CN103310279B - Multi-objective optimization product configuration method based on hybrid ant colony - Google Patents
Multi-objective optimization product configuration method based on hybrid ant colony Download PDFInfo
- Publication number
- CN103310279B CN103310279B CN201210062326.8A CN201210062326A CN103310279B CN 103310279 B CN103310279 B CN 103310279B CN 201210062326 A CN201210062326 A CN 201210062326A CN 103310279 B CN103310279 B CN 103310279B
- Authority
- CN
- China
- Prior art keywords
- production
- order
- product
- node
- index
- 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.)
- Expired - Fee Related
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The present invention provides a kind of multi-objective optimization product configuration method based on hybrid ant colony, comprises the following steps：（1）According to the different situations of consumer product order, each order is divided into multiple production phases；（2）The production node of each order is obtained, determines the production moment of each order, calculates production cost of the order product at the production moment of the order；（3）Determine whether each order arranges production；（4）It is determined that need the scheduling scheme of order produced；（5）Output scheduling scheme, arranges production., can be with optimization production scheduling, reasonable distribution production time by the method.
Description
Technical field
The present invention relates to a kind of multi-objective optimization product configuration method based on hybrid ant colony, belong to large-scale customization
Production schedule Flexible planning scheduling field under pattern, mainly for multi-objective optimization question.
Background technology
At present, the research direction of products configuration is deployed primarily directed to the expression of model and the solution of algorithm, its is normal
Mainly solved with algorithm using intelligent optimization algorithm, representative therein has artificial fish-swarm algorithm, genetic algorithm, artificial immunity to calculate
Method, with decision tree and Min-conflicts change algorithm etc..
Above method on general allocation problem can more satisfactorily rapid solving, but still suffer from part deficiency：
Broad sense：Defined from the characteristics of products configuration of multiple-objection optimization
1st, only for the structural model and functional module of product, using the similarity of model as classification foundation, mostly only
Algorithm using minimum production cost as target.But under large-scale customization pattern, the products configuration of enterprise should be related to entirely
The life cycle of product, should be a series of by inventory cost, CSAT, the vacant production capacity of dynamic, the dynamic quality of production etc.
New optimization purpose and constraint, which are included, considers scope.
2nd, traditional product configuration scheme and the mechanism of temporally benchmark scheduling is not introduced into, is simply running into rush order
When, completed simply using rush order as override target, without analyzing its reasonability.
3rd, product configuration scheme at this stage is mainly for the configuration mode for being production process of the single product in enterprise,
The connection problem of production phase is not embodied.
Narrow sense：Discussed from algorithm structure composition itself
1st, existing general intelligence optimized algorithm mainly finds mode or single pheromones algorithm using single, function compared with
To be single, the main analog part of actual information search system.And in fact, in real life any complication system
All it is organized, has the division of labor, different searching routes has different pheromones regulatory mechanisms.
2nd, using products configuration algorithm as a system come to study its important characteristic be self-organizing, this is all
One common trait of intelligent optimization algorithm.Definition of the feedback in systematics is the present behavior of influence system behavior in future.
The accumulation of pheromones on optimal path, algorithm is set to advance towards optimal direction as positive feedback, but the path in actual nature
Node has its intrinsic saturation degree, easily causes the production congestion of node.
3rd, when search space increases, rising due to searching for node in the order of magnitude, the repeatability of systematic search greatly improves,
Search efficiency is decreased obviously.
4th, on the premise of multi-objective optimization question, the characteristics of by structural model and functional module, although limiting one
The generation of fixed invalid configuration, but the convergence of system is still poor, product easily produces substantial amounts of possible arrangement, it is necessary to people
Work carries out suboptimization again.
The present invention asks on the basis of being studied based on more than for solving multiple-objection optimization under Mass Customization Production Model
Inscribe (multi objective optimization problem, MOP), have studied it is a kind of containing multi-ant colony, multi information element it is mixed
Close polymorphic ant colony algorithm (polymorphic ant colony algorithm, PACA).And Gridding Method is proposed, study
Hybrid ant colony under Timing Constraints.The multiple target matrix and multi-objective restriction of correlation are established, and proposes conjunction
Suitable hybrid ant colony step.
The content of the invention
The invention aims to solve above-mentioned technical problem, there is provided a kind of multiple target based on hybrid ant colony is excellent
Change product configuration method, to realize the disposal options more optimized to order product, larger utilize existing resource.
The present invention adopts the technical scheme that：
A kind of multi-objective optimization product configuration method based on hybrid ant colony, comprises the following steps：
(1) according to the different situations of consumer product order, each order is divided into multiple production phases；
(2) the production node of each order is obtained, determines the production moment of each order, calculates the order product in the order
Produce the production cost at moment；
(3) determine whether each order arranges production；
(4) scheduling scheme for the order that needs produce is determined；
(5) output scheduling scheme, arrange production.
Further, described (2) step is to determine parameter by following algorithm：
By the mathematical modeling for quantifying order, there is provided：
Object function：
Model constrains：
In formula, K is the production phase sum of order product；K is the index in K production phase；NkFor k-th of production rank
The production node quantity possessed in section；R is the production unit index in k-th of production phase；G is tkThe production that moment is included
Product order species；H is the index of order species in set G；NmFor the product sum of every class order；J is set NmIn index；
tkFor the initial time of order i k-th of production phase；For tkMoment (a, b, c) individual product production node (x,
Y) production cost；The unit inventory cost of node (x, y) is being produced for (a, b, c) individual product；For client
The expectation production time of node (x, y) is being produced to (a, b, c) individual product；Produced for (a, b, c) individual product
The actual production time of node (x, y)；Be (a, b, c) individual product produce node (x, y) additional inventory when
Between；Π is set to the irreversible extension factor of enterprise, introduces as back order tolerance parameter, can be set to definite value；For
tkMoment set NkThe production capacity summation that can be provided；For tkProduction capacity required for moment product.
The beneficial effects of the invention are as follows：
For solving multi-objective optimization question (multi objective under Mass Customization Production Model
Optimization problem, MOP), pass through a kind of mixing polymorphic ant colony algorithm containing multi-ant colony, multi information element
(polymorphic ant colony algorithm, PACA).And Gridding Method is proposed, it have studied Timing Constraints
Under hybrid ant colony.The multiple target matrix and multi-objective restriction of correlation are established, and proposes suitable mixing ant colony and calculates
Method step, the production to order are optimized.
Brief description of the drawings
Accompanying drawing 1 is present invention products configuration structural representation under MC patterns；
Accompanying drawing 2 is present invention production node mesh generation schematic diagram；
Accompanying drawing 3 is the products configuration digraph under temporal constraint of the present invention；
Accompanying drawing 4 is the multiple target Weight Decision-making flow chart of all kinds of orders of the present invention；
Accompanying drawing 5 is the flow chart of products configuration in multiple-objection optimization of the present invention.
Embodiment
Below in conjunction with the accompanying drawings to the specific reality of multi-objective optimization product configuration method of the present invention based on hybrid ant colony
The mode of applying elaborates.
1st, referring to accompanying drawing 1, the quantitative mathematic model of product order is established, object function peace treaty is provided for ant optimization algorithm
Beam condition.
Object function：
Model constrains：
In formula, K is to the production phase sum of customed product under MC patterns；K is the index in K production phase；NkFor
The production node quantity possessed in k-th of production phase；R is the production unit index in k-th of production phase；G is tkWhen
Carve, comprising product order species；H is the index of order species in set G；NmFor the product sum of every class order；J is collection
Close NmIn index；tkFor the initial time of order i k-th of production phase；For tkMoment (a, b, c) individual product
In the production cost of production node (x, y)；The unit inventory cost of node (x, y) is being produced for (a, b, c) individual product；For client is being produced to (a, b, c) individual product the expectation production time of node (x, y)；For (a, b,
C) actual production time of the individual product in production node (x, y)；It is that (a, b, c) individual product is producing node (x, y)
The additional inventory time；Π is set to the irreversible extension factor of enterprise, introduces as back order tolerance parameter, can be set to definite value
It is not covered；For tkMoment set NkThe production capacity summation that can be provided；For tkMoment product institute
The production capacity needed.
In multi-objective optimization question, the configuration process of product often relates to n factor, and its weight relationship is mainly by visitor
Decide at family.The present invention is quantified for the qualitative language between any two factor by improved H, so as to for
Many factors establish hierarchical structure, and establishing product model for system provides foundation.
Introduce the importance scale that function g (x, y) represents the factor x contrast factors y under system comprehensive evaluation.
If the property set of K customer's order is W=[w1,w2,w3,…wn], establish the Comment gathers Q=[L of products configuration1,
L2,L3,L4], define α:W → L makes review extraction, then can obtain Comprehensive Evaluation collection W of the client for Wnm。
In formula, i=1,2 ..., N；L1、L2、L3、L4For different scale parameters, andDefine L1=
1、L2=2, L3=3, L4=6.The weight sets for defining order demand collection is combined into R=[r1,r2,r3,…rn], using normalization power to
Amount：To realize that products configuration global optimum establishes weighted average type object function：
Construct the judgement rate matrix of evaluation index
If aij=f (qi,qj), solution judges rate matrix characteristic vector, constructs fuzzy relation matrix：
According to Fig. 1 adjustment flow, for rush order and the optimization operation main line of non-emergent order, by formula (5) band
Enter object function and model constraint, establish judgment matrix.Establish the excellent of non-emergent order and rush order respectively on this basis
Change object function.
If integrated cost Z1, comprehensive production time Z2Respectively with q1、q2In mapping relations, customer's order is in tkMoment, k-th
Remaining manufacturing parameter in production phase is respectively and q3…qnIn mapping relations.
In summary, first kind product order (non-emergent order), if n=5, and q3Representative products additional inventory, q4Represent
Product comprehensive quality, q5Production capacity saturation degree is represented, can be calculated by formula (6)-(9).
It is solved using with method, the weight vector after being normalized is
B11=(0.4333,0.0687,0.1070,0.2474,0.1436)
Therefore establish objective optimization generic function.
minf(W)11=0.4333w1+0.0687w2+0.1070w3+0.2474w4+0.1436w5 (10)
Second class product order (rush order)
First, using formula (10) founding mathematical models:
minf(W)21=0.4333w1+0.0687w2+0.1070w3+0.2474w4+0.1436w5 (11)
Whether judgement now meets constraints formula (4).
Meet output, be such as unsatisfactory for adjusting target component collection, establish following matrix:
It is solved using with method, the weight vector after being normalized is
B22=(0.1297,0.4637,0.1154,0.1641,0.1271)
minf(W)22=0.1297w1+0.4637w2+0.1154w3+0.1641w4+0.1271w5 (12)
3rd, the present invention uses Gridding Method, if node number variable is n, and is divided into K equal portions, so as to by n
The decision-making of variable is changed into K level decision problems.After being conducted into actual production node set, the production phase is used as according to reality
Border production node set carries out primary mesh generation.Introduce virtual production node concept on the premise of decile is unable to, and by its
Absolute forbidden node is set to, so as to which the space complexity of ant group algorithm is reduced into an order of magnitude.Mesh generation mode is such as
Shown in Fig. 2.
4th, using product order sequential as constraints, the second subseries is carried out to production node set.For complex product
Order, on the basis of division obtains each stage relations of production in first time, originated and cut with the production stage of customer requirement
Only the time is constraints, completes the digraph customization division of various product collaborative manufacturing chain.The structure of its manufacturing operation can adopt
Mode represents shown in Fig. 3.
In summary, according to the result divided for the first time and for the second time, it may be determined that in tkIt is each in moment ant group algorithm
Production node corresponding to class ant, so that it is determined that the feasible zone of algorithm, further reduce the space complexity of the algorithm.
6th, the present invention carries out products configuration using hybrid ant colony
In this algorithm, the state transition probability that element j is transferred to by element i in t ant k is：
Wherein, α is information heuristic greedy method, represents the relative importance of track, and its value is bigger, is cooperated between ant stronger；β
For expected heuristic value, the relative importance of visibility is represented, its value is bigger, and transition probability is closer to greed rule.ηij(t)
For heuristic function, its expression formula is defined as：τijIt is (t) different according to pheromone update strategy for information flow function,
Using model：
Pheromone updating rule is as follows：
τij(t+N)=(1- ρ) × τij(t)+Δτij(t),Volatility coefficient
Hybrid ant colony solves multi-objective optimization question as a kind of, is now often mutually restricted between each target
Or conflict.It can be said that on the premise of multiple-objection optimization, the quality of solution has certain relativity, and the information of ant colony
Element should also have certain otherness.When ant i is in optimizing, information content θ that companion is dischargediThere should be corresponding difference.Root
According to the established multi objective fuzzy product model of 2.2 sections, and define B → θi, setting ant XijGiven birth in production node (x, y)
The probability of production is：
Default parameters is arranged to α=1, β=1, ρ=0.2, maximum cycle 200.Determine multiple target parameter with all kinds of
The relation of ant colony legacy information element amount, determines that its new probability formula is：
A, first kind order
B, the second class order
In formula, kth class key element is to ant A in (x, y) production nodeijAttraction probability be For pheromones amount.
7th, the design process of the present invention is briefly described, referring to shown in accompanying drawing 4,5：
Step 1, the different situations according to consumer product order, determine dynamic dispatching time adjustment.
Step 2, the information type according to product order, different production task classifications is formed, construct corresponding ant class
Do not correspond to therewith.
Step 3, it is constructed for different types of ant colony by fuzzy decision scheme judge rate matrix, so that it is determined that more
The majorized function of target problem, it is determined that every weighted index.
Step 4, it is per the corresponding forbidden node of class ant setting, determines feasible zone.
Step 5, by mesh generation and Timing Constraints reduce search space, and determine each order initial time and
The planned production time.
Step 6, according to Order Type, relation of the multiple target parameter with all kinds of ant colony legacy informations element amount is determined, to determine
Select the probability of different production nodes.
Step 7, time t and cycle-index are arranged to zero, maximum cycle is set.Make first in each edge (i, j)
Beginningization information content is τij(t)=const, const are constant, and set initial initial time pheromones incrementss Δ τij=0.
Step 8, source point generate NcThe ant of batch, all kinds of ants in the batch are included per batch, if all kinds of ants
Quantity be 100.All ants new probability formula according to determined by step 6 selects path, and fresh information using roulette wheel method
Element.
Step 9, record by the ant quantity of each node in the batch, and record corresponding optimization target values.
Step 10, the renewal optimal route value of information, cycle-index Nc←Nc+ 1, while go back to step 8.
Step 11, reach maximum cycle and terminate, export.Calculate optimization aim now.Judge whether to meet model
Constraints.Such as meet and go to step 12, otherwise go to step 3.
Step 12, according to distribution condition of all kinds of ants on production node is recorded, carry out the traffic control of products configuration.
In summary, under Mass Customization Production Model, enterprise will for the flexible job efficiency requirements of production system
Improve constantly.Based on such a prospect, the present invention, for the Comprehensive Evaluation collection of order, establishes multiple-objection optimization mould for client
Type；And propose a kind of hybrid ant colony.In the present invention, algorithm is respectively provided with general for each moment of production phase
Property, the degradation mechanism of algorithm is enhanced, introduces production capacity saturation degree, eliminates the congestion problems of node；And use obscuring layer
Fractional analysis has quantified the weight vectors of multi-objective optimization question；Finally, further reduced by mesh generation and temporal constraint
Solution room, it is to solve the preferable means that multitask complex device products configuration process solves.
Under Mass Customization Production Model, client improves constantly to the complexity of customed product, bulky complex configuration number
According to unordered be processed into restrict the major constraints of enterprise's benign development.The present invention improves soft using customer demand as driving
The validity of property products configuration scheduling planning.
Described above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
Member, under the premise without departing from the principles of the invention, can also make some improvements and modifications, these improvements and modifications also should be regarded as
Protection scope of the present invention.
Claims (1)
1. a kind of multi-objective optimization product configuration method based on hybrid ant colony, comprises the following steps：
Step 1, the different situations according to consumer product order, each order is divided into multiple production phases, obtains the life of each order
Node is produced, the production moment of each order, the product of order produce the production cost at moment by quantifying the mathematics of order in order
Model determines；
Step 2, the information type according to product order, form different production task classifications, construct corresponding ant classification with
It is corresponding；
Step 3, it is constructed for different types of ant colony by fuzzy Decision Making Method judge rate matrix, so that it is determined that multiple target
The majorized function of problem, it is determined that every weighted index；
Step 4, it is per the corresponding forbidden node of class ant setting, determines feasible zone；
Step 5, by mesh generation and Timing Constraints search space is reduced, and determine initial time and the plan of each order
Production time；
Step 6, according to Order Type, relation of the multiple target parameter with all kinds of ant colony legacy informations element amount is determined, to determine to select
The probability of difference production node；
Step 7, by time t and cycle-index NcZero is arranged to, maximum cycle is set, made initial in each edge (i, j)
Change information content is τij(t)=const, const are constant, and set initial time pheromones incrementss Δ τij=0；
Step 8, source point generate NcThe ant of batch, all kinds of ants in the batch are included per batch, if the quantity of all kinds of ants
It is 100, all ants new probability formula according to determined by step 6 selects path, and fresh information element using roulette wheel method；
Step 9, record by the ant quantity of each node in the batch, and record corresponding optimization target values；
Step 10, the renewal optimal route value of information, cycle-index Nc←Nc+ 1, while go back to step 8；
Step 11, reach maximum cycle and terminate, export, calculate optimization aim now, judge whether the pact for meeting model
Beam condition, such as meet and go to step 12, otherwise go to step 3；
Step 12, according to distribution condition of all kinds of ants on production node is recorded, carry out the traffic control of products configuration；
Wherein quantify order mathematical modeling be：
Constraints is：
In formula, K is the production phase sum of order product；K is the index in K production phase；NkFor in k-th of production phase
The production node quantity possessed；R is the production unit index in k-th of production phase；G is tkThe product that moment is included is ordered
Single type；H is the index of order species in set G；NmFor the product sum of every class order；J is set NmIn index；tkFor
The initial time of order i k-th of production phase；For tkMoment (a, b, c) individual product is in production node (x, y)
Production cost；The unit inventory cost of node (x, y) is being produced for (a, b, c) individual product；For client couple
Expectation production time of (a, b, c) the individual product in production node (x, y)；Tied for (a, b, c) individual product in production
The actual production time of point (x, y)；The additional inventory time of node (x, y) is being produced for (a, b, c) individual product；
Π is set to the irreversible extension factor of enterprise, introduces as back order tolerance parameter, is set to definite value；For tkWhen
Carve set NkThe production capacity summation that can be provided；For tkProduction capacity required for moment product.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210062326.8A CN103310279B (en) | 2012-03-09 | 2012-03-09 | Multi-objective optimization product configuration method based on hybrid ant colony |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210062326.8A CN103310279B (en) | 2012-03-09 | 2012-03-09 | Multi-objective optimization product configuration method based on hybrid ant colony |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103310279A CN103310279A (en) | 2013-09-18 |
| CN103310279B true CN103310279B (en) | 2017-11-10 |
Family
ID=49135466
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210062326.8A Expired - Fee Related CN103310279B (en) | 2012-03-09 | 2012-03-09 | Multi-objective optimization product configuration method based on hybrid ant colony |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103310279B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700157B (en) * | 2015-02-03 | 2018-10-09 | 北京理工大学 | A kind of across unit work piece production method for searching path considering that transport capacity is limited |
| CN104914835A (en) * | 2015-05-22 | 2015-09-16 | 齐鲁工业大学 | Flexible job-shop scheduling multi-objective method |
| CN106786579A (en) * | 2016-12-08 | 2017-05-31 | 国网青海省电力公司 | A kind of off-network photovoltaic plant inside harmonic load index forecasting method |
| CN106779210B (en) * | 2016-12-13 | 2019-07-09 | 中国人民解放军国防科学技术大学 | Algorithm of Firepower Allocation based on ant group algorithm |
| CN107688901B (en) * | 2017-08-24 | 2021-05-11 | 北京星选科技有限公司 | Data adjusting method and device |
| CN108196518A (en) * | 2018-02-13 | 2018-06-22 | 东北大学 | Dual-proxy dynamic mixed flow operation minimization weights manufacture phase problem lower bound method for solving |
| CN110516936B (en) * | 2019-08-13 | 2022-04-08 | 武汉攀升鼎承科技有限公司 | Intelligent production line allocation system |
| CN114943489B (en) * | 2022-07-22 | 2022-10-21 | 浙江中控技术股份有限公司 | Production scheduling method and device based on improved genetic algorithm |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916404A (en) * | 2010-08-06 | 2010-12-15 | 沈阳工业大学 | Multi-factory cooperative scheduling optimization method during equipment manufacturing |
-
2012
- 2012-03-09 CN CN201210062326.8A patent/CN103310279B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916404A (en) * | 2010-08-06 | 2010-12-15 | 沈阳工业大学 | Multi-factory cooperative scheduling optimization method during equipment manufacturing |
Non-Patent Citations (5)
| Title |
|---|
| 基于混合蚁群算法的动态产品配置求解方法研究;付培红等;《中国制造业信息化》;20101231;第39卷(第23期);第13-18页 * |
| 基于蚁群算法的产品配置方法及其应用;李燚等;《计算机工程与应用》;20080930(第09期);第94-97、146页 * |
| 多态蚁群算法;徐精明等;《中国科学技术大学学报》;20050228;第35卷(第1期);第59-65页 * |
| 大规模定制企业的多项目计划模型与算法研究;吴娟;《中国博士学位论文全文数据库 经济与管理科学辑（月刊）》;20080715(第07期);第J152-19页 * |
| 大规模定制环境下供应链实施延迟生产的优化决策研究;饶凯;《中国博士学位论文全文数据库 经济与管理科学辑（月刊）》;20110715(第07期);第J152-120页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103310279A (en) | 2013-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103310279B (en) | Multi-objective optimization product configuration method based on hybrid ant colony | |
| He et al. | Towards green smart cities using Internet of Things and optimization algorithms: A systematic and bibliometric review | |
| Rathnayaka et al. | Framework to manage multiple goals in community-based energy sharing network in smart grid | |
| CN102073785B (en) | Daily gas load combination prediction method based on generalized dynamic fuzzy neural network | |
| Amjadi et al. | Estimation of electricity demand of Iran using two heuristic algorithms | |
| CN108964042A (en) | Regional power grid operating point method for optimizing scheduling based on depth Q network | |
| CN107977740A (en) | A kind of scene O＆M intelligent dispatching method | |
| CN103345657A (en) | Task scheduling method based on heredity and ant colony in cloud computing environment | |
| Zhang et al. | Multi-objective optimization of hydrothermal energy system considering economic and environmental aspects | |
| CN107748693A (en) | Group's virtual machine scheduling policy under cloud computing environment | |
| CN106230026A (en) | The power distribution network bilayer coordinated planning method containing distributed power source analyzed based on temporal characteristics | |
| CN105678407A (en) | Daily electricity consumption prediction method based on artificial neural network | |
| Reis et al. | Multi-reservoir operation planning using hybrid genetic algorithm and linear programming (GA-LP): An alternative stochastic approach | |
| CN109670650A (en) | The method for solving of Cascade Reservoirs scheduling model based on multi-objective optimization algorithm | |
| CN101944157B (en) | Biological intelligence scheduling method for simulation grid system | |
| CN102081754B (en) | Multi-expert dynamic coordination judging method and intellectualized aid decision support system | |
| Latifah et al. | Smart building: A literature review | |
| CN106228265A (en) | Based on Modified particle swarm optimization always drag phase transport project dispatching algorithm | |
| CN109214565A (en) | A kind of subregion system loading prediction technique suitable for the scheduling of bulk power grid subregion | |
| CN110400056A (en) | Cascade hydropower based on honourable space-time characterisation Optimization Scheduling and device a few days ago | |
| El Bourakadi et al. | Multi-agent system based sequential energy management strategy for Micro-Grid using optimal weighted regularized extreme learning machine and decision tree | |
| Mirjalili et al. | A comparative study of machine learning and deep learning methods for energy balance prediction in a hybrid building-renewable energy system | |
| Axhausen et al. | Including joint trips in a multi-agent transport simulation | |
| Huang et al. | A stochastic model for combined activity/destination/route choice problems | |
| CN103810642B (en) | Web service based collaborative manufacturing control method and control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171110 Termination date: 20210309 |