening the target building by adopting a preset screening method according to different subentry statistical indexes to obtain a target building candidate set.
Fig. 3 is a flowchart of obtaining a candidate set according to an embodiment of the present invention, which includes the following specific steps:
a1: and acquiring a subentry statistical index of the target building, and judging whether the target building belongs to a rigid subentry or an elastic subentry.
The subentry statistical indexes refer to different statistical indexes corresponding to different subentries, for example, the statistical indexes corresponding to the rigid building comprise daily average fluctuation, historical energy consumption data volume and rigid single square meter energy consumption; the statistical indexes corresponding to the elastic building comprise the maximum mutual information coefficient of the average temperature and the historical energy consumption, the historical energy consumption data volume and the elastic single square meter energy consumption.
A2: if the target building belongs to the rigidity subentry, judging whether the data volume of the target building meets a preset first quantity, if so, judging whether the target building is abnormal by adopting a box line method, and removing the abnormal target building.
A3: if the target building belongs to the elastic subentry, judging whether the data volume of the target building meets a preset second number or not; if the target building meets the preset second number, calculating a statistical index of a maximum mutual information coefficient of the average temperature and the historical energy consumption of the target building, judging whether the maximum mutual information coefficient is smaller than a preset threshold value, and if the maximum mutual information coefficient is smaller than the preset threshold value, removing the target building to obtain a target building candidate set.
In a global view, the statistical index results of all target buildings stored in the database are obtained, and target buildings with abnormal statistical indexes are removed from all the target buildings, specifically, if the target buildings belong to rigid items, and the first number is assumed to be 180, buildings with data volume less than 180 are removed, buildings with abnormal energy consumption of a single square meter are removed by using a box-line graph method, and buildings with abnormal daily fluctuation are removed by using a box-line graph method. Assuming that the second number is 300 and the preset threshold is 0.3, the removed data size is less than 300 buildings, and the removed maximum mutual information coefficient between the average temperature and the historical energy consumption is less than 0.3.
In an optional implementation manner of the embodiment of the present invention, the method further includes, in consideration of the area, traversing all areas, obtaining statistical indexes of all remaining target buildings in the area, removing buildings with abnormal energy consumption per square meter in the area by using a box-line graph method, and removing buildings with abnormal daily average energy consumption in the area by using the box-line graph method. And saving the final target building candidate set to a database.
S4: and screening out similar buildings from the target building candidate set according to the judgment attribute of the building to be predicted by adopting a preset judgment rule, and predicting the future energy utilization condition of the building to be predicted by using the historical energy utilization data of the similar buildings.
Referring to fig. 4, a flowchart of determining whether a building is a similar building according to an embodiment of the present invention, in the embodiment of the present invention, the selecting a similar building from the target building candidate set according to the determination attribute of the building to be predicted by using a preset determination rule includes:
and inquiring a target building which is the same as the building area to be predicted from the target building candidate set, and judging whether the target building in the target building candidate set belongs to a similar building of the building to be predicted or not by adopting the preset judgment rule.
That is, if the target building in the target building candidate set and the building to be predicted belong to the same area, it may be determined whether the target building and the building to be predicted belong to similar buildings by:
firstly, judging that the starting use time of the target building meets the requirement, such as putting into use after 2015;
and/or judging whether the area grades of the target building and the building to be predicted belong to the same grade, wherein the building areas of the building to be predicted and the target building are both 50000 square meters and the like. In the embodiment of the invention, the building area is divided into four grades, 1 grade: less than 50000 square meters; and 2, stage: 50000 + 75000 square meters; and 3, level: 75000 100000 square meters; 4, level: 100000 square meters or more.
And/or then if the building to be predicted has a small part of historical energy consumption data, respectively calculating the proportion of the target building and the feature of the building to be predicted in the classifier according to the features (temperature, humidity, time and the like) to be used in energy consumption prediction, wherein the feature weight sequence between the two buildings is required to be the same, and the weight coefficients are similar.
In an optional implementation manner of the embodiment of the present invention, the screening out similar buildings from the target building candidate set according to the judgment attribute of the building to be predicted by using a preset judgment rule includes:
and inquiring target buildings which are the same as the climate zone and the microclimate zone of the building to be predicted from the target building candidate set, and judging whether the target buildings in the target building candidate set belong to similar buildings of the building to be predicted by adopting the preset judgment rule.
According to the method, firstly, a box line method is adopted, primary screening is carried out on a target building according to day dimension historical energy consumption data of the target building, then, according to different classification results and statistical indexes of the target building, further screening is carried out on the primarily screened target building through different screening methods, a target building candidate set is obtained, and finally, a preset judgment rule is adopted for the target building in the target building candidate set, and the similar building is screened out from the target building candidate set. According to the method, the target building is processed and screened from multiple dimensions and multiple levels, so that the obtained historical energy consumption data of similar buildings can more accurately predict the future energy consumption condition of the building to be predicted, and the prediction efficiency is improved.
The second aspect of the present invention provides a similar building selecting apparatus based on energy consumption analysis, including:
the cleaning module is used for acquiring a target building to be screened in a certain area, and cleaning data of daily dimension historical energy consumption data of the target building by using a box line graph method to remove abnormal values;
the classification calculation module is used for classifying the cleaned historical energy consumption data according to different items and respectively calculating corresponding item statistical indexes aiming at the different items;
the screening module is used for screening the target building by adopting a preset screening method according to different itemized statistical indexes to obtain a target building candidate set;
and the similar building judgment module is used for screening out similar buildings from the target building candidate set according to the judgment attribute of the building to be predicted by adopting a preset judgment rule, and predicting the future energy utilization condition of the building to be predicted by using the historical energy utilization data of the similar buildings.
The third aspect of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to process a similar building selection method based on energy consumption analysis.
A fourth aspect of the present invention provides an electronic apparatus comprising:
a processor; and the number of the first and second groups,
a memory arranged to store computer executable instructions that, when executed, cause the processor to perform a similar building selection method based on energy consumption analysis.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (10)
1. A similar building selection method based on energy consumption analysis is characterized by comprising the following steps:
acquiring a target building to be screened in a certain area, and performing data cleaning on daily dimension historical energy consumption data of the target building by using a box-line graph method to remove abnormal values;
classifying the washed historical energy consumption data according to different items, and respectively calculating corresponding item statistical indexes aiming at the different items;
screening the target building by adopting a preset screening method according to different itemized statistical indexes to obtain a target building candidate set;
and screening out similar buildings from the target building candidate set according to the judgment attribute of the building to be predicted by adopting a preset judgment rule, and predicting the future energy utilization condition of the building to be predicted by using the historical energy utilization data of the similar buildings.
2. The method for selecting similar buildings based on energy consumption analysis according to claim 1, wherein the washed historical energy consumption data are classified according to different items, and corresponding item statistical indexes are respectively calculated for different items, comprising the steps of:
classifying the washed historical energy consumption data into rigid subentries and elastic subentries;
the rigidity index calculated for the rigidity subsection comprises: daily average fluctuation, historical energy consumption data volume and rigid single square meter energy consumption;
the elasticity index calculated for the elasticity clause includes: the maximum mutual information coefficient of the average temperature and the historical energy consumption, the historical energy consumption data volume and the elastic single square meter energy consumption.
3. The similar building selection method based on energy consumption analysis according to claim 1, wherein the method for screening the target building by adopting a preset screening method according to different itemized statistical indexes to obtain a target building candidate set comprises the following steps:
acquiring a subentry statistical index of the target building, and judging whether the target building belongs to a rigid subentry or an elastic subentry;
if the target building belongs to the rigidity subentry, judging whether the data volume of the target building meets a preset first quantity, if so, judging whether the target building is abnormal by adopting a box line method, and removing the target building with the abnormality;
if the target building belongs to the elastic subentry, judging whether the data volume of the target building meets a preset second number or not; if the target building meets the preset second number, calculating a statistical index of a maximum mutual information coefficient of the average temperature and the historical energy consumption of the target building, judging whether the maximum mutual information coefficient is smaller than a preset threshold value, and if the maximum mutual information coefficient is smaller than the preset threshold value, removing the target building to obtain a target building candidate set.
4. The similar building selection method based on energy consumption analysis according to claim 3, further comprising removing buildings with abnormal energy consumption within a single square meter and abnormal daily average energy consumption by using a box line method on the screened target buildings to obtain a target building candidate set.
5. The similar building selection method based on energy consumption analysis according to claim 1, wherein the step of adopting a preset judgment rule to screen similar buildings from the target building candidate set according to the judgment attribute of the building to be predicted comprises the following steps:
inquiring a target building which is the same as the building area to be predicted from the target building candidate set, and judging whether the target building in the target building candidate set belongs to a similar building of the building to be predicted or not by adopting the preset judgment rule;
and/or inquiring a target building which is the same as the climate zone and the microclimate zone of the building to be predicted from the target building candidate set, and judging whether the target building in the target building candidate set belongs to a similar building of the building to be predicted by adopting the preset judgment rule.
6. The similar building selection method based on energy consumption analysis according to claim 1, wherein whether the target building is similar to the building to be predicted is judged from multiple dimensions of the starting time of use, building area grade and energy consumption prediction characteristics of the building to be predicted respectively.
7. The similar building selection method based on energy consumption analysis according to claim 6, wherein judging whether the target building is similar to the building to be predicted according to the energy consumption prediction characteristics of the building to be predicted specifically comprises:
acquiring historical energy consumption data of the building to be predicted;
processing historical energy consumption data of the building to be predicted to obtain energy consumption prediction characteristics of the building to be predicted, wherein the energy consumption prediction characteristics comprise temperature, humidity and time;
respectively calculating the feature weights of the energy consumption prediction features of the target building and the building to be predicted in a classifier;
and judging whether the sequence and the coefficient of the characteristic weights of the target building and the building to be predicted meet preset requirements, and if so, judging that the target building belongs to a similar building of the building to be predicted.
8. The utility model provides a device is selected to similar building based on energy consumption analysis which characterized in that includes:
the cleaning module is used for acquiring a target building to be screened in a certain area, and cleaning data of daily dimension historical energy consumption data of the target building by using a box line graph method to remove abnormal values;
the classification calculation module is used for classifying the cleaned historical energy consumption data according to different items and respectively calculating corresponding item statistical indexes aiming at the different items;
the screening module is used for screening the target building by adopting a preset screening method according to different itemized statistical indexes to obtain a target building candidate set;
and the similar building judgment module is used for screening out similar buildings from the target building candidate set according to the judgment attribute of the building to be predicted by adopting a preset judgment rule, and predicting the future energy utilization condition of the building to be predicted by using the historical energy utilization data of the similar buildings.
9. A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to process the similar building selection method based on energy consumption analysis according to any one of claims 1-7.
10. An electronic device, comprising:
a processor; and the number of the first and second groups,
a memory arranged to store computer executable instructions that when executed cause the processor to perform the method of energy consumption analysis based similar building selection according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110786472.4A CN113468157B (en) | 2021-07-12 | 2021-07-12 | Similar building selection method and device based on energy consumption analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110786472.4A CN113468157B (en) | 2021-07-12 | 2021-07-12 | Similar building selection method and device based on energy consumption analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113468157A true CN113468157A (en) | 2021-10-01 |
| CN113468157B CN113468157B (en) | 2024-04-26 |
Family
ID=77880129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110786472.4A Active CN113468157B (en) | 2021-07-12 | 2021-07-12 | Similar building selection method and device based on energy consumption analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113468157B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429285A (en) * | 2021-12-31 | 2022-05-03 | 博锐尚格科技股份有限公司 | Energy-saving amount calculation method and device, electronic equipment and storage medium |
| CN116757534A (en) * | 2023-06-15 | 2023-09-15 | 中国标准化研究院 | Intelligent refrigerator reliability analysis method based on neural training network |
| CN117290797A (en) * | 2023-11-24 | 2023-12-26 | 国网山东省电力公司济宁供电公司 | Building energy consumption prediction method, system, device and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110190951A1 (en) * | 2010-02-01 | 2011-08-04 | International Business Machines Corporation | Assessing, forecasting and simulating energy consumption of buildings using energy efficiency coefficients |
| CN103019205A (en) * | 2012-12-13 | 2013-04-03 | 西安华腾光电有限责任公司 | Office building energy-saving monitoring method based on internet of things |
| CN106934596A (en) * | 2017-03-01 | 2017-07-07 | 广东中建普联科技股份有限公司 | Construction project data managing method and system based on similarity comparison |
| CN109858700A (en) * | 2019-02-01 | 2019-06-07 | 华北水利水电大学 | BP neural network heating system energy consumption prediction technique based on similar screening sample |
| CN110009156A (en) * | 2019-04-08 | 2019-07-12 | 北京博锐尚格节能技术股份有限公司 | Building energy consumption budget management method and storage medium |
| CN110276393A (en) * | 2019-06-19 | 2019-09-24 | 西安建筑科技大学 | A kind of compound prediction technique of green building energy consumption |
| CN112288597A (en) * | 2020-11-24 | 2021-01-29 | 四川长虹电器股份有限公司 | Energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm |
| CN112330012A (en) * | 2020-11-03 | 2021-02-05 | 山东大卫国际建筑设计有限公司 | Building energy consumption prediction method and equipment based on transfer learning |
-
2021
- 2021-07-12 CN CN202110786472.4A patent/CN113468157B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110190951A1 (en) * | 2010-02-01 | 2011-08-04 | International Business Machines Corporation | Assessing, forecasting and simulating energy consumption of buildings using energy efficiency coefficients |
| CN103019205A (en) * | 2012-12-13 | 2013-04-03 | 西安华腾光电有限责任公司 | Office building energy-saving monitoring method based on internet of things |
| CN106934596A (en) * | 2017-03-01 | 2017-07-07 | 广东中建普联科技股份有限公司 | Construction project data managing method and system based on similarity comparison |
| CN109858700A (en) * | 2019-02-01 | 2019-06-07 | 华北水利水电大学 | BP neural network heating system energy consumption prediction technique based on similar screening sample |
| CN110009156A (en) * | 2019-04-08 | 2019-07-12 | 北京博锐尚格节能技术股份有限公司 | Building energy consumption budget management method and storage medium |
| CN110276393A (en) * | 2019-06-19 | 2019-09-24 | 西安建筑科技大学 | A kind of compound prediction technique of green building energy consumption |
| CN112330012A (en) * | 2020-11-03 | 2021-02-05 | 山东大卫国际建筑设计有限公司 | Building energy consumption prediction method and equipment based on transfer learning |
| CN112288597A (en) * | 2020-11-24 | 2021-01-29 | 四川长虹电器股份有限公司 | Energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm |
Non-Patent Citations (3)
| Title |
|---|
| MOHAMED A. UMBARK ET AL.: "Energy Consumption in Residential Buildings: Comparison between Three Different Building Styles", 《 HTTPS://DOI.ORG/10.30560/SDR.V2N1P1》, 21 March 2020 (2020-03-21), pages 1 - 8 * |
| 曾凡芝: "重庆市某公共建筑节能设计优化分析", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, 15 March 2017 (2017-03-15), pages 038 - 540 * |
| 王马明: "基于数据驱动的建筑能耗评价方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, 15 July 2019 (2019-07-15), pages 038 - 217 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114429285A (en) * | 2021-12-31 | 2022-05-03 | 博锐尚格科技股份有限公司 | Energy-saving amount calculation method and device, electronic equipment and storage medium |
| CN116757534A (en) * | 2023-06-15 | 2023-09-15 | 中国标准化研究院 | Intelligent refrigerator reliability analysis method based on neural training network |
| CN116757534B (en) * | 2023-06-15 | 2024-03-15 | 中国标准化研究院 | Intelligent refrigerator reliability analysis method based on neural training network |
| CN117290797A (en) * | 2023-11-24 | 2023-12-26 | 国网山东省电力公司济宁供电公司 | Building energy consumption prediction method, system, device and medium |
| CN117290797B (en) * | 2023-11-24 | 2024-02-02 | 国网山东省电力公司济宁供电公司 | Building energy consumption prediction method, system, device and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113468157B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105930976B (en) | Node voltage sag severity comprehensive evaluation method based on weighted ideal point method | |
| CN113468157A (en) | Similar building selection method and device based on energy consumption analysis | |
| KR102097953B1 (en) | Failure risk index estimation device and failure risk index estimation method | |
| CN104899451A (en) | Time sequence prediction model selecting method based on statistical signal process | |
| RU2004126675A (en) | SYSTEM OF ANALYSIS OF DESIGN AND PRODUCTION PROCESSES | |
| CN111327377A (en) | Method, device, equipment and storage medium for field intensity prediction | |
| KR101553476B1 (en) | Apparatus for measuring likelihood ratio of building and method thereof | |
| CN112097365A (en) | Air conditioner fault detection and identification method and device based on prediction and classification model | |
| CN110503462A (en) | Power grid investment measuring and calculating method, system and medium based on grey correlation degree analysis | |
| CN111401642A (en) | Method, device and equipment for automatically adjusting predicted value and storage medium | |
| CN114118588A (en) | Peak-facing summer power failure prediction method based on game feature extraction under clustering undersampling | |
| JP5715445B2 (en) | Quality estimation apparatus, quality estimation method, and program for causing computer to execute quality estimation method | |
| CN111539840A (en) | Electricity stealing detection method and system fusing clustering and density estimation | |
| CN117575564A (en) | Extensible infrastructure network component maintenance and transformation decision evaluation method and system | |
| CN105931133A (en) | Distribution transformer replacement priority evaluation method and device | |
| CN116432524A (en) | Transformer oil temperature prediction method, device, equipment and storage medium | |
| CN113887816A (en) | Intelligent prediction method, device and equipment for social reserve of household appliances | |
| CN112116139A (en) | Power demand prediction method and system | |
| CN115943399A (en) | Generation method, generation device, program, information processing method, and information processing device | |
| CN112734289A (en) | National defense technology development period evaluation method and system | |
| CN112348584A (en) | Vehicle estimation method, device and equipment | |
| CN111340276A (en) | Method and system for generating prediction data | |
| CN115009744B (en) | Method and device for predicting delivery duration of front cargo | |
| CN104217093A (en) | Method and apparatus for identifying root cause of defect using composite defect map | |
| CN118604640B (en) | Battery evaluation method, device, electronic equipment, storage medium and program product |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |