CN108197748A - A kind of flow of the people Forecasting Methodology based on mind evolutionary - Google Patents
A kind of flow of the people Forecasting Methodology based on mind evolutionary Download PDFInfo
- Publication number
- CN108197748A CN108197748A CN201810015168.8A CN201810015168A CN108197748A CN 108197748 A CN108197748 A CN 108197748A CN 201810015168 A CN201810015168 A CN 201810015168A CN 108197748 A CN108197748 A CN 108197748A
- Authority
- CN
- China
- Prior art keywords
- flow
- people
- mind evolutionary
- forecasting methodology
- evolutionary
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 2
- 238000009472 formulation Methods 0.000 abstract description 2
- 239000000203 mixture Substances 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000003786 synthesis reaction 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (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)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of flow of the people Forecasting Methodologies based on mind evolutionary, this method is based on neural network prediction model, considering influences the factor of Power supply business Room flow of the people, whether the input data for taking prediction model is corresponding time point, same day weather, is working day, exports the flow of the people predicted value it is expected the moment.The present invention optimizes traditional neural network structure by mind evolutionary, hidden layer weights, threshold value are optimized by convergent and operation dissimilation, cut down the prediction error of hidden layer weights, threshold value at random caused by generation, so as to build the higher prediction model of precision, the flow of the people prediction level in the Power supply business Room is improved, the solution formulation that own services level is promoted for the Power supply business Room provides more accurate scientific basis.
Description
Technical field
The present invention relates to a kind of flow of the people Forecasting Methodologies, belong to intelligent predicting technical field.
Background technology
As electric power enterprise business is gradually included in deeper market economy environment, power marketing industry is improved with quality services
Business has become the necessary work that current power enterprise carries out day-to-day operations management.The Power supply business Room is used as and is directly facing electric power
The window-unit of user, the quality of service level directly affect impression of the Electricity customers for enterprise.
The flow of the people in the Power supply business Room be the manning in the Power supply business Room, equipment core reference foundation, for power supply
The service quality of business hall itself is a key influence factor.Although traditional neural network can be used for carrying out numerical value to flow of the people
Prediction, but its precision of prediction is not high, still has to be hoisted, it is therefore desirable to design a kind of more accurate flow of the people prediction modeling side
Method.
Invention content
The defects of technical problems to be solved by the invention are for involved in background technology proposes a kind of new flow of the people
Forecasting Methodology improves precision of prediction.
The present invention is in order to solve the above technical problems, and using following technical scheme:
A kind of flow of the people Forecasting Methodology based on mind evolutionary, includes the following steps:
Step 1:Corresponding time point data format, same day weather data form is set separately and whether it is working day data format;
Step 2:Tectonic model input data feature vector:
E=[T i , W i , K i ]
WhereiniThe same day weather at moment is denoted asW i , if it is for work diaryK i , corresponding time point is denoted asT i ;
Step 3:For mind evolutionary arrange parameter, the parameter of setting includes Population Size, winning sub- population, interim son kind
Group, hidden layer, iterations;
Step 4:Operation similartaxis is carried out to mind evolutionary, when the score of interim sub- population is less than the score of winning sub- population
When, operation similartaxis stops, on the contrary then continue operation similartaxis.
Step 5:When operation similartaxis stops, the best initial weights and threshold value of BP neural network are obtained;
Step 6:Historical data is inputted, training BP neural network obtains prediction model;
Step 7:Correspondence time point to be predicted is inputted to prediction model, same day weather, whether is working day, you can is obtained and is treated
The flow of the people of predicted time point.
The present invention has following technique effect using above technical scheme:
This method is based on neural network prediction model, and traditional neural network structure is optimized by mind evolutionary, is obtained
Go out the higher prediction model of precision of prediction, improve the flow of the people prediction level in the Power supply business Room, promoted certainly for the Power supply business Room
The solution formulation of body service level provides more accurate scientific basis.
Description of the drawings
Fig. 1 is the flow chart of the present invention.
Fig. 2 is the principle of the present invention figure.
Specific embodiment
Technical scheme of the present invention is described in further detail below in conjunction with the accompanying drawings:
Those skilled in the art of the present technique are it is understood that unless otherwise defined, all terms used herein(Including technology art
Language and scientific terminology)With the identical meaning of the general understanding with the those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, which should be understood that, to be had and the meaning in the context of the prior art
The consistent meaning of justice, and unless defined as here, will not be with idealizing or the meaning of too formal be explained.
The present invention provides a kind of flows of the people based on mind evolutionary to predict modeling method, which is based on BP nerves
Network introduces mind evolutionary and BP neural network structure is optimized, so as to promote precision of prediction.Mind evolutionary is
A kind of optimization algorithm constantly evolved by iteration, this method can realize the optimization to neural network prediction model:By becoming
Same and operation dissimilation optimizes hidden layer weights, threshold value, cuts down the prediction mistake of hidden layer weights, threshold value at random caused by generation
Difference, so as to build the higher prediction model of precision.
As shown in Fig. 2, a kind of flow of the people prediction modeling method based on mind evolutionary of the present invention, synthesis are examined
Consider the factor of Power supply business Room flow of the people that influences, the input data for taking prediction model be corresponding time point, same day weather, whether be
Working day exports the flow of the people predicted value it is expected the moment.
Corresponding time point data format:According to the investigation and analysis to business handling situation, it is 5 minutes to take the sampling period.Its
In be for the processing method at corresponding time point:It takes 24 hours and makes,MWhenNMinute mark is(M+N/60), divide in the case of when 14 15,
As 14+15/60=14.25.
Same day weather data form:The degree of trip is influenced according to weather, is classified as 5 ranks, each rank is assigned
Give a coding:(Sunny=1),(Cloudy=2),(Light rain=3),(Moderate rain/slight snow/rain and snow mixed=4),(Heavy rain/heavy snow
= 5),(Extra torrential rain/snow or typhoon=6).
Whether it is working day data format:Work diary is 1, and nonworkdays is denoted as 0:(Mon-Fri=1),(Week
Six/Zhou Tian=0).
Tectonic model input data feature vector:iThe weather condition at moment is denoted asW i , working day situation is denoted asK i , at this time
Time point is denoted asT i .Then mode input feature vector is:
E=[T i , W i , K i ]。
For mind evolutionary arrange parameter.Mind evolutionary is a kind of algorithm constantly evolved by iteration, is evolved
When per all groups of individuals of a generation be known as a group, a group is divided into several sub-groups.The parameter of setting includes
Population Size, winning sub- population, interim sub- population, hidden layer, iterations.
Operation similartaxis is carried out to mind evolutionary(In the range of sub-group, the individual process to be competed as victor
It is convergent), when the score of interim sub- population is less than the score of winning sub- population, operation similartaxis stops, conversely, continuing to become
Biconditional operation.
When operation similartaxis stops, the best initial weights and threshold value of BP neural network are obtained, i.e. prediction model is optimal knot
Structure.
Historical data is inputted, training BP neural network obtains prediction model.
Time point to be predicted is inputted to prediction model, same day weather, whether is working day, you can obtains the Power supply business Room
It is expected the flow of the people at moment.
The model is based on BP neural network, specifically as shown in Figure 1, by introducing mind evolutionary to BP neural network knot
Structure optimizes, so as to promote precision of prediction.
The above is only some embodiments of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (5)
1. a kind of flow of the people Forecasting Methodology based on mind evolutionary, which is characterized in that include the following steps:
Step 1:Corresponding time point data format, same day weather data form is set separately and whether it is working day data format;
Step 2:Structure forecast mode input data characteristics vector:
E=[T i , W i , K i ]
WhereinW i ForiThe same day weather at moment, if be for work diaryK i , corresponding time point is denoted asT i ;
Step 3:For mind evolutionary arrange parameter, the parameter of setting includes Population Size, winning sub- population, interim son kind
Group, hidden layer, iterations;
Step 4:Operation similartaxis is carried out to mind evolutionary, when the score of interim sub- population is less than the score of winning sub- population
When, operation similartaxis stops, on the contrary then continue operation similartaxis;
Step 5:When operation similartaxis stops, the best initial weights and threshold value of BP neural network are obtained;
Step 6:Historical data is inputted, training BP neural network obtains prediction model;
Step 7:Correspondence time point to be predicted is inputted to prediction model, same day weather, whether is working day, you can is obtained and is treated
The flow of the people of predicted time.
A kind of 2. flow of the people Forecasting Methodology based on mind evolutionary according to claim 1, which is characterized in that data
Sampling period be 5 minutes.
A kind of 3. flow of the people Forecasting Methodology based on mind evolutionary according to claim 1, which is characterized in that step
It is for the data format at corresponding time point in one:It takes 24 hours and makes,MWhenNMinute mark is(M+N/60).
A kind of 4. flow of the people Forecasting Methodology based on mind evolutionary according to claim 1, which is characterized in that step
It is for same day weather data form in one:The degree of trip is influenced according to weather, K rank is classified as, to each rank
Assign a coding.
A kind of 5. flow of the people Forecasting Methodology based on mind evolutionary according to claim 1, which is characterized in that step
For whether being that working day data format is in one:Work diary is 1, and nonworkdays is denoted as 0.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810015168.8A CN108197748B (en) | 2018-01-08 | 2018-01-08 | People flow prediction method based on thought evolution algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810015168.8A CN108197748B (en) | 2018-01-08 | 2018-01-08 | People flow prediction method based on thought evolution algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108197748A true CN108197748A (en) | 2018-06-22 |
CN108197748B CN108197748B (en) | 2020-11-24 |
Family
ID=62588213
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810015168.8A Active CN108197748B (en) | 2018-01-08 | 2018-01-08 | People flow prediction method based on thought evolution algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108197748B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111026624A (en) * | 2019-11-11 | 2020-04-17 | 国网甘肃省电力公司信息通信公司 | Fault prediction method and device of power grid information system |
CN116822965A (en) * | 2023-08-28 | 2023-09-29 | 中铁七局集团电务工程有限公司武汉分公司 | Subway construction risk early warning method and system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170186093A1 (en) * | 2015-12-23 | 2017-06-29 | Aetna Inc. | Resource allocation |
CN106991208A (en) * | 2017-02-28 | 2017-07-28 | 浙江工业大学 | Forecasting Methodology based on the injector performance using the BP artificial neural networks for improving mind evolutionary |
-
2018
- 2018-01-08 CN CN201810015168.8A patent/CN108197748B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170186093A1 (en) * | 2015-12-23 | 2017-06-29 | Aetna Inc. | Resource allocation |
CN106991208A (en) * | 2017-02-28 | 2017-07-28 | 浙江工业大学 | Forecasting Methodology based on the injector performance using the BP artificial neural networks for improving mind evolutionary |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111026624A (en) * | 2019-11-11 | 2020-04-17 | 国网甘肃省电力公司信息通信公司 | Fault prediction method and device of power grid information system |
CN111026624B (en) * | 2019-11-11 | 2023-06-02 | 国网甘肃省电力公司信息通信公司 | Fault prediction method and device of power grid information system |
CN116822965A (en) * | 2023-08-28 | 2023-09-29 | 中铁七局集团电务工程有限公司武汉分公司 | Subway construction risk early warning method and system |
CN116822965B (en) * | 2023-08-28 | 2023-11-21 | 中铁七局集团电务工程有限公司武汉分公司 | Subway construction risk early warning method and system |
Also Published As
Publication number | Publication date |
---|---|
CN108197748B (en) | 2020-11-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108539738B (en) | Short-term load prediction method based on gradient lifting decision tree | |
EP3822880A1 (en) | Load prediction method and apparatus based on neural network | |
CN109002942A (en) | A kind of short-term load forecasting method based on stochastic neural net | |
CN109711620A (en) | A kind of Short-Term Load Forecasting Method based on GRU neural network and transfer learning | |
CN102129511B (en) | System for forecasting short-term wind speed of wind power station based on MATLAB | |
CN104376371B (en) | A kind of distribution based on topology is layered load forecasting method | |
CN102722759A (en) | Method for predicting power supply reliability of power grid based on BP neural network | |
CN106971238A (en) | The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S | |
CN105631517A (en) | Photovoltaic power generation power short term prediction method based on mind evolution Elman neural network | |
CN107609774B (en) | Photovoltaic power prediction method for optimizing wavelet neural network based on thought evolution algorithm | |
CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
Tian et al. | A network traffic hybrid prediction model optimized by improved harmony search algorithm | |
CN108197748A (en) | A kind of flow of the people Forecasting Methodology based on mind evolutionary | |
CN111415049A (en) | Power failure sensitivity analysis method based on neural network and clustering | |
CN113780679B (en) | Load prediction method and device based on ubiquitous power Internet of things | |
CN107895211A (en) | A kind of long-medium term power load forecasting method and system based on big data | |
CN104915727A (en) | Multi-dimensional isomorphic heterogeneous BP neural network optical power ultrashort-term prediction method | |
CN104252647B (en) | Electro-load forecast method based on anti-distance weighting interpolation method | |
CN109214610A (en) | A kind of saturation Methods of electric load forecasting based on shot and long term Memory Neural Networks | |
CN112052985A (en) | Lightgbm-based medium-short term low voltage prediction method | |
CN115526393B (en) | Manufacturing cost prediction method based on screening of key influencing factors of power transformation engineering | |
CN113344290B (en) | Method for correcting sub-season rainfall weather forecast based on U-Net network | |
Jareanpon et al. | An adaptive RBF network optimised using a genetic algorithm applied to rainfall forecasting | |
Qing-wei et al. | Prediction of electricity consumption based on genetic algorithm-RBF neural network | |
CN205263860U (en) | Wind power foresees system based on genetic algorithm optimizes neural network |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |