CN116907139B - Improved association rule cooling side energy efficiency optimization method based on similarity search - Google Patents
Improved association rule cooling side energy efficiency optimization method based on similarity search Download PDFInfo
- Publication number
- CN116907139B CN116907139B CN202310829094.2A CN202310829094A CN116907139B CN 116907139 B CN116907139 B CN 116907139B CN 202310829094 A CN202310829094 A CN 202310829094A CN 116907139 B CN116907139 B CN 116907139B
- Authority
- CN
- China
- Prior art keywords
- working condition
- similar
- temp
- cop
- under
- 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.)
- Active
Links
- 238000001816 cooling Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000005457 optimization Methods 0.000 title claims abstract description 18
- 238000005265 energy consumption Methods 0.000 claims abstract description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 13
- 238000005065 mining Methods 0.000 claims abstract description 10
- 238000004140 cleaning Methods 0.000 claims abstract description 6
- 239000000498 cooling water Substances 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000005611 electricity Effects 0.000 claims description 8
- 238000007710 freezing Methods 0.000 claims description 7
- 230000008014 freezing Effects 0.000 claims description 7
- 238000005057 refrigeration Methods 0.000 claims description 6
- 238000011217 control strategy Methods 0.000 abstract description 6
- 238000004422 calculation algorithm Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 8
- 238000004134 energy conservation Methods 0.000 description 4
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 229910021419 crystalline silicon Inorganic materials 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012774 insulation material Substances 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- F25B49/00—Arrangement or mounting of control or safety devices
-
- 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
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Mechanical Engineering (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Thermal Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The improved association rule cooling side energy efficiency optimization method based on similarity search comprises the steps of obtaining historical data of a cooling side of a certain water chilling unit, and cleaning to construct a database; collecting real-time data of a cooling side of a certain water chilling unit; searching strategies under the similar historical working conditions, the corresponding energy consumption ratio of the similar working conditions and the corresponding energy consumption ratio of the similar working conditions according to the collected real-time data and the historical data, namely setting control points in the historical working conditions similar to the current working conditions, wherein the control points comprise cooling water pump temperature difference control and/or tower outlet water temperature control. According to the invention, the matching working condition can be searched and matched more comprehensively based on the association rule of the similarity, the control strategy search based on the historical data is realized through the similarity threshold division and the association rule, the project energy efficiency is optimized, the operation cost is reduced, and more reasonable data sets can be generated independently for mining.
Description
Technical Field
The invention relates to the technical field of energy efficiency optimization of a high-efficiency refrigerating machine room, in particular to an improved association rule cooling side energy efficiency optimization method based on similarity search.
Background
Along with the continuous running of the requirements of carbon peak and carbon neutralization into social production, various industries gradually realize the importance of energy conservation and emission reduction in production, and meanwhile, the energy conservation problem is more and more focused by students worldwide due to the energy problem commonly faced in the world. According to the statistics of the United nations environmental planning agency, the energy consumption of the building is more than 50% of the total civil energy consumption, and the energy consumption of the Chinese building is about 25% of the total social energy consumption, wherein the heating ventilation air conditioner is a unbroken energy consumption large household, and in the public building, the energy consumption of the air conditioning system can reach 30% -50%.
At present, the technical directions for improving the cooling energy efficiency mainly include the following:
Advanced refrigeration techniques are utilized. Currently, air source heat pump, ground source heat pump, absorption refrigeration and other technologies have become mainstream. The technology has the characteristics of high efficiency, environmental protection, energy conservation and the like, and can obviously improve the energy efficiency of cooling.
Intelligent control technology is utilized. The intelligent control technology can enable the operation of the system to be more efficient and energy-saving by accurately controlling the cooling system. At present, intelligent control systems based on artificial intelligence and the internet of things technology have been widely used.
Adopts energy-saving materials and energy-saving technology. At present, some novel energy-saving materials and energy-saving technologies have been applied to the building field, such as heat insulation materials, high-efficiency heat exchangers, variable frequency control of fans and water pumps, and the like.
And (5) carrying out energy efficiency evaluation and optimization of the cooling system. By evaluating and optimizing the energy efficiency of the cooling system, the energy consumption bottleneck in the system can be found and solved, so that the energy efficiency of cooling is improved.
In short, with the continuous development and application of the technology, the energy efficiency optimization of the cooling side has become an important research direction in the field of heating and ventilation, and simultaneously, the technical support is provided for realizing the aims of energy conservation and emission reduction of the building.
The existing mature optimization control scheme for the cooling side in the industry comprises an optimization algorithm based on modeling and convex optimization and a correlation rule data mining algorithm based on historical data, wherein the convex optimization method requires modeling of physical parameters, nameplate information and historical data of each device, and is large in implementation engineering quantity; the association rule algorithm carries out discretization processing on the data, processes the data into a history working condition, energy efficiency and a control strategy, and finally uses the control strategy with highest confidence coefficient for searching the optimal energy efficiency under the closest history working condition as a core to carry out mining.
Disclosure of Invention
Aiming at the technical problems of high energy consumption, low energy efficiency, difficult optimization and the like of the cooling side, the invention provides an improved association rule cooling side energy efficiency optimization method based on similarity search.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
The improved association rule cooling side energy efficiency optimization method based on similarity search is characterized by comprising the following steps of:
s1, acquiring historical data of a cooling side of a certain water chiller, performing data cleaning treatment, and constructing a database; the historical data comprises cooling side heat, freezing side cold energy, outdoor temperature and outdoor wet bulb temperature;
S2, acquiring real-time data of a cooling side of a certain water chiller, wherein the real-time data comprise cooling side heat, freezing side cold quantity, outdoor temperature and outdoor wet bulb temperature at the current moment;
S3, searching a searching strategy under the similar historical working conditions, the corresponding energy consumption ratio of the similar working conditions and the corresponding energy consumption ratio of the similar working conditions according to the collected real-time data and the historical data, namely setting control points in the historical working conditions similar to the current working conditions, wherein the control points comprise cooling water pump temperature difference control and/or tower outlet water temperature control.
Further, searching for similar history conditions specifically includes:
s3.1, setting a threshold value;
S3.2, if the phase difference between the current working condition and the historical working condition is smaller than a set threshold value, the current working condition and the historical working condition are considered to be similar;
When W i={Q1i,Q2i,temp1i,temp2i is represented by the formula W i which is an ith working condition set, Q 1i which represents cooling side heat under the historical ith working condition, Q 2i which represents refrigerating side cold under the historical ith working condition, temp 1i which represents outdoor wet bulb temperature under the ith working condition, temp 2i which represents outdoor temperature under the ith working condition;
If the mth working condition set W m={Q1m,Q2m,temp1m,temp2m exists, the following conditions are satisfied:
abs(Q1i-Qim)<Q1delta_min,abs(Q2i-Q2m)<Q2delta_min,
abs(temp1i-temp1m)<temp1delta_min,abs(temp2i-temp2m)<temp2delta_min,
Wherein abs is absolute value, and Q 1delta_min,Q2delta_min temp1delta_min temp2delta_min is distance threshold;
Then the ith set of operating conditions W i is considered similar to the mth set of operating conditions W m;
Forming a similar working condition set from all working condition sets similar to the ith working condition set W i, wherein Q 1 represents cooling side heat under the current working condition, Q 2 represents refrigerating side cold under the current working condition, temp 1 represents outdoor wet bulb temperature under the current working condition, temp 2 represents outdoor temperature under the current working condition;
s3.3, checking the support degree of similar working conditions:
For each similar working condition set, calculating the similar working condition set, and obtaining the number of the similar working condition sets corresponding to each corresponding similar working condition set, namely, for all similar working condition sets formed by the working condition sets similar to the ith working condition set W i The method meets the following conditions:
wherein W i is the number of similar working condition sets of W i;
when W is more than or equal to w_min, the corresponding working condition set W is considered to appear at least w_min times in the historical data, and the working condition set W is considered to be not occasionally appearing; or alternatively
When the data volume is abundant, judging that w i/N is more than minSup, wherein minSup is the minimum support degree, and N is the sample data volume, namely replacing the original discrete calculation of the association rule by using similarity calculation;
S3.4 similar condition-COP associated mining:
At the similar working condition set Selecting the quantity of refrigeration under the searched working condition/the quantity of electricity consumption COP i under the searched working condition to be larger than the current quantity of refrigeration/the current quantity of electricity consumption COP 1, and counting the quantity of COP approaching to the quantity of the COP in the corresponding similar working condition;
Similarly, setting a threshold for the COP, considering that the COP is dissimilar when the COP exceeds a certain threshold, and finally obtaining the quantity of the electricity consumption COP which is larger than the current electricity consumption COP 1 under the corresponding similar working condition:
W-Ci={Q1i,Q2i,temp1i,temp2i,COPi}
wherein W-C i is a parameter set under the corresponding working condition-COP;
s3.5 similar condition-COP-strategy association mining:
W-Ci-Si={Q1i,Q2i,temp1i,temp2i,COPi,Si}
Wherein W-C i-Si is a parameter set of a use strategy under a corresponding working condition-COP, and S i is a corresponding strategy;
when the occurrence number is larger than a certain threshold value and the strategy under the working condition with the highest COP is multiplexed, selecting a set with higher COP and highest control parameter confidence as the selected rule which is mined in the history database under the working condition which is quite close to the current working condition:
R={sup1,up2,…,upn}
wherein Sup i=w-c-si/w-ci, sup is the support, w-c-s: corresponding to the working conditions-corresponding to the number under cop, w-c: the number of corresponding cops under the corresponding working conditions.
Compared with the prior art, the invention has the beneficial effects that:
1) And compared with the traditional association rule method, the method can search the matched working conditions more comprehensively.
2) And the control parameters with the highest energy efficiency ratio are found to control through the similarity threshold division and the association rule, so that the control strategy search based on historical data is realized, the project energy efficiency optimization is realized, and the running cost is reduced.
3) A random module is added in the practical application, and more reasonable data sets can be automatically generated for mining within an allowable range.
Drawings
FIG. 1 is a block diagram of the operation of the system of the present invention;
FIG. 2 is a flow chart of the improved association rule cooling side energy efficiency optimization method based on similarity search of the present invention.
Detailed Description
The invention is further defined by the following examples in conjunction with the accompanying drawings, but should not be construed to limit the scope of the invention.
The cooling side energy efficiency optimization method based on data driving comprises the following modules:
1) Historical data cleaning module: the module is responsible for generating and cleaning redundant historical data, and the correlation rule algorithm based on similarity search needs the relatively clean and highly reliable historical data, and if dirty data exist in the historical data, the actual implementation is influenced.
2) And a data self-updating module: because the system is continuously operated, after a large amount of historical data is acquired, new data is continuously imported into the database, and along with the continuous accumulation of the data, various working conditions and corresponding control parameters under various working conditions exist in the database theoretically, wherein the control parameters comprise: the number of the cooling towers is opened, the water temperature of the cooling towers is discharged, the number of the cooling water pumps is opened, and the temperature difference of the cooling water pumps is reduced.
3) The algorithm module: the association rule search algorithm based on the similarity is provided for solving the problem that data are scattered and accuracy is reduced when association rules are mined, and for each piece of data, the algorithm replaces common discretization processing by a similarity calculation method and then searches strategies under similar working conditions, energy consumption ratios corresponding to the similar working conditions and energy consumption ratios corresponding to the similar working conditions.
4) And (3) a random module: in order to improve the diversity of the historical data, a certain randomness is introduced in the strategy, and the situation that the expanded data possibly exists is specifically realized as follows: if similar working condition data cannot be searched currently, or the searched working condition data does not meet the filtering condition of the algorithm module, random outward exploration is considered to be performed,
If the historical working conditions do not meet the requirements, the random module can increase the number of the cooling towers or adjust the temperature difference of the cooling pump based on the current working conditions.
The function of the random module is: under the condition that project safety is not affected, the random module can expand the historical data set, and the insufficient diversity of the historical working conditions is prevented.
The algorithm module comprises the following modules:
Historical similar working condition searching module: and searching the same historical working conditions in all the historical data through the input working conditions, wherein the searching method is to set a threshold value, and if the difference between the current working conditions and the historical working conditions is smaller than a set value, the current working conditions and the historical working conditions are considered to be similar. The specific calculation formula is as follows:
for a certain working condition set
Wi={Q1i,Q2i,temp1i,temp2i}
If there is a working condition set
Wm={Q1m,Q2m,temp1m,temp2m}
So that
abs(Q1i-Q1m)<Q1delta_min
And abs (Q) 2i-Q2m)<Q2delta_min
And abs (temp) 1i-temp1m)<temp1delta_min
And abs (temp) 2i-temp2m)<temp1delta_min
Then the set of conditions W i is considered similar to W m and all sets of conditions similar to set of conditions W i form a set of similar conditions.
Wherein, Q 1,Q2,temp1,temp2 is respectively: cooling side heat, freezing side cold, outdoor temperature, outdoor wet bulb temperature. The distance is an adjustable parameter, if the distance is set to be large, more similar working conditions can be searched, but the confidence level is reduced, meanwhile, the time consumption for searching can be increased, and if the distance is set to be too small, the proper working conditions cannot be searched, so that the proper parameters are set to be particularly important.
And (5) checking the support degree of similar working conditions: for each similar working condition set, calculating the similar working condition set, and obtaining the number of the similar working condition sets corresponding to each corresponding similar working condition set, namely, the similar working condition set for the working condition iThe method comprises the following steps:
Wherein W 1 is the number of similar working condition sets of W 1;
When W is more than or equal to w_min, the corresponding working condition set W is considered to appear at least w_min times in the historical data, if the working condition set W is considered to be not occasionally appear, when the data volume is abundant, the working condition set W can be changed into a judgment that W i/N is more than minS, wherein minS is the minimum support degree, N is the sample data volume, and the similarity calculation is utilized to replace the original discrete calculation of the association rule.
Similar operating condition-COP associated mining: and selecting COP larger than the current value in the screened similar working conditions, counting the number of COP approaching to the COP in the corresponding similar working conditions, setting a threshold value for the COP, considering that the COP is dissimilar when the COP exceeds a certain threshold value, and finally acquiring the number of COP larger than the current COP in the corresponding similar working conditions.
W-Ci={Q1i,Q2i,temp1i,temp2i,COPi}
Wherein W-C i is the parameter set under the corresponding working condition-COP.
Similar condition-COP-policy association mining: in the screened data, searching the number of working conditions which are all used and are close to the current control parameters, and the more the number is, the more reliable the strategy is considered.
Because the control parameters are continuous variables, the similarity calculation is carried out by setting a threshold value according to experience, the threshold value can be set according to experience, fluctuation of data is allowed to occur in a certain range, and the more the quantity of the data occurs, the more the situation that the expected COP can be achieved by using the given strategy under the working condition is considered.
W-C-Si={Q1i,Q2i,temp1i,temp2i,COPi,Si}
Wherein W-C-S i is the parameter set of the usage strategy under the corresponding working condition-COP.
And finally, selecting strategies with the quantity larger than a certain threshold value and under the working condition of highest COP in the (4) to multiplex in the similar working condition-COP-strategy association mining, and increasing the data quantity.
The strategy corresponds to the strategy with the maximum number of working conditions obtained in the step (4) compared with the working conditions obtained in the step (3), and the strategy is taken as a multiplexing strategy, namely the confidence in the association rule.
R={sup1,up2,…,upn}
Wherein sup i=w-c-si/-ci
That is, the algorithm will select the set in the history database that has a higher COP under conditions that are quite close to the current condition and that has the highest confidence level in the control parameters as the mined selected rule.
Example 1: optimized control of cooling side of water chiller in certain project
Firstly, acquiring cooling side data of a water chiller of a certain item, cleaning historical data, storing the cleaned historical data into an algorithm database, and then storing new data into the algorithm database at regular time according to a format, thereby completing the construction of an algorithm search library. And then taking the cooling side heat quantity, the freezing side cold quantity, the outdoor temperature and the outdoor wet bulb temperature as search parameters for evaluating whether working conditions are similar or not, then transmitting the parameters into an algorithm module for similarity search, then calculating data with COP performance superior to that of the current performance in the similar working conditions, and finally searching a control strategy with highest confidence in the searched working conditions-COP set, and then multiplexing the control strategy. Through simulation, the energy is expected to be saved by about 5% under the actual working condition.
Claims (1)
1. The improved association rule cooling side energy efficiency optimization method based on similarity search is characterized by comprising the following steps of:
s1, acquiring historical data of a cooling side of a certain water chiller, performing data cleaning treatment, and constructing a database; the historical data comprises cooling side heat, freezing side cold energy, outdoor temperature and outdoor wet bulb temperature;
S2, acquiring real-time data of a cooling side of a certain water chiller, wherein the real-time data comprise cooling side heat, freezing side cold quantity, outdoor temperature and outdoor wet bulb temperature at the current moment;
S3, searching a searching strategy under the similar historical working conditions, the corresponding energy consumption ratio of the similar working conditions and the corresponding energy consumption ratio of the similar working conditions according to the collected real-time data and the historical data, namely setting control points in the historical working conditions similar to the current working conditions, wherein the control points comprise cooling water pump temperature difference control and/or tower outlet water temperature control;
the searching history similar working conditions specifically comprise:
s3.1, setting a threshold value;
S3.2, if the phase difference between the current working condition and the historical working condition is smaller than a set threshold value, the current working condition and the historical working condition are considered to be similar;
When W i={Q1i,Q2i,temp1i,temp2i is represented by the formula W i, Q 1i represents the cooling side heat quantity under the i-th working condition of history, Q 2i represents the freezing side cold quantity under the i-th working condition of history, temp 1i represents the outdoor wet bulb temperature under the i-th working condition, temp 2i represents the outdoor temperature under the i-th working condition;
If the mth working condition set W m={Q1m,Q2m,temp1m,temp2m exists, the following conditions are satisfied:
abs(Q1i-Qim)<Q1delta_min,abs(Q2i-Q2m)<Q2delta_min,
abs(temp1i-temp1m)<temp1delta_min,abs(temp2i-temp2m)<temp2delta_min,
Wherein abs is absolute value, and Q 1delta_min,Q2delta_min temp1delta_min temp2delta_min is distance threshold;
Then the ith set of operating conditions W i is considered similar to the mth set of operating conditions W m;
Forming a similar working condition set from all working condition sets similar to the ith working condition set W i, wherein Q 1 represents cooling side heat under the current working condition, Q 2 represents refrigerating side cold under the current working condition, temp 1 represents outdoor wet bulb temperature under the current working condition, temp 2 represents outdoor temperature under the current working condition;
s3.3, checking the support degree of similar working conditions:
For each similar working condition set, calculating the similar working condition set, and obtaining the number of the similar working condition sets corresponding to each corresponding similar working condition set, namely, for all similar working condition sets formed by the working condition sets similar to the ith working condition set W i The method meets the following conditions:
wherein W i is the number of similar working condition sets of W i;
when W is more than or equal to w_min, the corresponding working condition set W is considered to appear at least w_min times in the historical data, and the working condition set W is considered to be not occasionally appearing; or alternatively
When the data volume is abundant, judging that w i/N is more than minSup, wherein minSup is the minimum support degree, and N is the sample data volume, namely replacing the original discrete calculation of the association rule by using similarity calculation;
S3.4 similar condition-COP associated mining:
At the similar working condition set Selecting the quantity of refrigeration under the searched working condition/the quantity of electricity consumption COP i under the searched working condition to be larger than the current quantity of refrigeration/the current quantity of electricity consumption COP 1, and counting the quantity of COP approaching to the quantity of the COP in the corresponding similar working condition;
Similarly, setting a threshold for the COP, considering that the COP is dissimilar when the COP exceeds a certain threshold, and finally obtaining the quantity of the electricity consumption COP which is larger than the current electricity consumption COP 1 under the corresponding similar working condition:
W-Ci={Q1i,Q2i,temp1i,temp2i,COPi}
wherein W-C i is a parameter set under the corresponding working condition-COP;
s3.5 similar condition-COP-strategy association mining:
W-Ci-Si={Q1i,Q2i,temp1i,temp2i,COPi,Si}
Wherein W-C i-Si is a parameter set of a use strategy under a corresponding working condition-COP, and S i is a corresponding strategy;
when the occurrence number is larger than a certain threshold value and the strategy under the working condition with the highest COP is multiplexed, selecting a set with higher COP and highest control parameter confidence as the selected rule which is mined in the history database under the working condition which is quite close to the current working condition:
R={sup1,sup2,…,supn}
Wherein Sup i=w-c-si/w-ci, sup is the support, w-c-s: corresponding to the working conditions-corresponding to the number under cop, w-c:
The number of corresponding cops under the corresponding working conditions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310829094.2A CN116907139B (en) | 2023-07-07 | 2023-07-07 | Improved association rule cooling side energy efficiency optimization method based on similarity search |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310829094.2A CN116907139B (en) | 2023-07-07 | 2023-07-07 | Improved association rule cooling side energy efficiency optimization method based on similarity search |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116907139A CN116907139A (en) | 2023-10-20 |
CN116907139B true CN116907139B (en) | 2024-05-14 |
Family
ID=88352401
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310829094.2A Active CN116907139B (en) | 2023-07-07 | 2023-07-07 | Improved association rule cooling side energy efficiency optimization method based on similarity search |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116907139B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101477375A (en) * | 2009-01-05 | 2009-07-08 | 东南大学 | Sensor data verification method based on matrix singular values association rules mining |
CN101667013A (en) * | 2009-09-04 | 2010-03-10 | 天津大学 | Control method of optimized running of combined cooling and power distributed energy supply system of micro gas turbine |
CN110506186A (en) * | 2018-03-20 | 2019-11-26 | Lg电子株式会社 | The refrigerator and Cloud Server of the reason of for diagnosing abnormality |
CN111723456A (en) * | 2020-05-08 | 2020-09-29 | 华南理工大学 | Central air-conditioning system energy efficiency optimization method based on NSGA-II algorithm |
CN115808001A (en) * | 2021-09-13 | 2023-03-17 | 深圳达实智能股份有限公司 | Method for identifying abnormal operation and regulation of refrigeration station of central air conditioning system and electronic equipment |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7840515B2 (en) * | 2007-02-16 | 2010-11-23 | Panasonic Corporation | System architecture and process for automating intelligent surveillance center operations |
-
2023
- 2023-07-07 CN CN202310829094.2A patent/CN116907139B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101477375A (en) * | 2009-01-05 | 2009-07-08 | 东南大学 | Sensor data verification method based on matrix singular values association rules mining |
CN101667013A (en) * | 2009-09-04 | 2010-03-10 | 天津大学 | Control method of optimized running of combined cooling and power distributed energy supply system of micro gas turbine |
CN110506186A (en) * | 2018-03-20 | 2019-11-26 | Lg电子株式会社 | The refrigerator and Cloud Server of the reason of for diagnosing abnormality |
CN111723456A (en) * | 2020-05-08 | 2020-09-29 | 华南理工大学 | Central air-conditioning system energy efficiency optimization method based on NSGA-II algorithm |
CN115808001A (en) * | 2021-09-13 | 2023-03-17 | 深圳达实智能股份有限公司 | Method for identifying abnormal operation and regulation of refrigeration station of central air conditioning system and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN116907139A (en) | 2023-10-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105571063B (en) | A kind of shallow layer ground-temperature energy energy management system and its implementation | |
CN111723456A (en) | Central air-conditioning system energy efficiency optimization method based on NSGA-II algorithm | |
CN110260470B (en) | Central air conditioner parallel connection cold machine load optimization distribution method based on swarm intelligence architecture | |
CN103020481B (en) | A kind of method based on energy-conservation determination air source heat pump floor heating optimal operating condition | |
CN108990383A (en) | A kind of data center's air-conditioning system forecast Control Algorithm | |
CN115493256B (en) | Intelligent optimizing method for energy-saving operation of central refrigerating system | |
Zhou et al. | An operational parameter optimization method based on association rules mining for chiller plant | |
CN110567101A (en) | Water chiller high-energy-efficiency control method based on support vector machine model | |
CN116384700A (en) | Energy efficiency optimization method for central air conditioning system based on data mining | |
CN102609766A (en) | Method for intelligently forecasting wind speed in wind power station | |
CN110895029A (en) | Building load prediction method based on temperature of chilled water | |
CN116680982A (en) | Method and system for determining optimal capacity of ground source-air source heat pump composite system unit | |
CN201944984U (en) | Energy-saving optimization control system of refrigerator room | |
CN116907139B (en) | Improved association rule cooling side energy efficiency optimization method based on similarity search | |
CN105299846A (en) | Machine room group control device and method based on overall relevance optimization | |
CN109084403B (en) | Method for obtaining static control strategy of water chilling unit based on air conditioner load time sequence distribution | |
CN111473480A (en) | Central air conditioner energy-saving control method based on decision tree classification | |
CN116562111A (en) | Data center energy saving method, device, system and storage medium | |
CN102679649A (en) | Energy conservation control device and energy conservation control method of refrigerating system | |
CN115903712A (en) | Energy-saving optimization method and optimization control system suitable for industrial refrigeration system | |
CN116227342A (en) | Regional cooling system cold station optimization algorithm based on simulation and cold load prediction model | |
CN112257779A (en) | Method for acquiring self-learning working condition parameters of central air conditioner | |
CN107062690A (en) | A kind of shallow layer ground-temperature energy energy management system | |
Liang et al. | Research on Key Technologies for Green Transformation of Existing Residential Buildings in Dense Urban Areas | |
CN103528294A (en) | Energy efficiency processing method and system for refrigerating 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |