CN105426984B - Water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm - Google Patents
Water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm Download PDFInfo
- Publication number
- CN105426984B CN105426984B CN201510704752.0A CN201510704752A CN105426984B CN 105426984 B CN105426984 B CN 105426984B CN 201510704752 A CN201510704752 A CN 201510704752A CN 105426984 B CN105426984 B CN 105426984B
- Authority
- CN
- China
- Prior art keywords
- individual
- subgroup
- water supply
- pipe network
- network node
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/043—Optimisation of two dimensional placement, e.g. cutting of clothes or wood
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm, it include: the network topology for establishing water supply network, obtain the complexity of each pipe network node in water supply network, and hydraulic analogy and simulation of water quality are carried out to the network topology, obtain the accessibility and pollutant concentration of each pipe network node；The initialization of population of multiparticle colony optimization algorithm is carried out in master computing node, carries out global search in the MAP stage；Local search is carried out in the Reduce stage, obtains newest global optimum's individual；Judge whether the fitness of newest global optimum's individual meets the default condition of convergence, if being unsatisfactory for the default condition of convergence, the task distributing step of being transferred to continues iteration evolution.The technical problem for efficiently solving water supply network sensor arrangement optimization time length in the prior art maximizes monitoring effect (such as most fast time detection contamination accident), the security risk that prevention drinking water causes by pollution.
Description
Technical field
The present invention relates to field of environment engineering technology more particularly to a kind of water supply networks based on multiparticle colony optimization algorithm
Sensor arrangement optimization method.
Background technique
Water supply network sensor arrangement is a Large-scale Optimization Problems.Since town water supply pipe network is by thousands of pipe
The composition such as road, node, water valve, water pump, scale are very huge.By taking the urban pipe network of 10000 node sizes as an example, it is assumed that water quality
The sensor sample time is 10 minutes, and entire emulation cycle is 72 hours, then the contamination accident number that we need to emulate is
10000 Х, 72 Х 60/10, if the data of storage primary pollution event occupy 4 bytes, needing to expend calculator memory is
172.8GB, if considering current simulator and single node computer hardware, wherein each contamination accident simulation needs 4 seconds every time
Clock, then need to complete for nearly 200 days all contamination accident emulation.
It can be seen that the water supply network sensor arrangement optimization time is long at present.
Summary of the invention
The embodiment of the present invention is by providing a kind of water supply network sensor arrangement optimization based on multiparticle colony optimization algorithm
Method solves the technical problem of water supply network sensor arrangement optimization time length in the prior art.
A kind of water supply network sensor arrangement optimization side based on multiparticle colony optimization algorithm provided in an embodiment of the present invention
Method, which comprises the steps of:
The network topology for establishing water supply network obtains the complexity of each pipe network node in the water supply network, and
Hydraulic analogy is carried out to the network topology and simulation of water quality obtains the accessibility and pollutant of each pipe network node
Concentration；
The initialization of population of multiparticle colony optimization algorithm is carried out in master computing node, wherein every in each population
The code length of individual is the total number of the pipe network node；
Task distributing step: be included in the MAP stage by each subgroup be mapped to Mapper calculate node carry out it is global
Search；
It is dense in the complexity of the Reduce stage based on each pipe network node, the accessibility and the pollutant
At least one of degree guidance intelligent single-particle carries out local search, obtains newest global optimum's individual；
Judge whether the fitness of newest global optimum's individual meets the default condition of convergence, if be unsatisfactory for described pre-
If the condition of convergence, then it is transferred to the task distributing step and continues iteration evolution, meet the default condition of convergence or reach
Terminate iteration when setting greatest iteration evolution number to develop and export optimal solution, so that it is determined that the position of sensor.
Preferably, the initialization of population that multiparticle colony optimization algorithm is carried out in master computing node, specifically includes:
M population is initialized, each population includes individual；
The M population is divided into subgroup to be assigned on cloud computing platform, number and the institute of Mapper calculate node are set
State the number of Reducer calculate node.
Preferably, described that each subgroup is mapped to a Mapper calculate node progress global search, packet in the MAP stage
It includes:
Fitness calculating is carried out to each subgroup；
Location updating is carried out to each subgroup according to iterative formula and speed updates.
Preferably, the complexity in the Reduce stage based on each pipe network node, the accessibility and
At least one of described pollutant concentration guides intelligent single-particle to carry out local search, obtains newest global optimum's individual, packet
It includes:
According to the individual number in each subgroup, the adaptive value group of each subgroup is obtained；
The adaptive value group of each subgroup is ranked up respectively；
It is dense in the complexity of the Reduce stage based on each pipe network node, the accessibility and the pollutant
One in degree guides the local search of the intelligent single-particle, find each subgroup local optimum individual and
Each individual corresponding adaptive value of the local optimum；
The local optimum individual is ranked up according to each local optimum individual corresponding adaptive value, to obtain
Newest global optimum's individual.
Preferably, it is described be transferred to the task distributing step continue iteration evolution, comprising:
Newest global optimum's individual is sent to the controller, by the controller by the newest optimum individual with
Individual in each subgroup carries out random replacement, obtains next-generation population；
It is transferred to the task distributing step based on the next-generation population to carry out continuing iteration evolution, the number of iterations increases by 1.
Preferably, the complexity in the Reduce stage based on each pipe network node, the accessibility and
At least one of described pollutant concentration guides intelligent single-particle to carry out local search, obtains newest global optimum's individual, packet
It includes:
The complexity of each pipe network node and the probability match for placing the sensor；And/or
The accessibility of each pipe network node and the probability match for placing the sensor；And/or
The dye object concentration of each pipe network node and the probability match for placing the sensor
The one or more technical solutions provided in the embodiment of the present invention, have at least the following technical effects or advantages:
The initialization of population is carried out in host node since the embodiment of the present invention is used；Then the Map stage uses more
Subgroup optimization algorithm carries out global search, and carries out local search using intelligent single-particle in the Reduce stage, and by whether full
The sufficient condition of convergence carrys out control loop evolution iteration, and the better position of sensor is placed until determining.Map- is based on to this
The parallel calculating method of Reduce model belongs to intelligence computation, and not only accuracy is high, but also fast speed, can efficiently determine and put
The position of sensor is set, and then efficiently solves the technical problem of water supply network sensor arrangement optimization time length in the prior art
Maximize monitoring effect (for example the most fast time detects contamination accident), the security risk that prevention drinking water causes by pollution.
Further, in order to solve the problems, such as that storage and simulation calculation amount are too big, we utilize cloud computing technology, devise and are based on
Distributed MA (cultural gene algorithm, Memetic Algorithm) calculation method of cloud platform, can effectively promote speed-up ratio, save
Count roughly evaluation time.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is the water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm in the embodiment of the present invention
Flow chart；
Fig. 2 is the realization block diagram that parallel Memetic algorithm is realized in the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Referring to fig. 1 and fig. 2, a kind of water supply network based on multiparticle colony optimization algorithm provided in an embodiment of the present invention
Sensor arrangement optimization method, includes the following steps:
S101, the network topology for establishing water supply network obtain the complexity of each pipe network node in water supply network, and
Hydraulic analogy and simulation of water quality are carried out to network topology, obtain the accessibility and pollutant concentration of each pipe network node.
Specifically, can use EPANET2.0 (loop approach software) draws network topology, to water supply network topology
Structure and pollutant phagocytic process are emulated.Specifically, when simulating pollution object is invaded from some pipe network node of water supply network,
It can use EPANET 2.0 and carry out waterpower simulation of water quality, water quality diffusion simulations are carried out to pollutant again on this basis.Specifically
Simulation process can be such that calls " Openfiles " function to open water supply network file first, utilizes " netsize " function meter
The scale of water supply network is calculated, calling " allocdata " function is water supply network data storage allocation, then calls " ENsolveH "
Function carries out day part water force, is calculated using the water quality that " ENsolvQ " function carries out day part, is finally called
The report of " ENreport " function creation calls " Enclose " releasing memory and closes file.
Certainly, it is not limited in the specific implementation process using above-mentioned EPANET2.0, other highest versions can also be used
Loop approach software or other similar software.
By the above-mentioned drafting to network topology and hydraulic analogy and simulation of water quality, in Map (mapping) stage benefit
When with EPANET emulator to hydraulic analogy and simulation of water quality, that is, the Map stage is the stage most time-consuming in algorithm, so adopting
Accelerate to solve with cloud computing, in Reduce (reduction) stage, influence matrix (Impact Matrix) is stored in distributed data
In library (Hbase), so that the adaptive value calculating for multiparticle colony optimization algorithm provides the foundation.
S102, the initialization of population that multiparticle colony optimization algorithm is carried out in master computing node, wherein every in each population
The code length of individual is the total number of pipe network node.
Specifically, initializing M population first, each population includes individual, and M population is assigned to cloud computing and is put down
On platform, the number of Mapper calculate node and the number of Reducer calculate node are set.20 are arranged in the specific implementation process
Worker process provides support.For example, the number that population can be set is 1000, each population includes 20 individuals.And
Optimal solution, the global optimum's individual, iteration evolution number of initial population are saved by controller.
Then execute task distributing step: being included in the MAP stage by each subgroup is mapped to a Mapper calculate node
Carry out global search.
S103, task distributing step: being included in the MAP stage by each subgroup is mapped to a Mapper calculate node, from
And it is divided into multiple subgroups and carries out parallel search.
Specifically, carrying out fitness calculating to each subgroup in the Map stage；And according to iterative formula to each subgroup into
Row location updating and speed update.Specifically, the prior art can be referred to by carrying out location updating and speed update, in order to illustrate book
Brief introduction, do not repeat herein.
S104, in the Reduce stage based in complexity, accessibility and pollutant concentration based on each pipe network node
At least one guidance intelligent single-particle carries out local search, obtains newest global optimum's individual.
Specifically, the Reduce stage is divided into 1stReduce and 2ndReduce, wherein in 1st Reduce stage, first root
According to the individual number in each subgroup, the adaptive value group of each subgroup is obtained.Then to the adaptive value component to each subgroup
It is not ranked up；One in complexity, accessibility again based on each pipe network node and pollutant concentration is to intelligent single-particle
Local search guide, to find local optimum individual and the corresponding adaptation of each local optimum individual of each subgroup
Value；Then in the 2ndReduce stage, according to the corresponding adaptive value of each local optimum individual to the local optimum individual found into
Row sequence, is sent to controller to obtain newest global optimum's individual.
Specifically, dense using the accessibility of pipe network node, complexity and pollutant when learning algorithm local by intelligence
Degree forms expertise rule and guides to the direction of local search.The complexity of each pipe network node and placement sensor
Probability match；And/or the probability match of the accessibility of each pipe network node and placement sensor；And/or each pipe network node
It contaminates object concentration and places the probability match of sensor.
Below to the accessibility of pipe network node, complexity and pollutant is dense is described respectively:
The accessibility of pipe network node refers to number of the water body after other pipe network nodes flowed out from the pipe network node, can
Up to higher pipe network node placement sensor is spent, then monitoring efficiency is higher.In specific implementation, the data emulated using EPANET
The water age of entire water supply network is recorded, the water flow percentage come from known pipe network node is tracked.For each pipe of water supply network
Net node xi, calculate from xiThe number n for flowing through other pipe network nodes, is denoted as xi n, the accessibility of the biggish pipe network node of n value
It is high.Accessibility rule are as follows: the accessibility of certain pipe network node is higher, in the Probability p (x of its place sensorsi) bigger.This
Rule can markaccessibility。
The complexity of pipe network node is derived from the attribute of graph theory interior joint degree, and other pipe network nodes are connected in water supply network and are got over
More pipe network node locations places sensor, large-scale pollutant is more readily detected, to reduce the cost of sensor.
Pollutant concentration refers to that pollutant is spread after a period of time, each pipe network section after any contamination accident occurs
The pollutant concentration of point is different.It is, in general, that the higher pipe network node of concentration will be detected by a sensor the shortest time,
Pollutant is easiest to the pipe network node being diffused into and places sensor, this rule can shorten the monitoring time of pollutant.
Specifically, just directly passing through the network topology of water supply network after the network topology for establishing water supply network
Can directly count the complexity of each pipe network node, and accessibility, the pollutant of each pipe network node need EPANET to
The invasion of pipe network pollutant carries out being counted to obtain after simulation obtains data.
After complexity, accessibility and the pollutant concentration of each pipe network node is calculated, guided using probabilistic method
Sensor arrangement, such as the bigger probability for placing sensor of accessibility of certain pipe network node are higher, for another example certain pipe network node
Complexity it is bigger place sensor probability it is higher.Specific implementation can be using the method for roulette wheel selection.
S105, judge whether the fitness of newest global optimum's individual meets the default condition of convergence, if being unsatisfactory for presetting
The condition of convergence is then transferred to task distributing step and continues iteration evolution, and satisfaction presets the condition of convergence or reaches setting maximum and changes
Terminate iteration when for evolution number to develop and export optimal solution, so that it is determined that the position of sensor.
Specifically, the default condition of convergence is default convergence threshold, the default convergence threshold is according to actual set.
Specifically, the task distributing step of being transferred to continues iteration evolution, comprising: obtain previous step S104 newest
Global optimum's individual is sent to controller, and the individual in newest optimum individual and each subgroup is carried out random replacement by controller,
Obtain next-generation population；Task distributing step is transferred to based on the obtained next-generation population to carry out continuing iteration evolution, iteration
Number increases by 1.
By the one or more technical solutions provided in the embodiments of the present invention, at least have the following technical effect that or
Advantage:
The initialization of population is carried out in host node since the embodiment of the present invention is used；Then the Map stage uses more
Subgroup optimization algorithm carries out global search, and carries out local search using intelligent single-particle in the Reduce stage, and by whether full
The sufficient condition of convergence carrys out control loop evolution iteration, and the better position of sensor is placed until determining.Map- is based on to this
The parallel calculating method of Reduce model belongs to intelligence computation, and not only accuracy is high, but also fast speed, can efficiently determine and put
The position of sensor is set, and then the technology for efficiently solving water supply network sensor arrangement optimization time length in the prior art is asked
Topic maximizes monitoring effect (for example the most fast time detects contamination accident), the safety wind that prevention drinking water causes by pollution
Danger.
Further, in order to solve the problems, such as that storage and simulation calculation amount are too big, we utilize cloud computing technology, devise and are based on
The distributed Memetic calculation method of cloud platform can effectively promote speed-up ratio, save and calculate the time.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (4)
1. a kind of water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm, which is characterized in that including such as
Lower step:
The network topology for establishing water supply network obtains the complexity of each pipe network node in the water supply network, and to institute
It states network topology progress hydraulic analogy and simulation of water quality obtains the accessibility and pollutant concentration of each pipe network node；
M population is initialized, each population includes individual, the M population is divided into subgroup is assigned to cloud computing and put down
On platform, the number of Mapper calculate node and the number of Reducer calculate node are set, wherein every in each population
The code length of individual is the total number of the pipe network node；
Task distributing step: being included in the MAP stage is mapped to Mapper calculate node for each subgroup and carries out global search；
In the complexity, the accessibility and the pollutant concentration of the Reduce stage based on each pipe network node
At least one guidance intelligent single-particle carry out local search, obtain newest global optimum individual；Wherein, the Reduce stage is divided into
1stReduce and 2ndReduce, wherein in the 1st Reduce stage, numbered, obtained according to the individual in each subgroup first
To the adaptive value group of each subgroup；Then the adaptive value group to each subgroup is ranked up respectively；It is based on each pipe network section again
One in complexity, accessibility and pollutant concentration put guides the local search of intelligent single-particle, to find
The local optimum individual and the corresponding adaptive value of each local optimum individual of each subgroup；Then in the 2ndReduce stage, according to
The individual corresponding adaptive value of each local optimum is ranked up the local optimum individual found, to obtain newest global optimum
Body is sent to controller；
Judge whether the fitness of newest global optimum's individual meets the default condition of convergence, if being unsatisfactory for the default receipts
Condition is held back, then is transferred to the task distributing step and continues iteration evolution, meet the default condition of convergence or reach setting
Terminate iteration when greatest iteration evolution number to develop and export optimal solution, so that it is determined that the position of sensor.
2. the water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm as described in claim 1, special
Sign is, described that each subgroup is mapped to a Mapper calculate node progress global search in the MAP stage, comprising:
Fitness calculating is carried out to each subgroup；
Location updating is carried out to each subgroup according to iterative formula and speed updates.
3. the water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm as claimed in claim 2, special
Sign is, described in the complexity, the accessibility and the pollution of the Reduce stage based on each pipe network node
At least one of object concentration guides intelligent single-particle to carry out local search, obtains newest global optimum's individual, comprising:
According to the individual number in each subgroup, the adaptive value group of each subgroup is obtained；
The adaptive value group of each subgroup is ranked up respectively；
In the complexity, the accessibility and the pollutant concentration of the Reduce stage based on each pipe network node
One the local search of the intelligent single-particle is guided, find the local optimum individual of each subgroup and each
The individual corresponding adaptive value of the local optimum；
The local optimum individual is ranked up according to each local optimum individual corresponding adaptive value, it is described to obtain
Newest global optimum's individual.
4. the water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm as described in claim 1, special
Sign is, described in the complexity, the accessibility and the pollution of the Reduce stage based on each pipe network node
At least one of object concentration guides intelligent single-particle to carry out local search, obtains newest global optimum's individual, comprising:
The complexity of each pipe network node and the probability match for placing the sensor；And/or
The accessibility of each pipe network node and the probability match for placing the sensor；And/or
The dye object concentration of each pipe network node and the probability match for placing the sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510704752.0A CN105426984B (en) | 2015-10-26 | 2015-10-26 | Water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510704752.0A CN105426984B (en) | 2015-10-26 | 2015-10-26 | Water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105426984A CN105426984A (en) | 2016-03-23 |
| CN105426984B true CN105426984B (en) | 2019-08-20 |
Family
ID=55505178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510704752.0A Expired - Fee Related CN105426984B (en) | 2015-10-26 | 2015-10-26 | Water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105426984B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3083553B1 (en) * | 2018-07-09 | 2023-05-19 | Suez Groupe | IMPROVED PLACEMENT OF SENSORS OF PHYSICO-CHEMICAL PARAMETERS IN A FLUID |
| CN108875937A (en) * | 2018-07-27 | 2018-11-23 | 苏州市自来水有限公司 | The purging method in each region of water supply network based on draw-off point preferred arrangement |
| CN110211641A (en) * | 2019-06-13 | 2019-09-06 | 纪震 | A kind of clustering method of gene expression data and terminal device |
| CN111832793A (en) * | 2020-01-10 | 2020-10-27 | 吉林建筑大学 | Pollution source positioning method and system based on sudden pollution event of pipe network |
| CN111832792B (en) * | 2020-01-10 | 2022-05-06 | 吉林建筑大学 | Method and system for arranging pipe network water quality monitoring points based on sudden pollution events |
| CN113139584B (en) * | 2021-03-29 | 2022-04-22 | 长江水利委员会长江科学院 | Sensor optimal arrangement method for water supply pipe network pollutant invasion point identification |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101448267A (en) * | 2008-12-31 | 2009-06-03 | 中山大学 | Wireless sensor network node coverage optimization method based on particle swarm algorithm |
| CN103945395A (en) * | 2014-02-27 | 2014-07-23 | 北京理工大学 | Particle-swarm-based rapid optimization deployment method for wireless network sensors |
| US9122993B2 (en) * | 2013-01-30 | 2015-09-01 | Harris Corporation | Parallel multi-layer cognitive network optimization |
-
2015
- 2015-10-26 CN CN201510704752.0A patent/CN105426984B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101448267A (en) * | 2008-12-31 | 2009-06-03 | 中山大学 | Wireless sensor network node coverage optimization method based on particle swarm algorithm |
| US9122993B2 (en) * | 2013-01-30 | 2015-09-01 | Harris Corporation | Parallel multi-layer cognitive network optimization |
| CN103945395A (en) * | 2014-02-27 | 2014-07-23 | 北京理工大学 | Particle-swarm-based rapid optimization deployment method for wireless network sensors |
Non-Patent Citations (2)
| Title |
|---|
| Parallel K-PSO Based on MapReduce;junjun Wang等;《2012 IEEE 14th International Conference on Communication Technology》;20121111;第151-156页 |
| 突发性污染情况下给水管网传感器优化选址;张土乔等;《哈尔滨工业大学学报》;20091231;第1-6页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105426984A (en) | 2016-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105426984B (en) | Water supply network sensor arrangement optimization method based on multiparticle colony optimization algorithm | |
| Hassanzadeh et al. | Managing water in complex systems: An integrated water resources model for Saskatchewan, Canada | |
| Sheldon et al. | Maximizing the spread of cascades using network design | |
| Li et al. | A neural network based distributed intrusion detection system on cloud platform | |
| CN106875004B (en) | Composite mode neuronal messages processing method and system | |
| Lee et al. | Decision support system for mass dispensing of medications for infectious disease outbreaks and bioterrorist attacks | |
| CN105184368B (en) | A kind of distribution extreme learning machine optimization integrated framework method system and method | |
| CN104063261A (en) | Multi-objective optimization virtual machine placing method under cloud environment | |
| CN103699944A (en) | Wind and photovoltaic generation power prediction system with multiple prediction modes | |
| CN103365727A (en) | Host load forecasting method in cloud computing environment | |
| CN103294595B (en) | A kind of software repair based on genetic algorithm | |
| CN104331749A (en) | AGV optimization scheduling method based on simulated annealing particle swarm | |
| Nkwonta et al. | A review on water resources yield model | |
| CN107506861A (en) | A kind of short-term wind speed forecasting method, apparatus and system | |
| Moreno et al. | Biocomplexity of deforestation in the Caparo tropical forest reserve in Venezuela: an integrated multi-agent and cellular automata model | |
| CN109670260A (en) | A kind of mountain fire sprawling Area Prediction method, apparatus and equipment | |
| Nicol et al. | Adaptive management of migratory birds under sea level rise | |
| Shourian et al. | Interbasin water transfer capacity design by two approaches of simulation-optimization and multicriteria decision making | |
| Moghaddasi et al. | A trade-off analysis of adaptive and non-adaptive future optimized rule curves based on simulation algorithm and hedging rules | |
| D’Ercole et al. | An integrated modeling approach to optimize the management of a water distribution system: improving the sustainability while dealing with water loss, energy consumption and environmental impacts | |
| Kim et al. | A memetic approach for improving minimum cost of economic load dispatch problems | |
| CN106161599A (en) | A kind of method reducing cloud storage overall overhead when there is data dependence relation | |
| Dinu et al. | Self-adapting fitness evaluation times for on-line evolution of simulated robots | |
| CN116663406A (en) | Deep learning compiler impulse neural network operator processing method, system and medium | |
| CN112101608A (en) | Offshore wind farm site selection method and device |
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 |
Granted publication date: 20190820 Termination date: 20201026 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |