CN108629400A - A kind of chaos artificial bee colony algorithm based on Levy search - Google Patents
A kind of chaos artificial bee colony algorithm based on Levy search Download PDFInfo
- Publication number
- CN108629400A CN108629400A CN201810464727.3A CN201810464727A CN108629400A CN 108629400 A CN108629400 A CN 108629400A CN 201810464727 A CN201810464727 A CN 201810464727A CN 108629400 A CN108629400 A CN 108629400A
- Authority
- CN
- China
- Prior art keywords
- bee
- algorithm
- candidate solution
- formula
- solution
- 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
Classifications
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of chaos artificial bee colony algorithms based on Levy search.The algorithm introduces chaology and L é vy theory of flight, realizes a kind of new artificial bee colony algorithm；Solution is initialized by chaology, accelerates algorithm the convergence speed；It is employing the bee optimizing stage that globally optimal solution boot policy is added, is improving the algorithm overall situation and search plain ability；It is following the bee stage that L é vy countermeasures are added, is jumping out locally optimal solution, so that inventive algorithm balances global and local optimizing ability, improve the precision of optimizing solution.
Description
Technical field
The present invention relates to a kind of chaos artificial bee colony algorithms based on Levy search.
Background technology
Traditional " swarm intelligence " this concept in 1989[1], by nearly development in 30 years, colony intelligence optimization algorithm is employed
In many complicated practical problems, good effect is achieved.
Karaboga in 2005 et al. is looked for food by honeybee and dancing behavior is inspired, it is proposed that artificial bee colony
(Artificial Bee Colony) algorithm[2-3].Optimizing is carried out by simulating bee colony gathering honey and dancing characteristic, is quickly obtained
Locally optimal solution.Artificial bee colony algorithm is efficient, solve effect it is good, receive significant attention, be successfully applied to tagsort,
The fields such as artificial neural network training, minimal attributes reductions.That there are algorithms is precocious for traditional artificial ant colony algorithm, convergence rate is slow,
The shortcomings of local search ability is strong but global optimizing ability is poor, as the problem of facing mankind becomes increasingly complex, to algorithm
Optimizing requirement is also higher and higher, how to improve algorithm and is absorbed in local optimum, improve algorithm the convergence speed, improves efficiency of algorithm, especially
It keeps the stability of algorithm when encountering higher-dimension challenge, all becomes urgently to be resolved hurrily in artificial bee colony algorithm optimization and asks
Topic.
Also there are numerous scholars to propose the improvement of artificial bee colony algorithm in recent years, improves the overall situation of algorithm to a certain extent
Optimizing ability and solving precision.2015, Zhang H [4] et al. proposed that will improve artificial bee colony algorithm is used for integrated circuit cloth
Line field；Rough set theory is introduced ant colony algorithm by Ye Dongyi [5] et al., and is applied to minimal attributes reductions problem.2017,
He Y [6] propose a kind of binary system artificial bee colony algorithm to solve alliance's knapsack problem, and Cui L [7] are adaptive by population size
Mode introduces artificial bee colony algorithm, the exploitation for balanced algorithm and search capability.In conclusion either still being answered from theory
From the point of view of, being optimized to artificial bee colony algorithm all has research value and realistic meaning.
In order to improve the global optimizing ability of algorithm, the precision of optimizing solution is improved, chaology and L é vy flight reasons are introduced
By the present invention proposes a kind of new artificial bee colony algorithm (LABC).
Bibliography：
[1]Hinchey M G,Sterritt R,Rouff C.Swarms and swarm intelligence[J]
.Computer,2007,40(4):111-113.
[2]Karaboga D.An idea based on honey bee swarm for numerical
Optimization [J] .Technical Report-TR06.Kayseri, Turkey:Erciyes University, 2005.
[3]Karaboga D,Basturk B.A powerful and efficient algorithm for
numerical function optimization:Artificial bee colony algorithm[J].Journal of
Global Optimization, 2007,39 (3):459-471.
[4]Zhang H,Ye D.Key-node-based local search discrete artificial bee
colony algorithm for obstacle-avoiding rectilinear Steiner tree construction
[J].Neural Computing and Applications.2015,26(4):875-898.
One effective combinatorial artificial ant colony algorithm [J] electronics of the bright minimal attributes reductions problem of [5] Ye Dongyi, Chen Zhao
Journal .2015 (05):1014-1020.
[6]He Y,Xie H,Wong T L,et al.A novel binary artificial bee colony
algorithm for the set-union knapsack problem[J].Future Generation Computer
Systems,2018,78:77-86.
[7]Cui L,Li G,Zhu Z,et al.A novel artificial bee colony algorithm
with an adaptive population size for numerical function optimization[J]
.Information Sciences.2017,414:53-67.。
Invention content
The purpose of the present invention is to provide a kind of chaos artificial bee colony algorithm based on Levy search, which improves entirely
The precision of office's optimizing ability and optimizing solution.
To achieve the above object, the technical scheme is that：A kind of chaos artificial bee colony algorithm based on Levy search,
Include the following steps：
Step S1, initialization population quantity 2SN employs bee and follows bee each SN, and maximum iteration itermax is followed
The maximum search number limit of bee initializes the solution of artificial bee colony algorithm using chaology；
Step S2, chaos sequence is generated using Logistic mapping formulas (1), candidate solution initialization is carried out using formula (2)：
Wherein, μ ∈ [0,4] are random number, and when the time series of μ=4 is in Complete Chaos state, i=1 ..., SN, SN is honey
Source quantity；J=1,2 ..., D, D are individual dimension；K indicates iterations；Lower bound is tieed up for jth,The upper bound is tieed up for jth；
Step S3, the bee search phase is employed to find candidate solution using the strategy of global optimum's guiding, formula is such as shown in (3)：
Wherein,It is tieed up for the jth of i-th of candidate solution in the t times iteration,For k-th candidate solution jth dimension (k ≠
I φ) φ be [- 1,1] random number,It is tieed up for the jth of current optimal solution,α be [0,1] with
Machine number, β=0.5, iter are current iteration number, and itermax is maximum iteration；
Step S4, follow the bee stage that the L é vy countermeasures in cuckoo algorithm is combined to carry out neighborhood search, formula such as (4) institute
Show；L é vy flights are a kind of Markov random processes, and moving step length obeys L é vy distributions, and formula is such as shown in (5)：
Wherein,It is tieed up for the jth of i-th of candidate solution in the t times iteration,It is tieed up for the jth of current optimal solution, r is
The random number of (0,1), s are the step-length of L é vy countermeasures；
L (s)~| s |-1-β, 0 β≤2 ＜ (5)
Wherein, s is arbitrary width, as shown in formula (6)：
S=u/ | v |1/β (6)
U and v meets normal distribution, u~N (0, σ u2), v~N (0, σ v2)：
Γ is standard Gamma functions, wherein
Step S5, the fitness value of candidate solution, formula such as (8) institute are calculated according to target function value and fitness calculation formula
Show, follows bee according to greedy selection algorithm, formula such as (9) is shown, if newer candidate solution fitness value is higher than original candidate
Solution, then replace original candidate solution；Otherwise retain original candidate solution；
Wherein, piFor the probability of nectar source selection, fit (xi) it is nectar source xiFitness value；
If candidate solution step S6, searched does not update also reaching maximum search number limit, corresponding position is employed
It hires bee and is changed into investigation bee, new candidate solution is generated using formula (2), continues to search near candidate solution neighborhood using formula (3)
Rope；
When step S7, reaching algorithm end condition, the optimal solution searched out is exported, terminates algorithm.
Compared to the prior art, the invention has the advantages that：
1) chaos intialization：The present invention initializes solution using chaos sequence；Chaos sequence have ergodic and with
Machine, the diversity and randomness of solution can be increased by carrying out initialization using chaos sequence, accelerate convergence rate；
2) L é vy countermeasures globally optimal solution guiding search：This method is received particle cluster algorithm and is inspired, and is searched for employing bee
Stage introduces the globally optimal solution boot policy of particle cluster algorithm, and modified parameters, improves the ability of searching optimum of algorithm；It follows
The bee stage uses the step-length modified parameters of L é vy countermeasures, in candidate solution neighborhood search, can increase algorithm and jump out part most
Excellent ability improves solving precision；
3) this algorithm can be used for Multiobjective Optimization Problem.
Description of the drawings
Fig. 1 is inventive algorithm flow chart.
Specific implementation mode
Below in conjunction with the accompanying drawings, technical scheme of the present invention is specifically described.
As shown in Figure 1, a kind of chaos artificial bee colony algorithm based on Levy search of the present invention, includes the following steps：
Step S1, initialization population quantity 2SN employs bee and follows bee each SN, and maximum iteration itermax is followed
The maximum search number limit of bee initializes the solution of artificial bee colony algorithm using chaology；
Step S2, chaos sequence is generated using Logistic mapping formulas (1), candidate solution initialization is carried out using formula (2)：
Wherein, μ ∈ [0,4] are random number, and when the time series of μ=4 is in Complete Chaos state, i=1 ..., SN, SN is honey
Source quantity；J=1,2 ..., D, D are individual dimension；K indicates iterations；Lower bound is tieed up for jth,The upper bound is tieed up for jth；
Step S3, the bee search phase is employed to find candidate solution using the strategy of global optimum's guiding, formula is such as shown in (3)：
Wherein,It is tieed up for the jth of i-th of candidate solution in the t times iteration,For k-th candidate solution jth dimension (k ≠
I φ) φ be [- 1,1] random number,It is tieed up for the jth of current optimal solution,α be [0,1] with
Machine number, β=0.5, iter are current iteration number, and itermax is maximum iteration；
Step S4, follow the bee stage that the L é vy countermeasures in cuckoo algorithm is combined to carry out neighborhood search, formula such as (4) institute
Show；L é vy flights are a kind of Markov random processes, and moving step length obeys L é vy distributions, and formula is such as shown in (5)：
Wherein,It is tieed up for the jth of i-th of candidate solution in the t times iteration,It is tieed up for the jth of current optimal solution, r is
The random number of (0,1), s are the step-length of L é vy countermeasures；
L (s)~| s |-1-β, 0 β≤2 ＜ (5)
Wherein, s is arbitrary width, as shown in formula (6)：
S=u/ | v |1/β (6)
U and v meets normal distribution, u~N (0, σ u2), v~N (0, σ v2)：
Γ is standard Gamma functions, wherein
Step S5, the fitness value of candidate solution, formula such as (8) institute are calculated according to target function value and fitness calculation formula
Show, follows bee according to greedy selection algorithm, formula such as (9) is shown, if newer candidate solution fitness value is higher than original candidate
Solution, then replace original candidate solution；Otherwise retain original candidate solution；
Wherein, piFor the probability of nectar source selection, fit (xi) it is nectar source xiFitness value；
If candidate solution step S6, searched does not update also reaching maximum search number limit, corresponding position is employed
It hires bee and is changed into investigation bee, new candidate solution is generated using formula (2), continues to search near candidate solution neighborhood using formula (3)
Rope；
When step S7, reaching algorithm end condition, the optimal solution searched out is exported, terminates algorithm.
The above are preferred embodiments of the present invention, all any changes made according to the technical solution of the present invention, and generated function is made
When with range without departing from technical solution of the present invention, all belong to the scope of protection of the present invention.
Claims (1)
1. a kind of chaos artificial bee colony algorithm based on Levy search, which is characterized in that include the following steps：
Step S1, initialization population quantity 2SN employs bee and bee each SN, maximum iteration itermax is followed to follow bee
Maximum search number limit initializes the solution of artificial bee colony algorithm using chaology；
Step S2, chaos sequence is generated using Logistic mapping formulas (1), candidate solution initialization is carried out using formula (2)：
Wherein, μ ∈ [0,4] are random number, and when the time series of μ=4 is in Complete Chaos state, i=1 ..., SN, SN is nectar source number
Amount；J=1,2 ..., D, D are individual dimension；K indicates iterations；Lower bound is tieed up for jth,The upper bound is tieed up for jth；
Step S3, the bee search phase is employed to find candidate solution using the strategy of global optimum's guiding, formula is such as shown in (3)：
Wherein,It is tieed up for the jth of i-th of candidate solution in the t times iteration,(k ≠ i φ) is tieed up for the jth of k-th of candidate solution
φ is the random number of [- 1,1],It is tieed up for the jth of current optimal solution,α is the random number of [0,1],
β=0.5, iter are current iteration number, and itermax is maximum iteration；
Step S4, the bee stage is followed to combine in cuckoo algorithmCountermeasures carry out neighborhood search, and formula is such as shown in (4)；Flight is a kind of Markov random process, and moving step length is obeyedDistribution, formula is such as shown in (5)：
Wherein,It is tieed up for the jth of i-th of candidate solution in the t times iteration,For current optimal solution jth tie up, r be (0,
1) random number, s areThe step-length of countermeasures；
L (s)~| s |-1-β, 0 β≤2 ＜ (5)
Wherein, s is arbitrary width, as shown in formula (6)：
S=u/ | v |1/β (6)
U and v meets normal distribution, u~N (0, σu 2), v~N (0, σv 2)：
Γ is standard Gamma functions, wherein
Step S5, the fitness value of candidate solution is calculated according to target function value and fitness calculation formula, formula such as (8) is shown,
Follow bee according to greedy selection algorithm, formula such as (9) is shown, if newer candidate solution fitness value is higher than original candidate solution,
Then replace original candidate solution；Otherwise retain original candidate solution；
Wherein, piFor the probability of nectar source selection, fit (xi) it is nectar source xiFitness value；
If candidate solution step S6, searched does not update also reaching maximum search number limit, bee is employed in corresponding position
It is changed into investigation bee, new candidate solution is generated using formula (2), is continued search near candidate solution neighborhood using formula (3)；
When step S7, reaching algorithm end condition, the optimal solution searched out is exported, terminates algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810464727.3A CN108629400A (en) | 2018-05-15 | 2018-05-15 | A kind of chaos artificial bee colony algorithm based on Levy search |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810464727.3A CN108629400A (en) | 2018-05-15 | 2018-05-15 | A kind of chaos artificial bee colony algorithm based on Levy search |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108629400A true CN108629400A (en) | 2018-10-09 |
Family
ID=63693541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810464727.3A Pending CN108629400A (en) | 2018-05-15 | 2018-05-15 | A kind of chaos artificial bee colony algorithm based on Levy search |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108629400A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109558700A (en) * | 2019-02-12 | 2019-04-02 | 福州大学 | A kind of level Four design of gears method based on DSM-ABC algorithm |
| CN109754057A (en) * | 2019-01-31 | 2019-05-14 | 福州大学 | Reducer dead weight design method combined with speed disturbance mechanism chaotic locust algorithm |
| CN111982118A (en) * | 2020-08-19 | 2020-11-24 | 合肥工业大学 | Method and device for determining walking track of robot, computer equipment and storage medium |
| CN112995075A (en) * | 2021-02-15 | 2021-06-18 | 青岛科技大学 | Acoustic channel equalization method based on championship selection chaotic artificial bee colony algorithm |
| CN113365282A (en) * | 2021-06-22 | 2021-09-07 | 成都信息工程大学 | WSN obstacle area covering deployment method adopting artificial bee colony algorithm of problem features |
| CN113673662A (en) * | 2021-08-02 | 2021-11-19 | 南京邮电大学 | Chaotic bee colony Web service combination optimization method based on reverse learning |
| CN114550827A (en) * | 2022-01-14 | 2022-05-27 | 山东师范大学 | Gene sequence comparison method and system |
-
2018
- 2018-05-15 CN CN201810464727.3A patent/CN108629400A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109754057A (en) * | 2019-01-31 | 2019-05-14 | 福州大学 | Reducer dead weight design method combined with speed disturbance mechanism chaotic locust algorithm |
| CN109754057B (en) * | 2019-01-31 | 2022-05-13 | 福州大学 | Reducer dead weight design method combined with speed disturbance mechanism chaotic locust algorithm |
| CN109558700A (en) * | 2019-02-12 | 2019-04-02 | 福州大学 | A kind of level Four design of gears method based on DSM-ABC algorithm |
| CN109558700B (en) * | 2019-02-12 | 2022-05-17 | 福州大学 | Four-stage gear design method based on DSM-ABC algorithm |
| CN111982118A (en) * | 2020-08-19 | 2020-11-24 | 合肥工业大学 | Method and device for determining walking track of robot, computer equipment and storage medium |
| CN111982118B (en) * | 2020-08-19 | 2023-05-05 | 合肥工业大学 | Robot walking track determining method and device, computer equipment and storage medium |
| CN112995075B (en) * | 2021-02-15 | 2022-04-26 | 青岛科技大学 | Acoustic channel equalization method based on championship selection chaotic artificial bee colony algorithm |
| CN112995075A (en) * | 2021-02-15 | 2021-06-18 | 青岛科技大学 | Acoustic channel equalization method based on championship selection chaotic artificial bee colony algorithm |
| CN113365282A (en) * | 2021-06-22 | 2021-09-07 | 成都信息工程大学 | WSN obstacle area covering deployment method adopting artificial bee colony algorithm of problem features |
| CN113673662A (en) * | 2021-08-02 | 2021-11-19 | 南京邮电大学 | Chaotic bee colony Web service combination optimization method based on reverse learning |
| CN113673662B (en) * | 2021-08-02 | 2024-01-09 | 南京邮电大学 | Chaotic swarm Web service combination optimization method based on reverse learning |
| CN114550827A (en) * | 2022-01-14 | 2022-05-27 | 山东师范大学 | Gene sequence comparison method and system |
| CN114550827B (en) * | 2022-01-14 | 2022-11-22 | 山东师范大学 | Gene sequence comparison method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108629400A (en) | A kind of chaos artificial bee colony algorithm based on Levy search | |
| Wang et al. | Stud krill herd algorithm | |
| Rini et al. | Particle swarm optimization: technique, system and challenges | |
| Tang et al. | A hybrid improved whale optimization algorithm | |
| Siqueira et al. | Simplified binary cat swarm optimization | |
| Li et al. | Analysis and improvement of the bacterial foraging optimization algorithm | |
| Luo et al. | Novel grey wolf optimization based on modified differential evolution for numerical function optimization | |
| CN108875896A (en) | A kind of disturbance chaos artificial bee colony algorithm certainly of global optimum's guidance | |
| Guo et al. | Modified brain storm optimization algorithm for multimodal optimization | |
| Xu et al. | A survey on dynamic neural networks for natural language processing | |
| Cai et al. | Self-organizing neighborhood-based differential evolution for global optimization | |
| Fei et al. | Research on data mining algorithm based on neural network and particle swarm optimization | |
| Fan et al. | A modified salp swarm algorithm based on the perturbation weight for global optimization problems | |
| Meng et al. | PaDE-NPC: Parameter adaptive differential evolution with novel parameter control for single-objective optimization | |
| CN108171322A (en) | A kind of Learning Algorithm based on particle group optimizing | |
| Wang et al. | Cooperative velocity updating model based particle swarm optimization | |
| CN112085144A (en) | Method for guiding artificial bee colony through adaptive covariance learning | |
| Amponsah et al. | An enhanced class topper algorithm based on particle swarm optimizer for global optimization | |
| Liu et al. | An efficient differential evolution via both top collective and p-best information | |
| Li et al. | A hybrid multi-group co-evolution intelligent optimization algorithm: pso-gwo | |
| CN114662638A (en) | Mobile robot path planning method based on improved artificial bee colony algorithm | |
| CN113034343B (en) | Parameter-adaptive hyperspectral image classification GPU parallel method | |
| CN108921354A (en) | A method of the ant colony algorithm for solving TSP problems based on particle group optimizing | |
| Zhang et al. | Linear weighted Gbest-guided artificial bee colony algorithm | |
| CN114004326A (en) | ELM neural network optimization method based on improved suburb algorithm |
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 |
Application publication date: 20181009 |
|
| RJ01 | Rejection of invention patent application after publication |