CN107065520B - A kind of air-cooler parameter configuration optimization method - Google Patents

A kind of air-cooler parameter configuration optimization method Download PDF

Info

Publication number
CN107065520B
CN107065520B CN201611131651.XA CN201611131651A CN107065520B CN 107065520 B CN107065520 B CN 107065520B CN 201611131651 A CN201611131651 A CN 201611131651A CN 107065520 B CN107065520 B CN 107065520B
Authority
CN
China
Prior art keywords
air
cooler
parameter
learner
parameter configuration
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
Application number
CN201611131651.XA
Other languages
Chinese (zh)
Other versions
CN107065520A (en
Inventor
李俊青
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Liaocheng University
Original Assignee
Liaocheng University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Liaocheng University filed Critical Liaocheng University
Priority to CN201611131651.XA priority Critical patent/CN107065520B/en
Publication of CN107065520A publication Critical patent/CN107065520A/en
Application granted granted Critical
Publication of CN107065520B publication Critical patent/CN107065520B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Automation & Control Theory (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention discloses a kind of air-cooler parameter configuration optimization methods, the specific steps are as follows: obtains air-cooler energy consumption, parameter and cooling ability and the needing adjusting parameter of the task in real time；Determine the target and constraint condition of parameter adjustment；Using the teaching optimization method adjusting parameter plan of establishment；The air-cooler parameter setting scheme is issued to each air-cooler.The invention proposes a kind of teaching optimization algorithms of air-cooler parameter configuration optimization problem, in conjunction with problem characteristic, algorithm uses a kind of novel coding and decoding mechanism based on integer, algorithm is divided into teaching and two stages of study, teaching phase can improve the quality of learning process, to improve development ability；Design the good study stage then reinforce between learning process.

Description

A kind of air-cooler parameter configuration optimization method
Technical field
The present invention relates to air-cooler parameter optimization technique field, specifically a kind of air-cooler parameter configuration optimization method.
Background technique
In recent years, Heating,Ventilating and Air Conditioning (HVAC) system is largely integrated into intelligent building.Multizone cooling fan system is then The core component of heating ventilation air-conditioning system.The system includes the distributed cooling device of multiple and different performances, for cooling for mentioning Energy.Heating ventilation air-conditioning system plays a significant role in terms of adjusting room temperature, and for people provide one it is comfortable and safe Working environment.However, heating ventilation air-conditioning system generally consumes a large amount of energy, how to reduce its energy consumption is always a problem.
In recent years, some heuristic and meta-heuristic algorithm has been used for solving the load optimized problem of air-cooler.Compare allusion quotation The algorithm of type includes branch and bound method, Lagrange relaxation method, genetic algorithm etc..Lagrange and branch and bound method The disadvantage is that inefficient and convergence capabilities are limited, thus cannot be used to solve the problems, such as extensive and complicated OCL.With inspiration The it is proposed and extensive use of formula method especially genetic algorithm, some intelligent optimization algorithms simultaneously propose extensively and optimize for OCL Problem proposes one kind based on binary encoding scheme, however, the major defect based on binary coding is to need to grow very much Coding fine-grained problem space could be described, thus need very high memory space and computing capability.A kind of population is excellent Change algorithm, is encoded using floating number representation method, which greatly reduces memory space needs, the disadvantage is that algorithm itself It is easy to restrain, thus is unable to reach optimal.A kind of drosophila optimization algorithm is for solving OCL problem.Other are asked for solving such The algorithm of topic further includes simulated annealing, evolution strategy, gradient descent method, differential evolution algorithm etc..
Summary of the invention
The purpose of the present invention is to provide a kind of air-cooler parameter configuration optimization methods greatly improved the efficiency, to solve The problems mentioned above in the background art.
To achieve the above object, the invention provides the following technical scheme:
A kind of air-cooler parameter configuration optimization method, the specific steps are as follows:
S1: air-cooler energy consumption, parameter and cooling ability and the needing adjusting parameter of the task are obtained in real time；
S2: the target and constraint condition of parameter adjustment are determined；
S3: using the teaching optimization method adjusting parameter plan of establishment；
S4: the air-cooler parameter setting scheme is issued to each air-cooler.
As the further technical solution of the present invention: air-cooler energy consumption, parameter and cooling ability and need in the S1 The wanting adjusting parameter of the task includes: that air-cooler is N number of, some air-cooler i, i=1,2 ..., N, decision variable PLRiIt indicates i-th The index of the unlatching ratio of air-cooler, that is, fractional load rate, then i-th of air-cooler energy consumption is Pi；The constraint condition of problem is, often Cold blast rate provided by a air-coolerSystem requirements CL need to be met, whereinIndicate i-th of air-cooler Semen donors, CL are overall cooling capacity needed for system.
As the further technical solution of the present invention: the target of the air-cooler parameter optimization in the S2 are as follows:
Pi=ai+biPLRi+ciPLRi 2+diPLRi 3(formula 1)；
Wherein, ai, bi, ciAnd diThe parameter of air-cooler is respectively indicated, N indicates the quantity of air-cooler, PiThat is i-th of cold wind The energy consumption of machine,Indicate that the semen donors of i-th of air-cooler, CL are overall cooling capacity needed for system；
Thus, two targets that system is optimized are as follows:
Minf=α f1+βf2(formula 4)
Wherein α and β indicates the weight coefficient of two targets.
As a further solution of the present invention: the S3 includes the following steps:
(1) a learner is generated according to air-cooler parameter configuration optimization problem, and learner group is added, recycled random raw At PnLearner group is added in a initial learner；
(2) target value of each learner is calculated, and initial population is ranked up, is selected best as teacher；
(3) it calculates current solution and concentrates individual average value and mean difference；
(4) setting learner group stopping criterion for iteration K, enables i=0；
(5) start teaching phase, i.e. stage of the learner to teacher learning；
(6) start the study stage, i.e. stage for learning from each other of learner；
(7) renewal learning person group；
(8) i=i+1 is enabled, judges whether i >=K condition meets, if it is satisfied, then exiting algorithm, exports best parameter configuration Scheme；Otherwise, step (5) are transferred to.
As a further solution of the present invention: the step (1) is achieved in that
According to air-cooler parameter configuration optimization problem, a learner is randomly generated, solution is added and concentrates, circulation generates Pn Learner constitutes initial learner group.
As a further solution of the present invention: the coding strategy in the step (2) is as follows:
Each air-cooler indicates that the length of string integer depends on the demand of system with a string integer.
As a further solution of the present invention: the teaching phase strategy in the step (5) is as follows:
A, mean difference M is calculatedt,j: firstly, sum of each learner on each element value of each string integer is calculated, It is secondary, calculate separately the average value of each element corresponding position；
B, D is calculatedt,j: firstly, selecting currently to solve the best individual concentrated as teacher, secondly, generating two random numbers；
C, new learner is generated；
D, original individual is updated.
As further scheme of the invention: the study stage policy in the step (6) is as follows:
E, two individuals are randomly choosedWith
F, a new individual is generated
G, original individual is updated.
Compared with prior art, the beneficial effects of the present invention are:
The invention proposes a kind of teaching optimization algorithms of air-cooler parameter configuration optimization problem to calculate in conjunction with problem characteristic Method uses a kind of novel coding and decoding mechanism based on integer, and algorithm is divided into teaching and two stages of study, rank of imparting knowledge to students Section can improve the quality of learning process, to improve development ability；It designs between the good study stage then reinforces Learning process.
Detailed description of the invention
Fig. 1 is the step block diagram of air-cooler parameter configuration optimization method of the present invention；
Fig. 2 is the step block diagram that air-cooler parameter configuration scheme is generated using teaching optimization method in the method for the present invention；
Fig. 3 is the air-cooler schematic diagram in the method for the present invention.
Fig. 4 is one of the comparison figure preferably solved that emulation experiment obtains in the present invention.
Fig. 5 is the two of the comparison figure preferably solved that emulation experiment obtains in the present invention.
Fig. 6 is the three of the comparison figure preferably solved that emulation experiment obtains in the present invention.
Specific embodiment
The technical solution of the patent is explained in further detail With reference to embodiment.
Please refer to Fig. 1-3, a kind of air-cooler parameter configuration optimization method, the specific steps are as follows:
S1: air-cooler energy consumption, parameter and cooling ability and the needing adjusting parameter of the task are obtained in real time；
S2: the target and constraint condition of parameter adjustment are determined；
S3: using the teaching optimization method adjusting parameter plan of establishment；
S4: the air-cooler parameter setting scheme is issued to each air-cooler.
The description of air-cooler parameter configuration problem: multizone cooling fan system generally comprises multiple air-coolers, as shown in Figure 3.
It include 3 cooling devices in figure.
One, air-cooler energy consumption, parameter and the cooling ability in the S1 and to need the task of adjusting parameter include: cold wind Machine is N number of, some air-cooler i, i=1,2 ..., N, decision variable PLRiIndicate the index i.e. portion of the unlatching ratio of i-th of air-cooler Divide load factor, then i-th of air-cooler energy consumption is Pi；The constraint condition of problem is cold blast rate provided by each air-coolerSystem requirements CL need to be met, whereinIndicate that the semen donors of i-th of air-cooler, CL are total needed for system Body cooling capacity.
Two, the target of the air-cooler parameter optimization in the S2 are as follows:
Pi=ai+biPLRi+ciPLRi 2+diPLRi 3(formula 1)；
Wherein, ai, bi, ciAnd diThe parameter of air-cooler is respectively indicated, N indicates the quantity of air-cooler, PiThat is i-th of cold wind The energy consumption of machine,Indicate that the semen donors of i-th of air-cooler, CL are overall cooling capacity needed for system；
Thus, two targets that system is optimized are as follows:
Minf=α f1+βf2(formula 4)
Wherein α and β indicates the weight coefficient of two targets.
Three, the S3 includes the following steps:
(1) a learner is generated according to air-cooler parameter configuration optimization problem, and learner group is added, recycled random raw At PnLearner group is added in a initial learner；
(2) target value of each learner is calculated, and initial population is ranked up, is selected best as teacher；
(3) it calculates current solution and concentrates individual average value and mean difference；
(4) setting learner group stopping criterion for iteration K, enables i=0；
(5) start teaching phase, i.e. stage of the learner to teacher learning；
(6) start the study stage, i.e. stage for learning from each other of learner；
(7) renewal learning person group；
(8) i=i+1 is enabled, judges whether i >=K condition meets, if it is satisfied, then exiting algorithm, exports best parameter configuration Scheme；Otherwise, step (5) are transferred to.
It mainly include teaching and two stages of study using the teaching optimization method adjusting parameter plan of establishment.What algorithm was used Variable and subscript are as follows: noteI-th of learner in (i=1,2 ..., m) expression system；Remember Mt,jIndicate learner in some mesh Average value on scale value；NoteIndicate the best learner in group；NoteIndicate j-th of target value of teacher；Remember rtTable Show random number of the value between [0,1]；Remember TFTeaching dynamics parameter is indicated, between [1,2] of general value；Remember Dt,jFor The difference degree of teacher；Remember Mt,jIndicate mean difference.
Algorithm mainly includes teaching phase study stage two parts.
Teaching phase specific steps are as follows: calculating difference first:Secondly a new study is generated PersonIf last new learner better than pervious, replaces it.
Study stage specific steps are as follows: randomly select two learners firstWithIfIt is better thanThen executeOtherwise, it executesIf new learner better than pervious, replaces it.
1, the step (1) is achieved in that
According to air-cooler parameter configuration optimization problem, a learner is randomly generated, solution is added and concentrates, circulation generates Pn Learner constitutes initial learner group.
2, the coding strategy in the step (2) is as follows:
Binary coding and real coding are two kinds of common encoding schemes, however, both schemes respectively have advantage and disadvantage.Two Code storage space requirement needed for scale coding is big, thus it is longer to calculate the time.Then search space is larger for real coding, restrains energy Power is insufficient.Based on this, we devise a kind of novel integer coding scheme, are described in detail below:
In given encoding scheme, each air-cooler is indicated with a string integer, and the length of string integer is depending on being The demand of system, i.e., the search precision that longer string integer indicates is higher, thus is also required to the longer calculating time, shorter integer String can quickly navigate to required approximate location, but be unable to reach higher search precision.For example, giving a string integer number Group { (8,7,5), (7,8,6), (6,7,3), (7,2,1), (8,3,4), (9,0,1) }, then first string integer (8,7,5) indicates The PLR value of first air-cooler, i.e., 0.875, the PLR value of second (7,8,6) expression, second air-cooler is 0.786, with this Analogize.
The advantages of above-mentioned coding has: (1) coding is simple and is easily achieved；(2) length of above-mentioned string integer is with iteration Constantly changed, at algorithm evolution initial stage, smaller value is arranged in the length of string integer, can quickly navigate to required search in this way Space, in the algorithm evolution middle and later periods, the larger value is arranged in the length of string integer, calculation search precision can be improved in this way, and then search Rope is to optimal value；(3) different integer string length can be set for different air-coolers, and then difference is set for different air-coolers Searching intensity.
3, the teaching phase strategy in the step (5) is as follows:
A, mean difference M is calculatedt,j: firstly, sum of each learner on each element value of each string integer is calculated, It is secondary, calculate separately the average value of each element corresponding position；For example, given disaggregation (8,7,5), (7,5,6), (6,9,3), (8, 2,1), (8,5,4), (9,3,1) }, { (9,7,5), (6,8,6), (7,7,3), (5,2,1), (8,2,4), (7,0,1) }, { (6 7,5), (7,4,6), (7,7,3), (9,2,1), (5,3,4), (9,7,1) }, then the first step obtain 23,21,15,20,17,18, 20,23,9,22,6,3,21,10,12,25,10,3 }, second step obtain 7.67,7.00,5.00,6.67,5.67,6.00, 6.67,7.67,3.00,7.33,2.00,1.00,7.00,3.33,4.00,8.33,3.33,1.00 }.
B, D is calculatedt,j: firstly, selecting currently to solve the best individual concentrated as teacher, secondly, generating two random numbers； For example, given disaggregation s1={ (8,7,5), (7,5,6), (6,9,3), (8,2,1), (8,5,4), (9,3,1) }, enable two it is random Number rt=0.3 and TF=1, then obtain Dt,2=0.1,0,0,0.1, -0.2,0, -0.2,0.4,0,0.2,0,0,0.3,0.5,0, 0.2, -0.1,0 } enables rt=0.8 and TF=2, then obtain Dt,3=0.27,0.00,0.00,0.27, -0.53,0.00, -0.53, 1.07,0.00,0.53,0.00,0.00,0.80,1.33,0.00,0.53, -0.27,0.00 }.
C, new learner is generated；
Based on step B, then newly generated individual
D, original individual is updated.
4, the study stage policy in the step (6) is as follows:
E, two individuals are randomly choosedWith
F, a new individual is generated
For example, disaggregation s1={ (8,7,5), (7,5,6), (6,9,3), (8,2,1), (8,5,4), (9,3,1) } s3= { (6,7,5), (7,4,6), (7,7,3), (9,2,1), (5,3,4), (9,7,1) } enables ri=0.5, it is assumed that s1 is better than s3, then has It is obtained after then rounding up
G, original individual is updated.
Four, result and analysis are tested:
1, emulation experiment parameter setting:
By verifying institute propositions algorithm performance, selection table 1 in listed by three kinds of cooling fan system data, programmed using C++ Language, realizes mentioned algorithm on IntelCorei73.4GHzPC machine, and with branch and bound method in the prior art, drawing Ge Lang relaxation method, genetic algorithm, particle swarm optimization algorithm, simulated annealing, evolution strategy, gradient descent method, difference Several algorithms such as evolution algorithm compare and analyze.
2 the simulation experiment results:
Table 3 gives for first example, the comparison result of several algorithm the data obtaineds.By table as it can be seen that being directed to six kinds Operation data, this algorithm obtain All Optimal Solutions, and the DCSA algorithm for being only second to this algorithm only obtain wherein three it is optimal Solution, comparison result demonstrate the superiority of this algorithm.In addition, this algorithm has found the optimal solution that other algorithms are not found, test The search capability of algorithm is demonstrate,proved.
Table 4 gives for second example, the comparison result of several algorithm the data obtaineds.By table as it can be seen that being directed to six kinds Operation data, this algorithm obtain 5 optimal solutions, and only to obtain two of them optimal for the DCSA algorithm for being only second to this algorithm Solution, comparison result demonstrate the superiority of this algorithm.In addition, this algorithm has found the optimal solution that other algorithms are not found, test The search capability of algorithm is demonstrate,proved.
Table 5 gives for third example, the comparison result of several algorithm the data obtaineds.By table as it can be seen that this algorithm phase Have than other algorithms and significantly improve, further demonstrates the superiority of algorithm.Table 6 then gives the solution of TLBO algorithm and preferably solves Ratio, further demonstrate the advance of algorithm.
Fig. 4-6 gives several algorithms and solves the comparison preferably solved that above-mentioned three kinds of examples obtain, as seen from the figure, this algorithm It is demonstrated by good performance.
Table 1: air-cooler data
The comparison of 2: the first examples of table
The comparison of 3: the second examples of table
Table 4: third example comparison result
The preferably solution ratio that table 5:TLBO algorithm obtains
The invention proposes a kind of teaching optimization algorithms of air-cooler parameter configuration optimization problem to calculate in conjunction with problem characteristic Method uses a kind of novel coding and decoding mechanism based on integer, and algorithm is divided into teaching and two stages of study, rank of imparting knowledge to students Section can improve the quality of learning process, to improve development ability；It designs between the good study stage then reinforces Learning process.
The preferred embodiment of the patent is described in detail above, but this patent is not limited to above-mentioned embodiment party Formula within the knowledge of one of ordinary skill in the art can also be under the premise of not departing from this patent objective Various changes can be made.

Claims (5)

1. a kind of air-cooler parameter configuration optimization method, which is characterized in that specific step is as follows:
S1: air-cooler energy consumption, parameter and cooling ability and the needing adjusting parameter of the task are obtained in real time；
Air-cooler energy consumption, parameter and cooling ability in the S1 and to need the task of adjusting parameter include: that air-cooler is N number of, Some air-cooler i, i=1,2 ..., N, decision variable PLRiIndicate the index i.e. fractional load of the unlatching ratio of i-th of air-cooler Rate, then i-th of air-cooler energy consumption is Pi；The constraint condition of problem is cold blast rate provided by each air-cooler System requirements CL need to be met, whereinIndicate that the semen donors of i-th of air-cooler, CL are overall cooling capacity needed for system；
S2: the target and constraint condition of parameter adjustment are determined；
The target of air-cooler parameter optimization in the S2 are as follows:
Pi=ai+biPLRi+ciPLRi 2+diPLRi 3(formula 1)；
Wherein, ai, bi, ciAnd diThe parameter of air-cooler is respectively indicated, N indicates the quantity of air-cooler, PiThat is i-th air-cooler Energy consumption,Indicate that the semen donors of i-th of air-cooler, CL are overall cooling capacity needed for system；
Thus, two targets that system is optimized are as follows:
Minf=α f1+βf2(formula 4)
Wherein α and β indicates the weight coefficient of two targets,
S3: using the teaching optimization method adjusting parameter plan of establishment；
The S3 includes the following steps:
(1) a learner is generated according to air-cooler parameter configuration optimization problem, and learner group is added, recycle random generation Pn Learner group is added in a initial learner；
(2) target value of each learner is calculated, and initial population is ranked up, is selected best as teacher；
(3) it calculates current solution and concentrates individual average value and mean difference；
(4) setting learner group stopping criterion for iteration K, enables i=0；
(5) start teaching phase, i.e. stage of the learner to teacher learning；
(6) start the study stage, i.e. stage for learning from each other of learner；
(7) renewal learning person group；
(8) i=i+1 is enabled, judges whether i >=K condition meets, if it is satisfied, then exiting algorithm, exports best parameter configuration side Case；Otherwise, step (5) are transferred to；
S4: the air-cooler parameter setting scheme is issued to each air-cooler.
2. air-cooler parameter configuration optimization method according to claim 1, which is characterized in that the step (1) is in this way It realizes:
According to air-cooler parameter configuration optimization problem, a learner is randomly generated, solution is added and concentrates, circulation generates Pn study Person constitutes initial learner group.
3. air-cooler parameter configuration optimization method according to claim 1, which is characterized in that the volume in the step (2) Code strategy is as follows:
Each air-cooler indicates that the length of string integer depends on the demand of system with a string integer.
4. air-cooler parameter configuration optimization method according to claim 1, which is characterized in that the religion in the step (5) It is as follows to learn stage policy:
A, mean difference M is calculatedt,j: firstly, sum of each learner on each element value of each string integer is calculated, secondly, point The average value of each element corresponding position is not calculated；
B, D is calculatedt,j: firstly, selecting currently to solve the best individual concentrated as teacher, secondly, generating two random numbers；
C, new learner is generated；
D, original individual is updated.
5. air-cooler parameter configuration optimization method according to claim 1, which is characterized in that in the step (6) It is as follows to practise stage policy:
E, two individuals are randomly choosedWith
F, a new individual is generated
G, original individual is updated.
CN201611131651.XA 2016-12-09 2016-12-09 A kind of air-cooler parameter configuration optimization method Active CN107065520B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611131651.XA CN107065520B (en) 2016-12-09 2016-12-09 A kind of air-cooler parameter configuration optimization method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611131651.XA CN107065520B (en) 2016-12-09 2016-12-09 A kind of air-cooler parameter configuration optimization method

Publications (2)

Publication Number Publication Date
CN107065520A CN107065520A (en) 2017-08-18
CN107065520B true CN107065520B (en) 2019-11-05

Family

ID=59618770

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611131651.XA Active CN107065520B (en) 2016-12-09 2016-12-09 A kind of air-cooler parameter configuration optimization method

Country Status (1)

Country Link
CN (1) CN107065520B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109974360B (en) * 2019-03-19 2020-10-27 东南大学 Fruit fly algorithm-based refrigeration system temperature optimization control method
CN111796512B (en) * 2019-04-08 2022-10-18 中移(苏州)软件技术有限公司 Method, device, equipment and storage medium for determining equipment scheduling parameters
CN113685895B (en) * 2021-09-09 2022-06-21 西安建筑科技大学 Heat exchange station parallel water pump optimization control method and system under distributed architecture

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1948873A (en) * 2006-11-09 2007-04-18 上海交通大学 Operating and optimization control method of differential pressure precooling fan
CN101334228A (en) * 2008-07-22 2008-12-31 烟台冰轮股份有限公司 Energy-saving -type quick freezing device for implementing energy saving by optimizing wind-guiding device
CN101923669A (en) * 2008-07-18 2010-12-22 史迪芬·凯斯 Intelligent adaptive design
JP5559414B1 (en) * 2013-11-18 2014-07-23 東京瓦斯株式会社 Energy system optimization method, energy system optimization device and program
CN104952001A (en) * 2015-07-02 2015-09-30 华侨大学 Method for performing power optimized scheduling on controllable loads comprising air conditioning loads
CN104977816A (en) * 2015-08-05 2015-10-14 哈尔滨工业大学 Soft measurement method for mechanical parameters of micropositioner and reticle stage of photoetching machine based on Compact Particle Swarm Optimization algorithm
CN105042800A (en) * 2015-09-01 2015-11-11 东南大学 Variable-frequency air conditioner load modeling and operation controlling method based on demand responses
CN105160069A (en) * 2015-08-05 2015-12-16 哈尔滨工业大学 Improved compact teaching optimization algorithm based mechanical parameter soft measurement method
CN105678429A (en) * 2016-02-19 2016-06-15 西南交通大学 Method for achieving multi-discipline multi-target optimization of air-conditioning system of electric car

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10175681B2 (en) * 2014-05-01 2019-01-08 Johnson Controls Technology Company High level central plant optimization

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1948873A (en) * 2006-11-09 2007-04-18 上海交通大学 Operating and optimization control method of differential pressure precooling fan
CN101923669A (en) * 2008-07-18 2010-12-22 史迪芬·凯斯 Intelligent adaptive design
CN101334228A (en) * 2008-07-22 2008-12-31 烟台冰轮股份有限公司 Energy-saving -type quick freezing device for implementing energy saving by optimizing wind-guiding device
JP5559414B1 (en) * 2013-11-18 2014-07-23 東京瓦斯株式会社 Energy system optimization method, energy system optimization device and program
CN104952001A (en) * 2015-07-02 2015-09-30 华侨大学 Method for performing power optimized scheduling on controllable loads comprising air conditioning loads
CN104977816A (en) * 2015-08-05 2015-10-14 哈尔滨工业大学 Soft measurement method for mechanical parameters of micropositioner and reticle stage of photoetching machine based on Compact Particle Swarm Optimization algorithm
CN105160069A (en) * 2015-08-05 2015-12-16 哈尔滨工业大学 Improved compact teaching optimization algorithm based mechanical parameter soft measurement method
CN105042800A (en) * 2015-09-01 2015-11-11 东南大学 Variable-frequency air conditioner load modeling and operation controlling method based on demand responses
CN105678429A (en) * 2016-02-19 2016-06-15 西南交通大学 Method for achieving multi-discipline multi-target optimization of air-conditioning system of electric car

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
multi-objective optimization of heat exchangers using a modified teaching-learning-based optimization algorithm;R. Venkata Rao；Vivek Patel;《Applied Mathematical Modelling》;20130630;第1147-1162页 *
直接供液CO2冷风机的设计优化;刘斌等;《制冷学报》;20120630;第33卷(第3期);第22-25页 *
车用空调冷凝器性能多目标优化方法;过海等;《浙江大学学报（工学版）》;20150131;第49卷(第1期);第142-149页 *

Also Published As

Publication number Publication date
CN107065520A (en) 2017-08-18

Similar Documents

Publication Publication Date Title
Delgarm et al. Multi-objective optimization of building energy performance and indoor thermal comfort: A new method using artificial bee colony (ABC)
Wei et al. Deep reinforcement learning for building HVAC control
Ahn et al. Application of deep Q-networks for model-free optimal control balancing between different HVAC systems
Duan et al. Solving chiller loading optimization problems using an improved teaching‐learning‐based optimization algorithm
Sha et al. Overview of computational intelligence for building energy system design
Luo et al. Optimal dispatch of air conditioner loads in southern China region by direct load control
Gacto et al. A multi-objective evolutionary algorithm for an effective tuning of fuzzy logic controllers in heating, ventilating and air conditioning systems
CN106647262A (en) Differential evolution method facing agile satellite multi-object task planning
CN107065520B (en) A kind of air-cooler parameter configuration optimization method
Lo et al. Economic dispatch of chiller plant by improved ripple bee swarm optimization algorithm for saving energy
CN106227043A (en) adaptive optimal control method
Ali et al. Optimized power control methodology using genetic algorithm
Heshmati et al. Measurement and analysis of urban infrastructure and its effects on urbanization in China
CN106845012A (en) A kind of blast furnace gas system model membership function based on multiple target Density Clustering determines method
CN107994574B (en) New energy consumption-oriented centralized temperature control load side demand response decision method
Wu et al. Intelligent optimization framework of near zero energy consumption building performance based on a hybrid machine learning algorithm
CN113191086A (en) Genetic algorithm-based electric heating heat load demand optimization method and system
Wen et al. Forecasting the annual household electricity consumption of Chinese residents using the DPSO-BP prediction model
CN105809315A (en) Method for automatically arranging electronic curriculum schedules of middle and primary schools
Zhang et al. Safe building hvac control via batch reinforcement learning
CN109492878A (en) A kind of evaluation method of super low energy consumption public building energy technical solution
CN106960101A (en) A kind of build-up tolerance optimization method based on mass loss and cost minimization
CN107590538A (en) A kind of dangerous source discrimination based on online Sequence Learning machine
Vergini et al. A critical overview of net zero energy buildings and fuzzy cognitive maps
CN112944599A (en) Multi-parameter coupling control method and device of air conditioning 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