CN108197759A - For the method and system of offshore oilfield group micro-capacitance sensor short-term electric load prediction - Google Patents
For the method and system of offshore oilfield group micro-capacitance sensor short-term electric load prediction Download PDFInfo
- Publication number
- CN108197759A CN108197759A CN201810088180.1A CN201810088180A CN108197759A CN 108197759 A CN108197759 A CN 108197759A CN 201810088180 A CN201810088180 A CN 201810088180A CN 108197759 A CN108197759 A CN 108197759A
- Authority
- CN
- China
- Prior art keywords
- dragonfly
- individual
- dragonfly individual
- ida
- update
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 241000238633 Odonata Species 0.000 claims abstract description 115
- 238000012706 support-vector machine Methods 0.000 claims abstract description 13
- 230000003044 adaptive effect Effects 0.000 claims abstract description 10
- 230000006978 adaptation Effects 0.000 claims abstract description 9
- 230000003542 behavioural effect Effects 0.000 claims abstract description 6
- 238000004321 preservation Methods 0.000 claims abstract description 4
- 230000006399 behavior Effects 0.000 claims description 23
- 238000005295 random walk Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 2
- 238000000926 separation method Methods 0.000 claims 1
- 230000006872 improvement Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000005611 electricity Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
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"
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of method and systems for offshore oilfield group micro-capacitance sensor short-term electric load prediction, and ability of searching optimum is strong, possesses higher precision of prediction and computational efficiency.This method includes：The respective upper limit value and lower limit value of punishment parameter C and nuclear parameter σ of support vector machines is set；Setting improves the dimension of the position vector of dragonfly algorithm IDA, maximum iteration, the quantity of dragonfly individual；Initialize the behavioral parameters of dragonfly individual；Calculate the adaptive value that dragonfly individual is current in IDA；By two generation dragonfly individuals by Map Sort, calculate and preserve corresponding maximum adaptation value；Update the position of food and natural enemy in IDA；Update the behavior of dragonfly individual in IDA；Update the position of dragonfly individual in IDA；When reaching maximum iteration, the position of the dragonfly individual according to corresponding to the maximum adaptation value of preservation is set the punishment parameter C of SVM and nuclear parameter σ, and offshore oilfield group micro-capacitance sensor short-term electric load is predicted based on SVM structure prediction models.
Description
Technical field
The present invention relates to power-system short-term load forecasting technical fields more particularly to one kind to be used for the micro- electricity of offshore oilfield group
The method and system of net short-term electric load prediction.
Background technology
Power-system short-term load forecasting is often referred to according to historical load data, other shadows such as comprehensive weather, season, temperature
The process that the factor of sound is done to forecast to following one day to one week electricity needs is the foundation of electric dispatching department distribution electric energy, directly
Affect power system security reliability service.Offshore oilfield group micro-capacitance sensor is gradually developed by Ship Electrical Power System, is born
It is mostly electric submersible pump to carry, and load variations are relatively large.Platform is powered by diesel engine, Gas Turbine Generating Units, and power generation capacity is very
It is limited.Therefore, it is even more important for offshore oilfield group micro-capacitance sensor to improve short-term load forecasting precision.
It is common in traditional short-term load forecasting method to have similar day, linear regression analysis, gray theory etc..These are passed
Forecasting Methodology of uniting is simple in structure, Technical comparing is ripe, but model is all based on greatly linear programming, it is difficult to predict the micro- electricity of offshore oilfield group
It nets the factors such as non-linear, meteorological and fluctuates larger load sequence.In recent years, intellectualized technology is fast-developing, such as：Expert system,
Fuzzy reasoning, neural network etc..For the uncertain factor of short term, fuzzy theory is with the obvious advantage.But offshore oilfield group
The time variation feature of micro-capacitance sensor short term so that fuzzy reasoning precision of prediction is unsatisfactory.
Artificial neural network (BPNN) has stronger robustness, can carry out unlimited approach and learning ability to non-linear
By force, but convergence rate is slow, is influenced the opposite discounting of precision of prediction, while may also restrain by initial connection weights, threshold parameter
To local minimum points.Support vector machines (Support Vector Machine, SVM) method is sent out on the basis of statistical theory
A kind of novel machine learning method that exhibition is got up, robustness is preferable, can effectively avoid being absorbed in local optimum and overcome dimension
The advantages that disaster.But in SVM prediction modeling process, punishment parameter C and nuclear parameter σ are generally chosen using trial and error procedure, are caused pre-
It surveys trouble and error is larger.There is scholar to propose a series of method that improvement support vector machines parameters are chosen.Such as：Pass through population
Algorithm improvement support vector machines is used for short-term load forecasting；It is pre- that short term is carried out using genetic algorithm optimization support vector machines
It surveys.By the addition of these optimization algorithms, so that the parameter of SVM is chosen more rapidly, accurately, while load prediction is improved
Precision.However, above-mentioned improvement SVM algorithm is relative complex, modeling speed is slow.During optimal iteration selection, SVM parameters are difficult to reach
To global optimum.
Invention content
An object of the present invention at least that, for how to overcome the above-mentioned problems of the prior art, provide one kind
For the method and system of offshore oilfield group micro-capacitance sensor short-term electric load prediction, ability of searching optimum is strong, possesses higher
Precision of prediction and computational efficiency.
To achieve these goals, the technical solution adopted by the present invention includes following aspects.
A kind of method for offshore oilfield group micro-capacitance sensor short-term electric load prediction, including：
The respective upper limit value and lower limit value of punishment parameter C and nuclear parameter σ of support vector machines is set；Setting improves dragonfly algorithm
The dimension of the position vector of IDA, maximum iteration, the quantity of dragonfly individual；Initialize the behavioral parameters of dragonfly individual；It calculates
The current adaptive value of dragonfly individual in IDA；By two generation dragonfly individuals by Map Sort, calculate and preserve corresponding maximum adaptation
Value；Update the position of food and natural enemy in IDA；Update the behavior of dragonfly individual in IDA；Update the position of dragonfly individual in IDA；
When not up to maximum iteration, back to starting the step of calculating the current adaptive value of dragonfly individual in IDA
It performs；When reaching maximum iteration, the position of the dragonfly individual according to corresponding to the maximum adaptation value of preservation sets SVM
Punishment parameter C and nuclear parameter σ, and based on SVM structure prediction model to offshore oilfield group micro-capacitance sensor short-term electric load carry out
Prediction.
Preferably, the behavioral parameters of the initialization dragonfly individual include：The initial solution of random generation dragonfly body position
X0；Random generation step-length vector Δ Xt；The alloted proportions s of random generation dragonfly individual behavior, is aligned weight a, cohesive force weight c,
Food attraction weight f and keep away enemy weight e；Random generation adjacent radius r and inertia weight w.
Preferably, the method includes：The punishment parameter C of SVM and core is set to join according to the current location of dragonfly individual
The classification accuracy of corresponding SVM is set as the current adaptive value of dragonfly individual by number σ.
Preferably, the method includes：According to the current location of dragonfly individual and food, the initial position of natural enemy, profit
The position X of food is calculated with Euclidean distance formula+With the position X of natural enemy-。
Preferably, the behavior of dragonfly individual includes in the update IDA：According to formulaTo update i-th
The separating behavior of a dragonfly individual, wherein, positions of the X for current dragonfly individual, XjFor the position of j-th of adjacent dragonfly individual, N
Quantity for adjacent dragonfly individual；According to formulaUpdate the alignment behavior of i-th of dragonfly individual, wherein, Vj
Represent the flying speed of j-th of adjacent dragonfly individual；According to formulaTo update i-th dragonfly individual
Cohesion behavior；According to formula Fi=X+- X updates the food attraction behavior of i-th of dragonfly individual；According to formula Ei=X--X
Enemy's behavior is kept away update i-th dragonfly individual.
Preferably, the position of dragonfly individual includes in the update IDA：When at least one individual neighbouring dragonfly of dragonfly
When individual, formula Δ X is utilizedt+1=(sSi+aAi+cCi+fFi+eEi)+wΔXtTo update step-length vector, and utilize formula Xt+1=
Xt+ΔXt+1To update the position of dragonfly individual；
When the dragonfly individual not closed on, formula X is utilizedt+1=Xt+Lévy(d)×XtTo update the position of dragonfly individual
Put, wherein, L é vy are random walk function, represent in the dimensional extent of position vector d randomly to any direction advance with
The distance of captain's degree.
Preferably, the random walk functionWherein, r1、r2For (0,1] in the range of
Random number,Γ (x)=(x-1)！, β is the constant equal to 1.5.
Preferably, the dimension d of the position vector is 6.
Preferably, the maximum iteration Mit is 150, and the quantity of dragonfly individual is 40.
A kind of system for offshore oilfield group micro-capacitance sensor short-term electric load prediction, including：Display, input and output
It equipment, at least one processor, the memory being connect at least one processor communication and is set for the power supply of power supply
It is standby；
Wherein, the display is used to show prediction result；The input-output equipment is used for input initialization parameter；Institute
It states memory and is stored with the instruction that can be performed by least one processor, described instruction is held by least one processor
Row, so that at least one processor is able to carry out the method.
In conclusion by adopting the above-described technical solution, the present invention at least has the advantages that：
(1) by being based on improving dragonfly algorithm and Support Vector Machines Optimized parameter progress short-term load forecasting, algorithm steps
Succinctly, ability of searching optimum is strong, possesses higher precision of prediction computational efficiency.
(2) this method and system are applied to offshore oilfield group micro-capacitance sensor, and relatively land network load fluctuation is big, there are no rules
It can follow, still be able to Accurate Prediction.
(3) this short-term load forecasting this method proposed by the invention and system prediction is accurate and calculating speed is fast, just
In oil field electric dispatching department reasonable distribution electric energy, the safe and orderly production of offshore oilfield group has been ensured.
Description of the drawings
Fig. 1 is the stream of the method for offshore oilfield group micro-capacitance sensor short-term electric load prediction according to embodiments of the present invention
Cheng Tu.
Fig. 2 is the knot of the system for offshore oilfield group micro-capacitance sensor short-term electric load prediction according to embodiments of the present invention
Structure schematic diagram.
Specific embodiment
With reference to the accompanying drawings and embodiments, the present invention will be described in further detail, so that the purpose of the present invention, technology
Scheme and advantage are more clearly understood.It should be appreciated that specific embodiment described herein is only to explain the present invention, and do not have to
It is of the invention in limiting.
Fig. 1 shows the side for offshore oilfield group micro-capacitance sensor short-term electric load prediction according to embodiments of the present invention
Method.The method of the embodiment includes the following steps：
Step 101：Initiation parameter
Specifically, for SVM, need to set punishment parameter C and the respective upper limit value and lower limit values of nuclear parameter σ (for example, C it is upper,
Lower limiting value is respectively 0,100；σ upper limit value and lower limit values are respectively 0,100)；Further, the present invention is introduced in prediction model and is improved
Dragonfly algorithm (Improvement Dragonfly Algorithm, IDA) for IDA, needs installation position vector (to wait to ask
Solution problem, such as the size of electric load, Annual distribution etc. in a short time) dimension d (for example, 6), maximum iteration Mit (examples
Such as, 150), the quantity (for example, 40) of dragonfly individual.
Step 102：Initialize dragonfly behavioral parameters
Such as the current solution X by dragonfly body positiontIt is set as the punishment parameter C of SVM to be optimized and nuclear parameter σ groups
It closes, generates the initial solution X of dragonfly body position at random in the range of [0,1]0, generation step-length vector Δ Xt=0.01；(0,1]
In the range of generate dragonfly individual at random the weight of 5 kinds of behaviors (including alloted proportions s, be aligned weight a, cohesive force weight c, food
Object attraction weight f keeps away enemy's weight e)；(0,1] in the range of generate adjacent radius r and inertia weight w at random.
Step 103：The current adaptive value of dragonfly individual in computed improved dragonfly algorithm
For example, can the punishment parameter C of SVM and core be set according to the current solution (i.e. current location) of dragonfly body position
The classification accuracy of corresponding SVM is set as the current adaptive value of dragonfly individual by parameter σ.
Step 104：Up and down for dragonfly optimal sequencing
Previous generation (t-1) is associated with this generation (t) dragonfly, by two generation dragonfly individuals by Map Sort, calculate and preserve
Corresponding maximum adaptation value.
Step 105：More new food, natural enemy position
Specifically, according to the current location of dragonfly individual and food, natural enemy initial position (for example, relative to dragonfly
The initial position of individual is randomly provided), utilize the position X of Euclidean distance formula calculating food+With the position X of natural enemy-。
Step 106：Update dragonfly behavior
It specifically, can be according to formulaUpdate the separating behavior of i-th of dragonfly individual, wherein, X
For the position of current dragonfly individual, XjFor the position of j-th of adjacent dragonfly individual, N is the quantity of adjacent dragonfly individual；According to public affairs
FormulaUpdate the alignment behavior of i-th of dragonfly individual, wherein, VjRepresent the flight of j-th of adjacent dragonfly individual
Speed；According to formulaTo update the cohesion behavior of i-th of dragonfly individual；According to formula Fi=X+- X comes more
The food attraction behavior of new i-th of dragonfly individual；According to formula Ei=X-- X keeps away enemy's behavior update i-th dragonfly individual.
Step 107：Update dragonfly position
When at least one neighbouring dragonfly individual of dragonfly individual, formula Δ X is utilizedt+1=(sSi+aAi+cCi+fFi+
eEi)+wΔXtTo update step-length vector, and utilize formula Xt+1=Xt+ΔXt+1To update the position of dragonfly individual；
When the dragonfly individual not closed on, formula X is utilizedt+1=Xt+Lévy(d)×XtTo update the position of dragonfly individual
Put, wherein, L é vy are random walk function, represent in the dimensional extent of position vector d randomly to any direction advance with
The distance of captain's degree.For example,Wherein, r1、r2For (0,1] in the range of random number,Γ (x)=(x-1)！, β is constant (such as 1.5).
As not up to maximum iteration Mit, return to step 103 recalculates dragonfly individual in improvement dragonfly algorithm and works as
Preceding adaptive value and its subsequent step.
When reaching maximum iteration Mit, step 109 is performed, according to the dragonfly corresponding to the maximum adaptation value of preservation
The position of individual, sets the punishment parameter C of SVM and nuclear parameter σ, and based on SVM build prediction model to offshore oilfield group micro- electricity
Net short-term electric load is predicted.
Fig. 2 shows the systems for offshore oilfield group micro-capacitance sensor short-term electric load prediction according to embodiments of the present invention
Structure diagram.It includes：Display 601, input-output equipment 602, at least one processor 603 and described at least one
The memory 604 and the power-supply device 605 for power supply that a processor 603 communicates to connect；
Wherein, display 601 is used to show prediction result；Input-output equipment 602 is used for input initialization parameter；It is described
Memory 604 is stored with the instruction that can be performed by least one processor 603, and described instruction is by least one processing
Device 603 performs, so that the method that at least one processor 603 is able to carry out aforementioned any embodiment.
The present invention also provides non-transitory computer-readable mediums, and including the instruction compiled on it, described instruction is used for
Perform the embodiment of aforementioned either method.Computer-readable medium may include any medium, can be read by signal processing apparatus
Go out the middle code for performing and being stored thereon, such as floppy disk, CD, tape or hard disk drive.Such code can include object
Code, source code and/or binary code.The code is usually number, is generally used for handling by traditional numerical data
Processor (such as microprocessor, microcontroller or logic circuit, such as programmable gate array, programmable logic circuit/device or special collection
Into circuit [ASIC]).
It should be appreciated that in various embodiments of the present invention, the size of the serial number of above-mentioned each process is not meant to perform
The priority of sequence, the execution sequence of each process should be determined with its function and internal logic, without the reality of the reply embodiment of the present invention
It applies process and forms any restriction.
It will be appreciated by those skilled in the art that：Program can be passed through by realizing all or part of step of above method embodiment
Relevant hardware is instructed to complete, aforementioned program can be stored in computer read/write memory medium, which is performing
When, perform step including the steps of the foregoing method embodiments；And aforementioned storage medium includes：Movable storage device, read-only memory
The various media that can store program code such as (Read Only Memory, ROM), magnetic disc or CD.
When the above-mentioned integrated unit of the present invention is realized in the form of SFU software functional unit and be independent product sell or
In use, it can also be stored in a computer read/write memory medium.Based on such understanding, the skill of the embodiment of the present invention
Art scheme substantially in other words can be embodied the part that the prior art contributes in the form of software product, the calculating
Machine software product is stored in a storage medium, is used including some instructions so that a computer equipment (can be personal
Computer, server or network equipment etc.) perform all or part of each embodiment the method for the present invention.It is and aforementioned
Storage medium include：The various media that can store program code such as movable storage device, ROM, magnetic disc or CD.
It is short-term based on the offshore oilfield group micro-capacitance sensor for improving dragonfly algorithm and Support Vector Machines Optimized in the various embodiments described above
Load forecasting model IDA-SVM enhances dragonfly up and down for relevance, the outstanding dragonfly individual of adjacent generations is remained, contracts
Short optimal iteration time；By the way that the support vector machines optimized penalty factor and nuclear parameter σ will be needed to combine and be used as dragonfly solution
Position, the classification accuracy adaptive value current as dragonfly that support vector machines is calculated, iteration goes out individual best of dragonfly
Position is optimal C, σ parameter of support vector machines.Chinese Bohai Sea offshore oilfield group micro-capacitance sensor is carried out using IDA-SVM algorithms
Short-term load forecasting the experimental results showed that IDA-SVM algorithm steps are succinct, ability of searching optimum is strong, possesses higher prediction essence
Degree and computational efficiency.
The detailed description of the above, the only specific embodiment of the invention rather than limitation of the present invention.The relevant technologies
The technical staff in field is in the case of the principle and range for not departing from the present invention, various replacements, modification and the improvement made
It should all be included in the protection scope of the present invention.
Claims (10)
- A kind of 1. method for offshore oilfield group micro-capacitance sensor short-term electric load prediction, which is characterized in that the method includes：The respective upper limit value and lower limit value of punishment parameter C and nuclear parameter σ of support vector machines is set；Setting improves dragonfly algorithm IDA Position vector dimension, maximum iteration, the quantity of dragonfly individual；Initialize the behavioral parameters of dragonfly individual；Calculate IDA The current adaptive value of middle dragonfly individual；By two generation dragonfly individuals by Map Sort, calculate and preserve corresponding maximum adaptation value；More The position of food and natural enemy in new IDA；Update the behavior of dragonfly individual in IDA；Update the position of dragonfly individual in IDA；When not up to maximum iteration, back to starting to perform the step of calculating the current adaptive value of dragonfly individual in IDA； When reaching maximum iteration, the position of the dragonfly individual according to corresponding to the maximum adaptation value of preservation sets the punishment of SVM Parameter C and nuclear parameter σ, and offshore oilfield group micro-capacitance sensor short-term electric load is predicted based on SVM structure prediction models.
- 2. according to the method described in claim 1, it is characterized in that, the behavioral parameters of the initialization dragonfly individual include：With The initial solution X of machine generation dragonfly body position0；Random generation step-length vector Δ Xt；The separation power of random generation dragonfly individual behavior Weight s, is aligned weight a, cohesive force weight c, food attraction weight f and keeps away enemy weight e；It is random to generate adjacent radius r and be used to Property weight w.
- 3. according to the method described in claim 2, it is characterized in that, the method includes：According to the current location of dragonfly individual The punishment parameter C of SVM and nuclear parameter σ is set, the classification accuracy of corresponding SVM is set as the current adaptation of dragonfly individual Value.
- 4. according to the method described in claim 3, it is characterized in that, the method includes：According to the current location of dragonfly individual And the initial position of food, natural enemy, utilize the position X of Euclidean distance formula calculating food+With the position X of natural enemy-。
- 5. according to the method described in claim 4, it is characterized in that, the behavior for updating dragonfly individual in IDA includes：According to FormulaThe separating behavior of i-th of dragonfly individual is updated, wherein, X is the position of current dragonfly individual, Xj For the position of j-th of adjacent dragonfly individual, N is the quantity of adjacent dragonfly individual；According to formulaTo update i-th The alignment behavior of dragonfly individual, wherein, VjRepresent the flying speed of j-th of adjacent dragonfly individual；According to formulaTo update the cohesion behavior of i-th of dragonfly individual；According to formula Fi=X+- X is a to update i-th of dragonfly The food attraction behavior of body；According to formula Ei=X-- X keeps away enemy's behavior update i-th dragonfly individual.
- 6. according to the method described in claim 5, it is characterized in that, the position of dragonfly individual includes in the update IDA：Work as dragonfly During at least one neighbouring dragonfly individual of dragonfly individual, formula Δ X is utilizedt+1=(sSi+aAi+cCi+fFi+eEi)+wΔXtCome more New step-length vector, and utilize formula Xt+1=Xt+ΔXt+1To update the position of dragonfly individual；When the dragonfly individual not closed on, formula X is utilizedt+1=Xt+Lévy(d)×XtUpdate the position of dragonfly individual, In, L é vy are random walk function, are represented in the dimensional extent of position vector d randomly to any direction advance random-length Distance.
- 7. the according to the method described in claim 6, it is characterized in that, random walk functionWherein, r1、r2For (0,1] in the range of random number, Γ (x)=(x-1)！, β is the constant equal to 1.5.
- 8. method according to any one of claim 1 to 7, which is characterized in that the dimension d of the position vector is 6.
- 9. method according to any one of claim 1 to 7, which is characterized in that the maximum iteration Mit is 150, The quantity of dragonfly individual is 40.
- A kind of 10. system for offshore oilfield group micro-capacitance sensor short-term electric load prediction, which is characterized in that the system packet It includes：Display, input-output equipment, at least one processor, the memory being connect at least one processor communication, with And the power-supply device for power supply；Wherein, the display is used to show prediction result；The input-output equipment is used for input initialization parameter；It is described to deposit Reservoir is stored with the instruction that can be performed by least one processor, and described instruction is performed by least one processor, So that at least one processor is able to carry out according to claim 1 to 9 any one of them method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810088180.1A CN108197759A (en) | 2018-01-30 | 2018-01-30 | For the method and system of offshore oilfield group micro-capacitance sensor short-term electric load prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810088180.1A CN108197759A (en) | 2018-01-30 | 2018-01-30 | For the method and system of offshore oilfield group micro-capacitance sensor short-term electric load prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108197759A true CN108197759A (en) | 2018-06-22 |
Family
ID=62591781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810088180.1A Pending CN108197759A (en) | 2018-01-30 | 2018-01-30 | For the method and system of offshore oilfield group micro-capacitance sensor short-term electric load prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108197759A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694482A (en) * | 2018-07-27 | 2018-10-23 | 西南石油大学 | Based on fractal theory and improved least square method supporting vector machine tide flow velocity prediction technique |
| CN109146196A (en) * | 2018-09-07 | 2019-01-04 | 河北工程大学 | A kind of residential communities hourly water demand forcast method |
| CN109507887A (en) * | 2018-12-28 | 2019-03-22 | 浙江大学 | The industrial melt index soft measurement method of fuzzy neural network combination colony intelligence optimizing |
| CN110232641A (en) * | 2019-06-13 | 2019-09-13 | 重庆邮电大学 | Method for secret protection based on power information system network regulation mechanism |
| CN110377034A (en) * | 2019-07-09 | 2019-10-25 | 哈尔滨工程大学 | A kind of waterborne vessel track following Global robust sliding-mode control based on dragonfly algorithm optimization |
| CN110929464A (en) * | 2019-11-20 | 2020-03-27 | 燕山大学 | Storage battery parameter identification method based on improved dragonfly algorithm |
| CN112327997A (en) * | 2020-10-29 | 2021-02-05 | 国网宁夏电力有限公司电力科学研究院 | Photovoltaic global maximum power tracking control method based on improved dragonfly algorithm |
| CN113971491A (en) * | 2021-10-27 | 2022-01-25 | 杭州市电力设计院有限公司余杭分公司 | Site selection and volume fixing optimization method, equipment and medium for power distribution network energy storage power station |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7739206B2 (en) * | 2006-01-24 | 2010-06-15 | Honda Research Institute Europe Gmbh | Combining model-based and genetics-based offspring generation for multi-objective optimization using a convergence criterion |
| CN105184398A (en) * | 2015-08-27 | 2015-12-23 | 华北电力大学（保定） | Power maximum load small-sample prediction method |
| CN106203614A (en) * | 2016-07-22 | 2016-12-07 | 吉林大学 | KP model densities Function identification method based on self adaptation Vespertilio searching algorithm |
| CN106570250A (en) * | 2016-11-02 | 2017-04-19 | 华北电力大学（保定） | Power big data oriented microgrid short-period load prediction method |
-
2018
- 2018-01-30 CN CN201810088180.1A patent/CN108197759A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7739206B2 (en) * | 2006-01-24 | 2010-06-15 | Honda Research Institute Europe Gmbh | Combining model-based and genetics-based offspring generation for multi-objective optimization using a convergence criterion |
| CN105184398A (en) * | 2015-08-27 | 2015-12-23 | 华北电力大学（保定） | Power maximum load small-sample prediction method |
| CN106203614A (en) * | 2016-07-22 | 2016-12-07 | 吉林大学 | KP model densities Function identification method based on self adaptation Vespertilio searching algorithm |
| CN106570250A (en) * | 2016-11-02 | 2017-04-19 | 华北电力大学（保定） | Power big data oriented microgrid short-period load prediction method |
Non-Patent Citations (4)
| Title |
|---|
| 傅军栋 等: "基于蜻蜓算法和支持向量机的变压器故障诊断", 《华东交通大学学报》 * |
| 吴伟民 等: "基于增强个体信息交流的蜻蜓算法", 《计算机工程与应用》 * |
| 宋俊敏 等: "基于蜻蜓算法的甘蔗收获机刀盘振动SVM预测模型", 《农机化研究》 * |
| 宋俊敏: "蜻蜓算法的改进及在甘蔗收获机中的应用", 《中国优秀硕士学位论文全文数据库 农业科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694482A (en) * | 2018-07-27 | 2018-10-23 | 西南石油大学 | Based on fractal theory and improved least square method supporting vector machine tide flow velocity prediction technique |
| CN108694482B (en) * | 2018-07-27 | 2022-01-14 | 西南石油大学 | Fractal theory and improved Least Square Support Vector Machine (LSSVM) tidal flow velocity prediction method |
| CN109146196A (en) * | 2018-09-07 | 2019-01-04 | 河北工程大学 | A kind of residential communities hourly water demand forcast method |
| CN109146196B (en) * | 2018-09-07 | 2021-07-23 | 河北工程大学 | Residential community district water consumption prediction method |
| CN109507887A (en) * | 2018-12-28 | 2019-03-22 | 浙江大学 | The industrial melt index soft measurement method of fuzzy neural network combination colony intelligence optimizing |
| CN110232641A (en) * | 2019-06-13 | 2019-09-13 | 重庆邮电大学 | Method for secret protection based on power information system network regulation mechanism |
| CN110377034A (en) * | 2019-07-09 | 2019-10-25 | 哈尔滨工程大学 | A kind of waterborne vessel track following Global robust sliding-mode control based on dragonfly algorithm optimization |
| CN110377034B (en) * | 2019-07-09 | 2022-05-17 | 哈尔滨工程大学 | Global robust sliding mode control method for track tracking of surface ship based on dragonfly algorithm optimization |
| CN110929464A (en) * | 2019-11-20 | 2020-03-27 | 燕山大学 | Storage battery parameter identification method based on improved dragonfly algorithm |
| CN110929464B (en) * | 2019-11-20 | 2022-06-03 | 燕山大学 | Storage battery parameter identification method based on improved dragonfly algorithm |
| CN112327997A (en) * | 2020-10-29 | 2021-02-05 | 国网宁夏电力有限公司电力科学研究院 | Photovoltaic global maximum power tracking control method based on improved dragonfly algorithm |
| CN113971491A (en) * | 2021-10-27 | 2022-01-25 | 杭州市电力设计院有限公司余杭分公司 | Site selection and volume fixing optimization method, equipment and medium for power distribution network energy storage power station |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197759A (en) | For the method and system of offshore oilfield group micro-capacitance sensor short-term electric load prediction | |
| Houssein et al. | A modified Marine Predator Algorithm based on opposition based learning for tracking the global MPP of shaded PV system | |
| Salimi | Stochastic fractal search: a powerful metaheuristic algorithm | |
| Dubey et al. | An overview and comparative analysis of recent bio-inspired optimization techniques for wind integrated multi-objective power dispatch | |
| Kumar et al. | Genetic algorithms | |
| Dehghani et al. | DTO: Donkey theorem optimization | |
| Li et al. | Efficient path planning method based on genetic algorithm combining path network | |
| Zheng et al. | Short‐term wind power prediction in microgrids using a hybrid approach integrating genetic algorithm, particle swarm optimization, and adaptive neuro‐fuzzy inference systems | |
| Park et al. | Short-Term Wind Electric Power Forecasting Using a Novel Multi-Stage Intelligent Algorithm. | |
| Saxena et al. | Application of computational intelligence in emerging power systems | |
| Pop et al. | Review of bio-inspired optimization applications in renewable-powered smart grids: Emerging population-based metaheuristics | |
| CN107590570A (en) | A kind of bearing power Forecasting Methodology and system | |
| JP6940831B2 (en) | Decision device, decision method, and decision program | |
| Razak et al. | A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting | |
| Tumari et al. | Data-driven control based on marine predators algorithm for optimal tuning of the wind plant | |
| EP4176388A1 (en) | Topicbert: decarbonizing bert with topics for efficient document classification | |
| Wattal et al. | Multivariate air pollution levels forecasting | |
| Geng et al. | An ensemble classifier algorithm for mining data streams based on concept drift | |
| Karam et al. | Applying convolutional neural networks for image detection | |
| Wai et al. | Intelligent daily load forecasting with fuzzy neural network and particle swarm optimization | |
| Zhao et al. | Particle swarm algorithm for classification rules generation | |
| Kumar et al. | AI based Economic Load Dispatch incorporating wind power penetration | |
| Kim et al. | Performance measures of metaheuristic algorithms | |
| Potharlanka et al. | Identifying Optimal Features using Whale Optimization Technique | |
| Bachlaus et al. | Optimization of system reliability using chaos-embedded self-organizing hierarchical particle swarm optimization |
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: 20180622 |
|
| RJ01 | Rejection of invention patent application after publication |