CN108966448A - A kind of light dynamic regulation method based on adaptive fuzzy decision tree - Google Patents
A kind of light dynamic regulation method based on adaptive fuzzy decision tree Download PDFInfo
- Publication number
- CN108966448A CN108966448A CN201810544765.XA CN201810544765A CN108966448A CN 108966448 A CN108966448 A CN 108966448A CN 201810544765 A CN201810544765 A CN 201810544765A CN 108966448 A CN108966448 A CN 108966448A
- Authority
- CN
- China
- Prior art keywords
- value
- level
- fuzzy
- attribute
- illumination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000003066 decision tree Methods 0.000 title claims abstract description 27
- 230000033228 biological regulation Effects 0.000 title claims abstract description 19
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 16
- 238000005286 illumination Methods 0.000 claims abstract description 75
- 230000000153 supplemental effect Effects 0.000 claims abstract description 11
- 239000002245 particle Substances 0.000 claims description 49
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000003760 hair shine Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/105—Controlling the light source in response to determined parameters
-
- 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
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The present invention provides a kind of light dynamic regulation method based on adaptive fuzzy decision tree, including step 1, the acquisition of supplemental characteristic: according to the factor for influencing street lamp illumination, determine that vehicle flowrate, ambient light illumination, PM2.5 and time point are the parameter for influencing street lamp illumination, and above-mentioned parameter is divided into several parameter levels；The degree of membership of step 2, supplemental characteristic calculates: bringing vehicle flowrate, ambient light illumination, PM2.5 and the value at time point into subordinating degree function, calculates the degree of membership data of above-mentioned parameter；The foundation of fuzzy decision tree-model: step 3 establishes the fuzzy decision tree-model between vehicle flowrate, ambient light illumination, PM2.5 and time point and street lamp illumination respectively；Step 4 brings the degree of membership data of parameter current into the fuzzy decision tree-model of step 3 foundation, obtains the street lamp level of illumination information for meeting current lighting requirement.
Description
Technical field
The light dynamic regulation method based on adaptive fuzzy decision tree that the present invention relates to a kind of, belongs to street lamp control system
Field.
Background technique
For the serious problem of night street lamp energy consumption, the main energy-saving control method of street lamp control system has time control, light at present
Control adjusts street lamp output power according to vehicle flowrate size.But these control methods do not comprehensively consider road traffic flow
Amount and the factors such as ambient condition design a kind of comprehensively consider various factors to predict the signal light control side of street lamp level of illumination thus
Method guarantees to reduce system energy consumption while lighting demand.
Summary of the invention
The present invention provides a kind of based on adaptive fuzzy decision to solve defect and deficiency existing in the prior art
The light dynamic regulation method of tree, solves and does not comprehensively consider road traffic flow and ambient condition etc. in Street lamps control technology
Influence problem of the factor to street lamp illumination.
In order to solve the above technical problems, the present invention provides a kind of light dynamic regulation side based on adaptive fuzzy decision tree
Method, comprising the following steps:
Step 1, the acquisition of supplemental characteristic: according to influence street lamp illumination factor, determine vehicle flowrate, ambient light illumination,
PM2.5 and time point are the parameter for influencing street lamp illumination, and above-mentioned parameter is divided into several parameter levels；
The degree of membership of step 2, supplemental characteristic calculates: bringing vehicle flowrate, ambient light illumination, PM2.5 and the value at time point into person in servitude
Category degree function calculates the degree of membership data of above-mentioned parameter；
The foundation of fuzzy decision tree-model: step 3 establishes vehicle flowrate, ambient light illumination, PM2.5 and time point and road respectively
Fuzzy decision tree-model between lamp illumination, detailed process is as follows:
3.1 respectively using vehicle flowrate, ambient light illumination, PM2.5 and the supplemental characteristic at time point as training sample, calculates fuzzy
Comentropy H (D):
In above formula, D is the fuzzy set of training sample, and n is the classification number of street lamp level of illumination, piNot go the same way in fuzzy set
The sample number of lamp level of illumination and the ratio of total sample number；
The calculating of 3.2 fuzzy message ratio of profit increase；
Fuzzy set D is divided with time point, it is assumed that time point is attribute A, calculates time point to the division information entropy of fuzzy set
HA(D):
In formula, | Di | for attribute A at dusk or the corresponding sample number of midnight each value, | D | for fuzzy set D sample it is total
Number, H (Di) be attribute A each value Fuzzy Information Entropy；
Computation attribute A, that is, time click and sweep divides the fuzzy message gain G ain (A) of fuzzy set D:
Gain (A)=H (D)-HA(D)
The division information for introducing time point adjusts information gain, the fuzzy message gain S (A) after being adjusted:
The fuzzy message ratio of profit increase GainRatio (A) of computation attribute A division fuzzy set:
Similarly, the fuzzy message ratio of profit increase of vehicle flowrate, ambient light illumination and PM2.5 are calculated, and by the big of information gain-ratio
It is small that attribute is ranked up, successively it is known as the first attribute, the second attribute, third attribute and the 4th by information gain-ratio is descending
Then attribute chooses root node of first attribute as fuzzy decision-tree；
3.3 firstly, divide root node according to parameter level, obtains the parameters grade branch of the first attribute,
Then the angle value that is subordinate to of current attribute is calculated, when being subordinate to significance value α of the angle value greater than parameter level branch,
Then current attribute is divided in the parameter level branch；
Then, the classification confidence level for calculating parameter level described in parameters grade branch, when classification confidence level is big
When its actual water level values β, then the parameter level branch stops division as leaf node；Otherwise, continue to divide；
The parameter level branch for continuing division is divided with the parameter level of the second attribute, obtains each of the second attribute
Parameter level branch, proceeds as described above, until each parameter level branch is leaf node, in this way, completing fuzzy decision
The foundation of tree-model；
The degree of membership data of parameter current are brought into the fuzzy decision tree-model of step 3 foundation, are expired by step 4
The street lamp level of illumination information of the current lighting requirement of foot.
Further, step 3.3 intelligently adjusts the step of significance value α and actual water level values β by particle swarm algorithm
It is as follows:
3.3.1 to population X={ X1...XmInitialized, wherein i-th of particle XiInitial position table in space
It is shown as xi 0=(xi1 0, xi2 0), initial flight speed is expressed as vi 0=(vi1 0, vi2 0)；
3.3.2 each particle X is calculatediFitness value fitness (xi t)；
3.3.3 by each particle XiFitness value fitness (xi t) and its after optimum position pBest value carry out
Compare, if the fitness value fitness (x of the particlei t) better than its after optimum position pBest value, then where the particle
Position is as optimal location pBest=(pi1, pi2)；
3.3.4 by each particle XiFitness value fitness (xi t) with all particles after optimum position gBest
Value is compared, if the particle answers angle value fitness (xi t) better than all particles after optimum position gBest value,
The particle position is as desired positions gBest=(pg1, pg2)；
3.3.5 to XiSpeed and position be iterated according to following formula:
In above-mentioned calculating formula: d=1,2 is the dimension of particle；vid t+1For the particle i speed that d is tieed up in the t+1 times iteration
Degree；vid tFor the particle i speed that d is tieed up in the t times iteration；xid tFor the position that d is tieed up in the t times iteration particle i；pid t
It is particle i in the position of the d individual extreme point tieed up；pgd tThe position of global extreme point is tieed up in d for population；Wherein, c1、c2
For acceleration constant, rand1And rand2For random function, value is [0,1]；
If 3.3.6 XiSpeed and position be not up to setting accuracy, then return step 3.3.2；If reaching setting accuracy,
At this point, the position x of setting accuracyiIn xi1、xi2Respectively significance value α value and actual water level values β value.
Further, in step 2, vehicle flowrate degree of membership calculating process is as follows:
Firstly, dividing vehicle flowrate z for P1、P2、P3Three grades；P1Indicate that vehicle flowrate is 0~100, P per hour2It indicates
Vehicle flowrate is 100~200, P per hour3Indicate that vehicle flowrate is 200~300 per hour；
Secondly, being calculated according to degree of membership calculation formula:
Further, in step 2, the calculating process of ambient light illumination degree of membership is as follows:
Firstly, collecting night average illumination is 25Lux, ambient light illumination y points are L1、L2、L3Three grades；L1Indicate ring
Border illumination is 0~15Lux, L2Expression ambient light illumination is 15~30Lux, L3Expression ambient light illumination is 30~45Lux；
Secondly, being calculated according to degree of membership calculating formula:
Further, in step 2, PM2.5 includes good and pollution two states: being well PM2.5 mean value less than 75 μ g/
m3, pollute and be greater than 75 μ g/m for PM2.5 mean value3；When calculating the degree of membership of PM2.5, PM2.5 value falls in value in good range and is
1, falling in value in pollution range is 0
Further, in step 2, time point is divided into dusk and midnight: dusk time interval is 19:00~23:00；Midnight
Time interval is 23:00~5:00；When calculating the degree of membership at time point, the time interval that time point falls in the dusk is taken as 1, is fallen
It is taken as 0 surely in the time interval section at midnight.
Further, street lamp level of illumination is divided into level-one, second level, three-level, level Four totally four grades, and level-one shows the way lamp with 30%
Power output, second level show the way lamp with 60% power output, and three-level shows the way lamp with 80% power output, and level Four shows the way lamp with 100%
Power output.
A kind of present invention advantageous effects achieved: light based on adaptive fuzzy decision tree provided by the invention
Dynamic regulation method cannot carry out light according to practical vehicle flowrate and ambient condition present invention mainly solves existing road lamp system and move
The problem of state regulates and controls.By determining that night influences the factor of street lamp illumination, analysis vehicle flowrate, ambient light illumination, PM2.5 and time point
With the relationship between street lamp illumination, fuzzy decision tree-model is established, realizes that street lamp illumination can carry out dynamic according to the actual situation
Regulation.The major parameter feature for analyzing Decision Tree Induction Algorithm simultaneously improves mould using particle swarm algorithm intelligence setup parameter value
Paste the inaccurate problem of decision Tree algorithms setup parameter value by rule of thumb
Detailed description of the invention
Fig. 1 fuzzy decision-tree schematic diagram of the embodiment of the present invention.
Specific embodiment
The invention will be further described combined with specific embodiments below.Following embodiment is only used for clearly illustrating
Technical solution of the present invention, and not intended to limit the protection scope of the present invention.
The invention patent is further illustrated with reference to the accompanying drawings and examples.
The present invention provides a kind of light dynamic regulation method based on adaptive fuzzy decision tree, comprising the following steps:
Step 1, the acquisition of supplemental characteristic: according to influence street lamp illumination factor, determine vehicle flowrate, ambient light illumination,
PM2.5 and time point are the parameter for influencing street lamp illumination, and above-mentioned parameter is divided into several parameter levels；
The degree of membership of step 2, supplemental characteristic calculates: bringing vehicle flowrate, ambient light illumination, PM2.5 and the value at time point into person in servitude
Category degree function calculates the degree of membership data of above-mentioned parameter, and calculating process is as follows:
Vehicle flowrate degree of membership calculating process: firstly, dividing vehicle flowrate z for P1、P2、P3Three parameter levels；P1It indicates per small
When vehicle flowrate be 0~100, P2Indicate that vehicle flowrate is 100~200, P per hour3Indicate that vehicle flowrate is 200~300 per hour
?；
Secondly, being calculated according to degree of membership calculation formula:
The calculating process of ambient light illumination degree of membership: firstly, collecting night average illumination is 25Lux, ambient light illumination y points are
L1、L2、L3Three parameter levels；L1Expression ambient light illumination is 0~15Lux, L2Expression ambient light illumination is 15~30Lux, L3It indicates
Ambient light illumination is 30~45Lux；
Secondly, being calculated according to degree of membership calculating formula:
PM2.5 includes good and two parameter levels of pollution: being well PM2.5 mean value less than 75 μ g/m3, pollute and be
PM2.5 mean value is greater than 75 μ g/m3；When calculating the degree of membership of PM2.5, it is 1 that PM2.5 value, which falls in value in good range, falls in dirt
Contaminating value in range is 0
Time point is divided into dusk and two parameter levels of midnight: dusk time interval is 19:00~23:00；Time at midnight
Section is 23:00~5:00；When calculating the degree of membership at time point, the time interval that time point falls in the dusk is taken as 1, falls in the noon
The time interval section at night is taken as 0 surely.
The foundation of fuzzy decision tree-model: step 3 establishes vehicle flowrate, ambient light illumination, PM2.5 and time point and road respectively
Fuzzy decision tree-model between lamp illumination, detailed process is as follows:
3.1 respectively using vehicle flowrate, ambient light illumination, PM2.5 and the supplemental characteristic at time point as training sample, calculates fuzzy
Comentropy H (D):
In above formula, D is the fuzzy set of training sample, and n is the classification number of street lamp level of illumination, piNot go the same way in fuzzy set
The sample number of lamp level of illumination and the ratio of total sample number；
The calculating of 3.2 fuzzy message ratio of profit increase；
Fuzzy set D is divided with time point, it is assumed that time point is attribute A, calculates time point to the division information entropy of fuzzy set
HA(D):
In formula, | Di | for attribute A at dusk or the corresponding sample number of midnight each value, | D | for fuzzy set D sample it is total
Number, H (Di) be attribute A each value Fuzzy Information Entropy；
Computation attribute A, that is, time click and sweep divides the fuzzy message gain G ain (A) of fuzzy set D:
Gain (A)=H (D)-HA(D)
The division information for introducing time point adjusts information gain, the fuzzy message gain S (A) after being adjusted:
The fuzzy message ratio of profit increase GainRatio (A) of computation attribute A division fuzzy set:
Similarly, the fuzzy message ratio of profit increase of vehicle flowrate, ambient light illumination and PM2.5 are calculated, and by the big of information gain-ratio
It is small that attribute is ranked up, successively it is known as the first attribute, the second attribute, third attribute and the 4th by information gain-ratio is descending
Then attribute chooses root node of first attribute as fuzzy decision-tree；
3.3 firstly, divide root node according to parameter level, obtains the parameters grade branch of the first attribute,
Then the angle value that is subordinate to of current attribute is calculated, when being subordinate to significance value α of the angle value greater than parameter level branch,
Then current attribute is divided in the parameter level branch；
Then, the classification confidence level for calculating parameter level described in parameters grade branch, when classification confidence level is big
When its actual water level values β, then the parameter level branch stops division as leaf node；Otherwise, continue to divide；
The parameter level branch for continuing division is divided with the parameter level of the second attribute, obtains each of the second attribute
Parameter level branch, proceeds as described above, until each parameter level branch is leaf node, in this way, completing fuzzy decision
The foundation of tree-model；The present invention also particle swarm algorithm has intelligently adjusted significance value α and actual water level values β, and steps are as follows:
3.3.1 to population X={ X1...XmInitialized, wherein i-th of particle XiInitial position table in space
It is shown as xi 0=(xi1 0, xi2 0), initial flight speed is expressed as vi 0=(vi1 0, vi2 0)；
3.3.2 each particle X is calculatediFitness value fitness (xi t)；
3.3.3 by each particle XiFitness value fitness (xi t) and its after optimum position pBest value carry out
Compare, pBest is the fuzzy decision-tree for the best performance that this particle generates so far, if the fitness value fitness of the particle
(xi t) better than its after optimum position pBest value, then the particle position is as optimal location pBest=(pi1,
pi2)；
3.3.4 by each particle XiFitness value fitness (xi t) with all particles after optimum position gBest
Value is compared, and gBest is the optimal fuzzy decision-tree that entire population is generated to so far, if the particle answers angle value
fitness(xi t) better than all particles after optimum position gBest value, in the particle position as desired positions
GBest=(pg1, pg2)；
3.3.5 to XiSpeed and position be iterated according to following formula:
In above-mentioned calculating formula: d=1,2 is the dimension of particle；vid t+1For the particle i speed that d is tieed up in the t+1 times iteration
Degree；vid tFor the particle i speed that d is tieed up in the t times iteration；xid tFor the position that d is tieed up in the t times iteration particle i；pid t
It is particle i in the position of the d individual extreme point tieed up；pgd tThe position of global extreme point is tieed up in d for population；Wherein, c1、c2
For acceleration constant, rand1And rand2For random function, value is [0,1]；
If 3.3.6 XiSpeed and position be not up to setting accuracy, then return step 3.3.2；If reaching setting accuracy,
At this point, the position x of setting accuracyiIn xi1、xi2Respectively significance value α value and actual water level values β value.
The degree of membership data of parameter current are brought into the fuzzy decision tree-model of step 3 foundation, are expired by step 4
The street lamp level of illumination information of the current lighting requirement of foot, street lamp level of illumination are divided into level-one, second level, three-level, level Four totally four etc.
Grade, level-one show the way lamp with 30% power output, and second level shows the way lamp with 60% power output, and the three-level lamp that shows the way is defeated with 80% power
Out, level Four shows the way lamp with 100% power output.
In addition, the present invention also provides a kind of road lamp system, including Street lamps control node, gateway node and monitoring center,
Video detection module and sensor are housed on each Street lamps control node, vehicle flowrate and environmental information is acquired, is converged by wireless network
Poly- to be sent to gateway node, gateway node is uploaded to streetlight monitoring center for information is acquired.Streetlight monitoring center has decision model
Block establishes fuzzy decision-tree by part degree of membership data, according to vehicle flowrate, ambient light illumination, PM2.5 and time point prediction street lamp
Level of illumination, publication dimming commands to gateway node carry out light dynamic regulation by Street lamps control node.
Embodiment
If choosing 100 roads to better illustrate the process for carrying out light dynamic regulation using fuzzy decision-tree
The road of environment such as table 1 is illustrated.
1:100 road environment of table is for street lamp illumination requirement table
Table 2: using street lamp illumination requirement table after method processing of the invention
Using the Street lamps control with light dynamic regulation function provided by the invention based on adaptive fuzzy decision tree
Method is transported the relationship in this way between analysis vehicle flowrate, ambient light illumination, PM2.5 and time point and street lamp level of illumination, is built
Vertical fuzzy decision-tree, as shown in Figure 1, this prediction model is predicted applied to street lamp illumination.If the time point of detection is the dusk, this
Period is vehicle flowrate peak period, so the output of street lamp full power is to guarantee road lighting demand；If detection time point is midnight,
Best street lamp level of illumination is gone out come decision according to vehicle flowrate, ambient light illumination, PM2.5 at this time.Choose 100 road environment information such as
Shown in table 1, data shown in table 2 are obtained after Fuzzy processing is carried out to it, street lamp illumination is divided into 4 grades.
The present invention is disclosed with preferred embodiment above, so it is not intended to limiting the invention, all to take equivalent replacement
Or the scheme technical solution obtained of equivalent transformation, it falls within the scope of protection of the present invention.
Claims (7)
1. a kind of light dynamic regulation method based on adaptive fuzzy decision tree, it is characterised in that the following steps are included:
Step 1, the acquisition of supplemental characteristic: according to influence street lamp illumination factor, determine vehicle flowrate, ambient light illumination, PM2.5 and
Time point is the parameter for influencing street lamp illumination, and above-mentioned parameter is divided into several parameter levels；
The degree of membership of step 2, supplemental characteristic calculates: bringing vehicle flowrate, ambient light illumination, PM2.5 and the value at time point into degree of membership
Function calculates the degree of membership data of above-mentioned parameter；
Step 3, the foundation of fuzzy decision tree-model: establishing vehicle flowrate, ambient light illumination, PM2.5 and time point respectively and street lamp shines
Fuzzy decision tree-model between degree, detailed process is as follows:
3.1 respectively using vehicle flowrate, ambient light illumination, PM2.5 and the supplemental characteristic at time point as training sample, calculates fuzzy message
Entropy H (D):
In above formula, D is the fuzzy set of training sample, and n is the classification number of street lamp level of illumination, piIt is shone for street lamps different in fuzzy set
Spend the sample number of grade and the ratio of total sample number；
3.2 the calculating of fuzzy message ratio of profit increase；
Fuzzy set D is divided with time point, it is assumed that time point is attribute A, calculates time point to the division information entropy H of fuzzy setA(D):
In formula, | Di | for attribute A at dusk or the corresponding sample number of midnight each value, | D | be fuzzy set D total sample number, H
(Di) be attribute A each value Fuzzy Information Entropy；
Computation attribute A, that is, time click and sweep divides the fuzzy message gain G ain (A) of fuzzy set D:
Gain (A)=H (D)-HA(D)
The division information for introducing time point adjusts information gain, the fuzzy message gain S (A) after being adjusted:
The fuzzy message ratio of profit increase GainRatio (A) of computation attribute A division fuzzy set:
Similarly, the fuzzy message ratio of profit increase of vehicle flowrate, ambient light illumination and PM2.5 are calculated, and presses the size pair of information gain-ratio
Attribute is ranked up, and is belonged to by descending the first attribute, the second attribute, the third attribute and the 4th of being successively known as of information gain-ratio
Property, then choose root node of first attribute as fuzzy decision-tree；
3.3 firstly, divide root node according to parameter level, obtains the parameters grade branch of the first attribute, then
The angle value that is subordinate to of current attribute is calculated, when be subordinate to angle value be greater than parameter level branch significance value α when, then when
Preceding attribute is divided in the parameter level branch；
Then, the classification confidence level for calculating parameter level described in parameters grade branch, when classification confidence level is greater than it
When actual water level values β, then the parameter level branch stops division as leaf node；Otherwise, continue to divide；
The parameter level branch for continuing division is divided with the parameter level of the second attribute, obtains the parameters of the second attribute
Grade branch, proceeds as described above, until each parameter level branch is leaf node, in this way, completing fuzzy decision-tree mould
The foundation of type；
Step 4 brings the degree of membership data of parameter current into the fuzzy decision tree-model of step 3 foundation, obtains to meet and work as
The street lamp level of illumination information that front lit requires.
2. the light dynamic regulation method according to claim 1 based on adaptive fuzzy decision tree, which is characterized in that step
Rapid 3.3 is as follows the step of intelligently adjusting significance value α and actual water level values β by particle swarm algorithm:
3.3.1 to population X={ X1...XmInitialized, wherein i-th of particle XiInitial position in space is expressed as
xi 0=(xi1 0, xi2 0), initial flight speed is expressed as vi 0=(vi1 0, vi2 0)；
3.3.2 each particle X is calculatediFitness value fitness (xi t)；
3.3.3 by each particle XiFitness value fitness (xi t) and its after the value of optimum position pBest compared
Compared with if the fitness value fitness (x of the particlei t) better than its after optimum position pBest value, then particle institute is in place
It sets as optimal location pBest=(pi1, pi2)；
3.3.4 by each particle XiFitness value fitness (xi t) with all particles after optimum position gBest value into
Row compares, if the particle answers angle value fitness (xi t) better than all particles after optimum position gBest value, in the grain
Sub- position is as desired positions gBest=(pg1, pg2)；
3.3.5 to XiSpeed and position be iterated according to following formula:
In above-mentioned calculating formula: d=1,2 is the dimension of particle；vid t+1For the particle i speed that d is tieed up in the t+1 times iteration；vid t
For the particle i speed that d is tieed up in the t times iteration；xid tFor the position that d is tieed up in the t times iteration particle i；pid tFor particle i
In the position of the individual extreme point of d dimension；pgd tThe position of global extreme point is tieed up in d for population；Wherein, c1、c2To accelerate
Spend constant, rand1And rand2For random function, value is [0,1]；
If 3.3.6 XiSpeed and position be not up to setting accuracy, then return step 3.3.2；If reaching setting accuracy, at this point,
The position x of setting accuracyiIn xi1、xi2Respectively significance value α value and actual water level values β value.
3. the light dynamic regulation method according to claim 1 based on adaptive fuzzy decision tree, it is characterised in that: step
In rapid two, vehicle flowrate degree of membership calculating process is as follows:
Firstly, dividing vehicle flowrate z for P1、P2、P3Three grades；P1Indicate that vehicle flowrate is 0~100, P per hour2It indicates per small
When vehicle flowrate be 100~200, P3Indicate that vehicle flowrate is 200~300 per hour；
Secondly, being calculated according to degree of membership calculation formula:
4. the light dynamic regulation method according to claim 1 based on adaptive fuzzy decision tree, it is characterised in that: step
In rapid two, the calculating process of ambient light illumination degree of membership is as follows:
Firstly, collecting night average illumination is 25Lux, ambient light illumination y points are L1、L2、L3Three grades；L1Indicate ambient light illumination
For 0~15Lux, L2Expression ambient light illumination is 15~30Lux, L3Expression ambient light illumination is 30~45Lux；
Secondly, being calculated according to degree of membership calculating formula:
5. the light dynamic regulation method according to claim 1 based on adaptive fuzzy decision tree, it is characterised in that: step
In rapid two, PM2.5 includes good and pollution two states: being well PM2.5 mean value less than 75 μ g/m3, pollute for PM2.5 mean value
Greater than 75 μ g/m3；When calculating the degree of membership of PM2.5, it is 1 that PM2.5 value, which falls in value in good range, falls in pollution range and takes
Value is 0.
6. the light dynamic regulation method according to claim 1 based on adaptive fuzzy decision tree, it is characterised in that: step
In rapid two, time point is divided into dusk and midnight: dusk time interval is 19:00~23:00；Midnight time interval be 23:00~
5:00；When calculating the degree of membership at time point, the time interval that time point falls in the dusk is taken as 1, falls in the time interval at midnight
Section is taken as 0 surely.
7. the light dynamic regulation method according to claim 1 based on adaptive fuzzy decision tree, it is characterised in that: road
Lamp level of illumination is divided into level-one, second level, three-level, level Four totally four grades, and level-one shows the way lamp with 30% power output, and second level shows the way
Lamp is with 60% power output, and three-level shows the way lamp with 80% power output, and level Four shows the way lamp with 100% power output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810544765.XA CN108966448A (en) | 2018-05-31 | 2018-05-31 | A kind of light dynamic regulation method based on adaptive fuzzy decision tree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810544765.XA CN108966448A (en) | 2018-05-31 | 2018-05-31 | A kind of light dynamic regulation method based on adaptive fuzzy decision tree |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108966448A true CN108966448A (en) | 2018-12-07 |
Family
ID=64492408
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810544765.XA Pending CN108966448A (en) | 2018-05-31 | 2018-05-31 | A kind of light dynamic regulation method based on adaptive fuzzy decision tree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108966448A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110267393A (en) * | 2019-06-05 | 2019-09-20 | 中铁城市规划设计研究院有限公司 | A kind of LED street lamp intelligent dimming control system based on illumination and vehicle flowrate |
| CN110718236A (en) * | 2019-10-12 | 2020-01-21 | 吴郁君 | Urban environment big data comprehensive collaborative management operation platform |
| CN111080150A (en) * | 2019-12-23 | 2020-04-28 | 杭州雷数科技有限公司 | Production data analysis method, apparatus, device and medium |
| CN111256428A (en) * | 2020-01-20 | 2020-06-09 | 连云港韬惠实业有限公司 | Self-adaptive fuzzy control method for temperature of refrigeration house |
| CN116774749A (en) * | 2023-08-25 | 2023-09-19 | 北京拓普尔通信技术有限公司 | Intelligent temperature-control electric power cabinet |
| CN116846082A (en) * | 2023-08-31 | 2023-10-03 | 北京拓普尔通信技术有限公司 | Intelligent remote control system for power distribution cabinet |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573873A (en) * | 2015-01-23 | 2015-04-29 | 哈尔滨工业大学 | Airport terminal departure passenger traffic volume prediction method based on fuzzy decision-making tree |
| CN106028506A (en) * | 2016-05-24 | 2016-10-12 | 吉林蓝锐电子科技有限公司 | Intelligent LED street lamp and control method thereof |
| CN106126328A (en) * | 2016-06-24 | 2016-11-16 | 同济大学 | A kind of traffic metadata management method based on event classification and system |
| CN106202886A (en) * | 2016-06-29 | 2016-12-07 | 中国铁路总公司 | Track circuit red band Fault Locating Method based on fuzzy coarse central Yu decision tree |
| CN106682915A (en) * | 2016-12-25 | 2017-05-17 | 东北电力大学 | User cluster analysis method in customer care system |
-
2018
- 2018-05-31 CN CN201810544765.XA patent/CN108966448A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573873A (en) * | 2015-01-23 | 2015-04-29 | 哈尔滨工业大学 | Airport terminal departure passenger traffic volume prediction method based on fuzzy decision-making tree |
| CN106028506A (en) * | 2016-05-24 | 2016-10-12 | 吉林蓝锐电子科技有限公司 | Intelligent LED street lamp and control method thereof |
| CN106126328A (en) * | 2016-06-24 | 2016-11-16 | 同济大学 | A kind of traffic metadata management method based on event classification and system |
| CN106202886A (en) * | 2016-06-29 | 2016-12-07 | 中国铁路总公司 | Track circuit red band Fault Locating Method based on fuzzy coarse central Yu decision tree |
| CN106682915A (en) * | 2016-12-25 | 2017-05-17 | 东北电力大学 | User cluster analysis method in customer care system |
Non-Patent Citations (1)
| Title |
|---|
| 孙娟，王熙照: "自适应模糊决策树算法", 《计算机工程与设计》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110267393A (en) * | 2019-06-05 | 2019-09-20 | 中铁城市规划设计研究院有限公司 | A kind of LED street lamp intelligent dimming control system based on illumination and vehicle flowrate |
| CN110718236A (en) * | 2019-10-12 | 2020-01-21 | 吴郁君 | Urban environment big data comprehensive collaborative management operation platform |
| CN111080150A (en) * | 2019-12-23 | 2020-04-28 | 杭州雷数科技有限公司 | Production data analysis method, apparatus, device and medium |
| CN111256428A (en) * | 2020-01-20 | 2020-06-09 | 连云港韬惠实业有限公司 | Self-adaptive fuzzy control method for temperature of refrigeration house |
| CN116774749A (en) * | 2023-08-25 | 2023-09-19 | 北京拓普尔通信技术有限公司 | Intelligent temperature-control electric power cabinet |
| CN116774749B (en) * | 2023-08-25 | 2023-11-03 | 北京拓普尔通信技术有限公司 | Intelligent temperature-control electric power cabinet |
| CN116846082A (en) * | 2023-08-31 | 2023-10-03 | 北京拓普尔通信技术有限公司 | Intelligent remote control system for power distribution cabinet |
| CN116846082B (en) * | 2023-08-31 | 2023-11-03 | 北京拓普尔通信技术有限公司 | Remote control system for power distribution cabinet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108966448A (en) | A kind of light dynamic regulation method based on adaptive fuzzy decision tree | |
| CN111739284B (en) | Traffic signal lamp intelligent timing method based on genetic algorithm optimization fuzzy control | |
| CN109919353A (en) | A kind of distributed photovoltaic prediction technique of the ARIMA model based on spatial coherence | |
| Tukymbekov et al. | Intelligent autonomous street lighting system based on weather forecast using LSTM | |
| CN111462485A (en) | Traffic intersection congestion prediction method based on machine learning | |
| CN111556631A (en) | Tunnel traffic lighting system intelligent control method based on PSO and RBFNN | |
| CN107864541A (en) | Tunnel illumination intelligent dimming method | |
| CN109948824A (en) | A method of thermal substation thermic load is predicted using mode identification technology | |
| CN115802559B (en) | Intelligent illumination control method and device, computer equipment and storage medium | |
| CN109902402B (en) | Intelligent lighting dimming control method based on multi-environment parameters | |
| CN107979900A (en) | A kind of road lamp intelligence energy saving method based on random forest regression forecasting algorithm | |
| CN115968088A (en) | Intelligent tunnel dimming method and system and computer storage medium | |
| CN114867165A (en) | Intelligent street lamp control method based on long-term and short-term memory neural network | |
| He et al. | Illumination control of intelligent street lamps based on fuzzy decision | |
| CN112954863A (en) | Street lamp intelligent control method and system based on big data analysis | |
| CN113505346B (en) | Urban street lamp data processing and combined regulation and control system based on artificial intelligence | |
| CN109709800A (en) | Based on fireworks algorithm-Adaptive Fuzzy PID LED street lamp intelligent control and device | |
| CN115767857A (en) | Intelligent street lamp illumination remote online monitoring, regulation and control management system | |
| CN114126159B (en) | Extreme weather-oriented intelligent street lamp dimming method, system and storage medium | |
| Kolasa | The concept of intelligent system for street lighting control using artificial neural networks | |
| CN110533264A (en) | Building performance evaluating method | |
| Ramadhani et al. | Smart Room Lighting System for Energy Efficiency in Indoor Environment | |
| CN117173895B (en) | Management monitoring system for automatic illumination adjustment of urban road | |
| Xue et al. | An Intelligent Dimming Algorithm of Streetlight Based on Fuzzy Neural Network | |
| CN110263407A (en) | Subway environment energy conservation cloud model construction method based on Internet of Things and big data |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181207 |