CN108573327A - Wireless sensing net node solar energy collecting power prediction algorithm based on weather data - Google Patents
Wireless sensing net node solar energy collecting power prediction algorithm based on weather data Download PDFInfo
- Publication number
- CN108573327A CN108573327A CN201810383872.9A CN201810383872A CN108573327A CN 108573327 A CN108573327 A CN 108573327A CN 201810383872 A CN201810383872 A CN 201810383872A CN 108573327 A CN108573327 A CN 108573327A
- Authority
- CN
- China
- Prior art keywords
- weather
- solar energy
- time slot
- changes
- prediction
- 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 claims abstract description 21
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000007726 management method Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010835 comparative analysis Methods 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 description 9
- 238000013461 design Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000002699 waste material Substances 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
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/02—Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed
-
- 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
-
- H02J3/383—
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- 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
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
- Y02E10/56—Power conversion systems, e.g. maximum power point trackers
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Selective Calling Equipment (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The present invention proposes the wireless sensing net node solar energy collecting power prediction algorithm based on weather data, can accurately predict the collection power of the wireless sensing net node with solar energy acquisition function while using smaller room and time.This discovery has fully considered influence of the Changes in weather to solar energy collecting power prediction, pass through the comparative analysis between Changes in weather and solar energy collecting power, interactively of the Changes in weather to solar energy acquisition is found that, to realize in the notable scene Accurate Prediction node solar energy collecting power of Changes in weather.This method can obtain very high precision of prediction in weather significant changes and weather smooth change scene simultaneously.
Description
Technical field
The present invention relates to the wireless sensing net node solar energy collecting power prediction algorithms based on weather data, belong to wireless
Sensor Network field.
Background technology
Wireless sensor network(WirelessSensorNetwork,WSN)Be by a large amount of static or mobile sensor with
The wireless network that the mode of self-organizing and multi-hop is constituted.Since low cost and height are motor-driven, WSN is in the past develops increasingly by joyous
It meets, while they can complete numerous application scenarios that traditional cable or cable network can not be handled, such as smart home, radiation
Monitoring, biocenological microcosmic observation and intelligent transportation etc..The basic composition of WSN is sensor node, and researcher passes through solid
Fixed point is launched or the random modes such as jettisoning are dispersed in monitoring region.
Conventional sensor node includes mainly four data acquisition, data processing, data transmission and power supply modules,
Middle power module is responsible for providing energy to its excess-three module.Growth trend between battery and other embedded system components
In the case of unmatched, the power management of resource-constrained embedded system is still a stern challenge.It is remote due to WSN
Reliable power supply is disposed and lacked to journey scene, and the sensor in network usually relies on battery and realizes that it is expected to appoint to provide energy
Business.Battery powered WSN finally can cause network to fail because of limited electrical power regardless of its energy efficiency, unless more
Change battery.If network is deployed in rugged environment or is not easy the scene reached, battery altering be even more an expensive expenditure very
To cannot achieve.A promising solution to this problem is to be used together environmental energy collection technique with battery,
The common environmental energy utilized that acquires has solar energy, vibrational energy, wind energy, noise etc..Solar energy is big, easy because of its energy density
The features such as acquisition and be widely used.
Energy harvesting capabilities, which are introduced wireless sensor network, will cause many designs about the structure of this system to be asked
Topic, such as energy predicting, energy management and Routing Protocol etc..Wherein energy predicting is even more the premise of other problems design, because
Either energy management or Routing Protocol, when design, all must take into consideration energy consumption, i.e., provide it according to existing utilisable energy
Performance level.Since the utilisable energy of the WSN with energy acquisition technology includes acquiring dump energy and the following certain time
Environmental energy, it is desirable to know that utilisable energy just must be able to predict the environmental energy of the following certain time acquisition.
By taking the WSN energy managements for possessing solar energy acquisition ability as an example, the WSN with environmental energy acquisition technique is in theory
On can continue operation because environmental energy acquisition technique can acquire the consumption that environmental energy carrys out supplementary sensor.But it is real
Border shows the sensor with energy acquisition ability for electric installation it is difficult to ensure that uninterrupted operation long-term WSN.Main cause is
Dependence to uncontrollable solar energy, solar energy are difficult to simulate and predict due to meteorologic factor, and the variation of time, space make it
Show higher short-term fluctuation.The uncertainty that solar energy is irradiated to the energy size of earth's surface results in node collecting energy
It is uncertain so that the energy management of WSN is difficult to energy neutral operation(ENO), i.e., the energy of system within the regular hour
Consumption is less than or equal to the energy of environment acquisition.WSN is typically to use height by dynamic debugging system performance level at runtime
The variable environmental energy of degree can realize ENO, but cause energy if system operates in always minimum performance level
Waste, and system at this time is also difficult to meet most tasks requirement;If system operation very may be used in higher performance level
The energy that environment acquires can be caused to be less than system energy consumption, terminate in advance the service life of network.Therefore, rational energy management is WSN
The essential condition that can permanently run, and the premise of energy management is to know system utilisable energy, can predict future
The environmental energy acquired in certain time.
It is directed to solar energy at present, prediction algorithm, such as EWMA, WCMA and Pro-Energy are proposed there are many researcher
Deng.Following short-term collection power is mainly predicted the analysis of history gathered data.In the stable scene of weather, above
Algorithm can be by prediction control errors to a very small extent, and especially WCMA can adapt to the simple change of weather, but
When big variation occurs for weather, algorithm above is then it is difficult to ensure that the accuracy of prediction.It is well known that most of scene one
Rain or shine conversion of weather condition is very common within it, therefore the variation of real-time weather is considered for the prediction algorithm of solar energy
It is necessary.
Invention content
The present invention proposes the wireless sensing net node solar energy collecting power prediction algorithm based on weather data, this method energy
Enough while using smaller room and time, the wireless sensing net node with solar energy acquisition function is accurately predicted
Power is collected, and is realized in the notable scene Accurate Prediction node solar energy collecting power of Changes in weather, while is notable in weather
Variation and weather smooth change scene can obtain very high precision of prediction.
Wireless sensing net node solar energy collecting power prediction algorithm of the present invention based on weather data, it is specific to execute
Steps are as follows:
Step 1:Real-time weather categorical data and the solar energy collecting power data for passing by adjacent 5 years in selection monitoring region, will
Weather pattern is divided into 6 kinds, is fine day respectively(C), it is fine with occasional clouds(PC), have cloud(SC), cloudy (MCI), cloudy (O), sleet
(RS);Statistical disposition is carried out to the solar energy collecting power of different weather type different time-gap, according between each weather class data
Multiplying power relationship, by multiplying power relationship map be weather pattern number index, enter step 2;
Step 2:Obtain the practical data of weather forecast on the same day, by the day on the prediction same day
Gas prediction dataWith the weather forecasting data of the previous dayIt is compared, obtains front and back two days weather
Variation coefficient, enter step 3;
Step 3:It is to reflect whether weather occurs the threshold value of significant changes, size is by history real-time weather number of types
It obtains, compares according to the analysis for collecting power data with nodeWith;If, then it is assumed that the prediction same day is with before
One day weather is essentially identical, direct jump procedure 4;If, then it is assumed that the prediction same day and the weather of the previous day are sent out
Raw significant changes, direct jump procedure 5;
Step 4:First consider the essentially identical situation of the weather of the prediction same day and the previous day, usesThe thought of algorithm;
It is before wireless sensing net nodeItThe energy acquisition value average value of time slot,It is oneMatrix has recorded before the time slot that will be predictedThe Changes in weather situation of a time slot, whereinBy calculating
Go out;Be for reflecting weight, whereinIt is finally to calculate reflection prediction by being calculated
The same day and the one day Changes in weather degree in front(It is determined by predicting the historical collection power data in place);And at this time too
Sun can acquire predicted value and can directly calculate, rear jump procedure 7;
Step 5:When the prediction same day significant changes occurring with the previous day weather, the practical data of weather forecast on the prediction same day is used
To correct prediction error;It is oneMatrix is used to store the time slot that will be predicted
And frontThe Changes in weather situation of a time slot, whereinIt is calculated by data of weather forecast, it is final to calculate
Prediction same day time slot when going out weather significant changesAnd frontThe Changes in weather degree of a time slot, enters step 6;
Step 6:When significant changes occur for weather, it is divided into two kinds of situations, respectively weather significantly improves significantly is deteriorated with weather;This
Influence of two kinds of situations to the acquisition of solar energy uses constantTo correct;Finally, when calculating weather generation significant changes
TheItThe solar energy collecting power that time slot is predicted, enter step 7;
Step 7:Prediction result is fed back into sensor node for energy management.
Further, in the step 2, front and back two days Changes in weather coefficientsCalculation formula be:
WhereinIt isItThe weather pattern index of time slot.
Further, in the step 4, by comparing the energy acquisition value of the leading slots on the day of prediction with beforeIt is right
Answer the energy acquisition value average value of time slotNumerical value change reflect the variation of weather conditions,Algorithm description is such as
Under:
Wherein,It isItThe predicted value of the solar energy collecting power of time slot,It isItTime slot
Solar energy collecting power actual observation value,It is weight factor, and;For frontIts time slot
Solar energy collecting power average value,It refer to same day time slot and pastThe Changes in weather feelings of its corresponding time slot
Condition, calculation formula are as follows:
In above formulaThe weight for being just,It is bigger, then weightAlso can be bigger, it is as follows:
It is oneMatrix has recorded before the time slot that will be predictedThe Changes in weather situation of a time slot is as follows
Formula:
In addition, in step 4It is calculate by the following formula:
。
Further, in the step 5 and step 6, definitionFor same day time slot and pastIts corresponding time slot
Changes in weather situation,Significant changes occur for weather, define simultaneouslyThe solar energy collecting power that significantly improves for weather is big
Increase,Subtract greatly for weather significantly variation solar energy collecting power, is shown below:
By to parameterSetting constrain influence of the different Changes in weather situations to solar energy collecting power, parameterIt to be determined with solar energy acquisition situation according to actual weather condition;For front and back two days Changes in weather feelings
Condition, shown in formula specific as follows:
Wherein,It is oneMatrix is used to store the time slot that will be predicted and frontThe day of a time slot
Gas situation of change, specificallyCalculating be shown below:
In addition it introduces, it is oneMatrix, for embodying weight;Wherein,It is bigger, then weightAlso can be bigger, i.e.,
It is more important nearer it is to the Changes in weather situation for the time slot that will be predicted, shown in specific following formula:
It willWithAfter multiplication divided bySum, and final result is determined as Changes in weather situation。
Further, in the step 6, final prediction algorithm such as following formula:
Wherein,It is to reflect whether weather occurs the threshold value of significant changes,Size be by history real-time weather type
The analysis that data and node collect power data obtains.
Advantageous effect
The present invention proposes the wireless sensing net node solar energy collecting power prediction algorithm based on weather data.This method can be
While using smaller room and time, the collection of the wireless sensing net node with solar energy acquisition function is accurately predicted
Power.This discovery has fully considered influence of the Changes in weather to solar energy collecting power prediction, by Changes in weather and the sun
The comparative analysis between power can be collected, it was found that Changes in weather is to the interactively of solar energy acquisition, to realize in day
Gas is changed significantly scene Accurate Prediction node solar energy collecting power.This method steadily becomes in weather significant changes and weather simultaneously
Changing scene can obtain very high precision of prediction.
Description of the drawings
Fig. 1 is that the collection power contrast of 24 time slots of winter schemes.
Fig. 2 is the weather pattern index correspondence of winter different time-gap different weather type.
Fig. 3 is EWMA, the energy curve of the solar energy acquisition of WCMA algorithms prediction.
Fig. 4 is prediction solar energy collecting power algorithm flow chart.
Specific implementation mode
Technical scheme of the present invention is described in further detail with reference to the accompanying drawings of the specification.
The present invention is too low for the existing wireless sensing net node energy management efficiency with solar energy acquisition function, often
The solar energy acquisition prediction algorithm of rule can not adapt to Changes in weather more frequent scene the problem of, it is proposed that by weather forecast
Weather data is introduced into the prediction algorithm of solar energy collecting power.Method detailed analysis first Changes in weather is collected with node
Contact between power quantizes to the influence for collecting power weather;Secondly, by Changes in weather be divided into no significant changes,
Weather significantly improves significantly to be deteriorated three kinds with weather, and discusses the collection power prediction of each case respectively.This method is not only
Influence of the Changes in weather to prediction result can be effectively solved, the precision of prediction result is improved, while improving the applicability of algorithm,
In the scene of Different climate feature, good prediction effect can be obtained.
This method is broadly divided into three parts, first, the pass between analysis different weather type and solar energy collecting power
System;Second is that calculating and analyzing the Changes in weather on the prediction same day and the previous day;Third, calculating the sun according to different weather situation of change
The predicted value of power can be collected.
(1)Analyze the relationship between different weather type and solar energy collecting power
By being obtained to the analysis of historical data, the weather pattern of Various Seasonal is to the influence degree of solar energy acquisition also area
Not.4 spring, summer, autumn, winter parts are splitted data by standard of season, these influence factors are mapped as weather pattern index
To reflect influence of the weather pattern to solar energy acquisition.
Select the real-time weather categorical data and node collection power number that some scene inner sensor node goes over adjacent 5 years
According to.First, weather pattern is divided into 6 kinds, is fine day respectively(C), it is fine with occasional clouds(PC), have cloud(SC), cloudy (MCI), cloudy day
(O), sleet (RS).Collection capacity in different time periods has apparent difference in one day, is divided into one day for 1 time slot with 1 hour
24 time slots.Secondly, statistical disposition is carried out to the solar energy collecting power of different weather type different time-gap(Fig. 1 shows the winter
The collection power contrast of 24 time slots in season).Finally according to the multiplying power relationship between each weather class data, by multiplying power relationship map
For weather pattern index.It can be obtained by Fig. 1, other than sunrise sunset, the collection capacity of remaining time slot and the relationship of weather pattern
It is very clear, thus multiplying power relationship of the weather pattern index of 11-17 time slots between each weather class data, the day of remaining time slot
Gas index of type is the mean value of all time slots.Since the data volume at cloudy day is big, its weather pattern index is setFor unit 1,
Remaining weather pattern index does conversion of equal value on the basis of the cloudy day, and Fig. 2 shows the winter different time-gap of some scene not on the same day
The weather pattern index correspondence of gas type.
(2)Calculate and analyze the Changes in weather on the prediction same day and the previous day
Algorithm has higher accuracy in the case where predicting that the weather in place does not have variation substantially, and
Algorithm is directed toAlgorithm does not adapt to Changes in weather this defect and is corrected so that algorithm can be in Changes in weather
In the case of prediction also have higher precision.But violent variation occurs for the weather for working as prediction place, as the cloudy day becomes fine
It when,Higher error is remained.The present invention thinking be exactly withBased on, introduce the reality on network
Shi Tianqi comes pairWithThis defect for being unable to adaptive prediction place weather significant changes is improved.
Because of changeable, the weather regulatory factor of weather conditionsCalculating want many-sided consideration.Such as predict the same day with before
Face weather conditions in one day can be such that the acquisition of solar energy occurs different compared to essentially identical, significant changes and acute variation etc.
Variation, and weather conditions are not simple linear relationships to the collection power of solar energy, therefore a point situation is needed to consider.In this base
On plinth, it is necessary to consider how to distinguish the variation on the prediction same day and front weather conditions in one day.By dividing historical data
Analysis, it is found that the principal element of the quality or perhaps the height of solar energy collecting power that determine weather conditions in one day is high noon
And weather conditions this period of time in the afternoon.If the weather conditions of high noon and are fine this period of time in the afternoon, then the same day
The collected solar energy of institute's energy will be higher;On the contrary, the weather conditions of high noon and are cloudy day or rain this period of time in the afternoon
It when, the solar energy collecting power on the same day will be very low.Therefore, new variable is introducedTo reflect the prediction same day and front
One day Changes in weather is specific such as formula (1):
Because the longitude and latitude of different scenes is different, therefore in formula (1)Value is not known yet.It isItTime slot
Weather pattern index.
(3)The predicted value of solar energy collecting power is calculated according to different weather situation of change:
After distinguishing different Changes in weather, it is necessary to consider the circular of each variation.
Fig. 3 is,The energy curve of algorithm prediction and per day error(Each time slot is 1 hour).Point
Analysis obtainsAlgorithm compare withAlgorithm reduces the error of prediction, but when Changes in weather is notable still have it is larger
Error.By rightMany experiments (weight when experiment of algorithmIt is fixed as 0.5), find the algorithm to not on the same day
The prediction error of gas situation of change is different.By comparison, it is found that the weather changed from fine day to the cloudy day, prediction error are non-
Chang great;The weather changed from the cloudy day to fine day, prediction error are larger;And when front and back two days weather conditions are essentially identical, in advance
It is very small to survey error.Therefore consider to classify to different Changes in weather situations, be broadly divided into two major classes, is i.e. weather occurs aobvious
It writes variation and significant changes does not occur with weather, use respectivelyWithTo indicate.
Complex situation is first discussed, i.e., there is a situation where when significant changes for weatherHow to calculate.According to
It is analyzed above and front and back two days situations of change is subdivided into two kinds again, be that the violent solar energy collecting power of Changes in weather increases respectively
And the violent solar energy collecting power of Changes in weather subtracts greatly.For the convenience of description, definitionSignificant changes occur for weather, simultaneously
DefinitionThe solar energy collecting power that significantly improves for weather increases,It is big for weather significantly variation solar energy collecting power
Subtract.As shown in formula (2).
By to parameterSetting constrain influence of the different Changes in weather situations to solar energy collecting power, parameterIt to be determined with solar energy acquisition situation according to actual weather condition.For front and back two days Changes in weather situations,
Specific such as formula (3) is shown.
Wherein,It is oneMatrix is used to store the time slot that will be predicted and frontThe weather of a time slot
Situation of change, specificallyCalculating such as formula (4) ~ (5).
Pass through the time slot that will be predicted and frontThe Changes in weather situation of a time slot reflects the day of time slot to be predicted
When vaporous condition, there are one what problem to be considered to beIt is on the weather conditions for the time slot that will be predicted influence
Different, the Changes in weather situation nearer it is to the time slot that will be predicted is clearly more important, it is therefore desirable to introduce weight
Concept.It is similarly oneMatrix is for embodying weight.Wherein,It is bigger, then weightAlso can be bigger, that is, it gets over
Be it is more important close to the Changes in weather situation of time slot that will be predicted, it is specific such as formula (6) ~ (7).
It willWithAfter multiplication divided bySum, and final result is determined as Changes in weather situation。
Next to consider that there is a situation where significant changes for weather, i.e.,Calculating.When front and back two days weather
When situation is all fine day or cloudy day, node collected energy value big variation will not occur, but this does not represent and does not send out
Changing because being equally fine day, as the factors such as temperature, humidity and generate tiny difference, select at this time
The thought of algorithm, by comparing the energy acquisition value of the leading slots on the day of prediction with beforeThe energy acquisition value of its corresponding time slot
Average valueNumerical value change reflect the variation of weather conditions,Algorithm description is as follows:
Wherein,It isItThe predicted value of the solar energy collecting power of time slot,It isItTime slot
Solar energy collecting power actual observation value,It is weight factor, and。For frontIts time slot's
The average value of solar energy collecting power,It refer to same day time slot and pastThe Changes in weather situation of its corresponding time slot.
Specific such as formula (9) ~ (10).
In formula (13)The weight for being just,It is bigger, then weightAlso can be bigger, such as formula (6) ~ (7).It is oneMatrix has recorded before the time slot that will be predictedThe Changes in weather situation of a time slot, such as formula (11) ~ (12)
Finally, our prediction algorithm such as formula (13):
Wherein,It is to reflect whether weather occurs the threshold value of significant changes,Size be by history real-time weather type
The analysis that data and node collect power data obtains.
This method is mainly to predict the detailed process of solar energy collecting power.
Predict solar energy collecting power:Solar energy collecting power flow figure is predicted as shown in figure 4, specifically executing step such as
Under:
Step 1:Real-time weather categorical data and the solar energy collecting power data for passing by adjacent 5 years in selection monitoring region, will
Weather pattern is divided into 6 kinds, is fine day respectively(C), it is fine with occasional clouds(PC), have cloud(SC), cloudy (MCI), cloudy (O), sleet
(RS).Statistical disposition is carried out to the solar energy collecting power of different weather type different time-gap, according between each weather class data
Multiplying power relationship, by multiplying power relationship map be weather pattern number index, enter step 2.
Step 2:Obtain the practical data of weather forecast on the same day, use formula(1)
By the weather forecasting data on the prediction same dayWith the weather forecasting data of the previous dayIt is compared, obtains
Front and back two days Changes in weather coefficients, enter step 3.
Step 3:It is to reflect whether weather occurs the threshold value of significant changes, size is by history real-time weather type
The analysis that data and node collect power data obtains, comparesWith.If, then think the prediction same day
It is essentially identical with the weather of the previous day, direct jump procedure 4;If, then it is assumed that the day on the prediction same day and the previous day
Significant changes, direct jump procedure 5 occur for gas.
Step 4:First consider the essentially identical situation of the weather of the prediction same day and the previous day, usesThe think of of algorithm
Think.Such as formula(9)It is shown,It is before wireless sensing net nodeItThe energy acquisition value average value of time slot,It is oneMatrix has recorded before the time slot that will be predictedThe weather of a time slot becomes
Change situation, whereinPass through formula(12)Calculating is got.Be for reflecting weight, whereinIt is
Pass through formula(7)It calculates, eventually by formula(10)Calculate the reflection prediction same day and the one day Changes in weather degree in front
(It is determined by predicting the historical collection power data in place).And formula can be used directly in solar energy acquisition predicted value at this time
(5)It calculates, rear jump procedure 7.
Step 5:When the prediction same day significant changes occurring with the previous day weather, the practical weather forecast on the prediction same day is used
Data correct prediction error.It is oneMatrix, being used to store will predict
Time slot and frontThe Changes in weather situation of a time slot, whereinIt is calculated by data of weather forecast, specifically
Such as formula(5), eventually by formula(3)Prediction same day time slot when calculating weather significant changesAnd frontWhen a
The Changes in weather degree of gap, enters step 6.
Step 6:When significant changes occur for weather, it is divided into two kinds of situations, respectively weather significantly improves significantly becomes with weather
Difference.Influence of the both of these case to the acquisition of solar energy is different, uses constantIt corrects, such as formula(2)It is shown.
Finally, using formula(13)Weather is calculated to occur the when significant changesItThe solar energy that time slot is predicted is received
Collect power, enter step 7.
Step 7:Prediction result is fed back into sensor node for energy management.
The foregoing is merely the better embodiment of the present invention, protection scope of the present invention is not with the above embodiment
Limit, as long as those of ordinary skill in the art should all be included in power according to equivalent modification or variation made by disclosed content
In protection domain described in sharp claim.
Claims (5)
1. the wireless sensing net node solar energy collecting power prediction algorithm based on weather data, it is characterised in that:It is specific to execute
Steps are as follows:
Step 1:Real-time weather categorical data and the solar energy collecting power data for passing by adjacent 5 years in selection monitoring region, will
Weather pattern is divided into 6 kinds, is fine day respectively(C), it is fine with occasional clouds(PC), have cloud(SC), cloudy (MCI), cloudy (O), sleet
(RS);Statistical disposition is carried out to the solar energy collecting power of different weather type different time-gap, according between each weather class data
Multiplying power relationship, by multiplying power relationship map be weather pattern number index, enter step 2;
Step 2:Obtain the practical data of weather forecast on the same day, by the weather forecasting number on the prediction same day
According toWith the weather forecasting data of the previous dayIt is compared, obtains front and back two days Changes in weather coefficients, enter
Step 3;
Step 3:It is to reflect whether weather occurs the threshold value of significant changes, size is by history real-time weather categorical data
The analysis that power data is collected with node obtains, comparesWith;If, then it is assumed that the day on the prediction same day and the previous day
Gas is essentially identical, direct jump procedure 4;If, then it is assumed that the weather of the prediction same day and the previous day occur significantly to become
Change, direct jump procedure 5;
Step 4:First consider the essentially identical situation of the weather of the prediction same day and the previous day, usesThe thought of algorithm;It is
Before wireless sensing net nodeItThe energy acquisition value average value of time slot,It is oneSquare
Battle array, has recorded before the time slot that will be predictedThe Changes in weather situation of a time slot, whereinBy being calculated;Be for reflecting weight, whereinIt is finally to calculate the reflection prediction same day by being calculated
With the one day Changes in weather degree in front(It is determined by predicting the historical collection power data in place);And solar energy at this time
Acquisition predicted value can be calculated directly, rear jump procedure 7;
Step 5:When the prediction same day significant changes occurring with the previous day weather, the practical data of weather forecast on the prediction same day is used
To correct prediction error;It is oneMatrix, be used to store the time slot that will predict with
And frontThe Changes in weather situation of a time slot, whereinIt is calculated by data of weather forecast, is finally calculated
Prediction same day time slot when weather significant changesAnd frontThe Changes in weather degree of a time slot, enters step 6;
Step 6:When significant changes occur for weather, it is divided into two kinds of situations, respectively weather significantly improves significantly is deteriorated with weather;This
Influence of two kinds of situations to the acquisition of solar energy uses constantTo correct;Finally, weather is calculated to occur the when significant changesItThe solar energy collecting power that time slot is predicted, enter step 7;
Step 7:Prediction result is fed back into sensor node for energy management.
2. the wireless sensing net node solar energy collecting power prediction algorithm according to claim 1 based on weather data,
It is characterized in that:In the step 2, front and back two days Changes in weather coefficientsCalculation formula be:
WhereinIt isItThe weather pattern index of time slot.
3. the wireless sensing net node solar energy collecting power prediction algorithm according to claim 1 based on weather data,
It is characterized in that:In the step 4, by comparing the energy acquisition value of the leading slots on the day of prediction with beforeIts corresponding time slot
Energy acquisition value average valueNumerical value change reflect the variation of weather conditions,Algorithm description is as follows:
Wherein,It isItThe predicted value of the solar energy collecting power of time slot,It isItTime slot
The actual observation value of solar energy collecting power,It is weight factor, and;For frontIts time slot's
The average value of solar energy collecting power,It refer to same day time slot and pastThe Changes in weather situation of its corresponding time slot,
Calculation formula is as follows:
In above formulaThe weight for being just,It is bigger, then weightAlso can be bigger, it is as follows:
It is oneMatrix has recorded before the time slot that will be predictedThe Changes in weather situation of a time slot is as follows
Formula:
In addition, being calculate by the following formula in step 4:
。
4. the wireless sensing net node solar energy collecting power prediction algorithm according to claim 1 based on weather data,
It is characterized in that:In the step 5 and step 6, definitionFor same day time slot and pastThe weather of its corresponding time slot
Situation of change,Significant changes occur for weather, define simultaneouslyThe solar energy collecting power that significantly improves for weather increases,Subtract greatly for weather significantly variation solar energy collecting power, is shown below:
By to parameterSetting constrain influence of the different Changes in weather situations to solar energy collecting power, parameterIt to be determined with solar energy acquisition situation according to actual weather condition;For front and back two days Changes in weather situations,
Shown in formula specific as follows:
Wherein,It is oneMatrix is used to store the time slot that will be predicted and frontThe weather of a time slot
Situation of change, specificallyCalculating be shown below:
In addition it introduces, it is oneMatrix, for embodying weight;Wherein,It is bigger, then weightAlso can be bigger, i.e.,
It is more important nearer it is to the Changes in weather situation for the time slot that will be predicted, shown in specific following formula:
It willWithAfter multiplication divided bySum, and final result is determined as Changes in weather situation。
5. the wireless sensing net node solar energy collecting power prediction algorithm according to claim 1 based on weather data,
It is characterized in that:In the step 6, final prediction algorithm such as following formula:
Wherein,It is to reflect whether weather occurs the threshold value of significant changes,Size be by history real-time weather type
The analysis that data and node collect power data obtains.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810383872.9A CN108573327B (en) | 2018-04-26 | 2018-04-26 | Weather data-based wireless sensor network node solar energy collection power prediction algorithm |
KR1020207033814A KR102439722B1 (en) | 2018-04-26 | 2018-10-24 | Weather data-based wireless sensor network node solar energy collection power prediction algorithm |
PCT/CN2018/111550 WO2019205528A1 (en) | 2018-04-26 | 2018-10-24 | Antenna data-based algorithm for predicting solar energy collection power of wireless sensor network node |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810383872.9A CN108573327B (en) | 2018-04-26 | 2018-04-26 | Weather data-based wireless sensor network node solar energy collection power prediction algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108573327A true CN108573327A (en) | 2018-09-25 |
CN108573327B CN108573327B (en) | 2022-03-29 |
Family
ID=63574390
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810383872.9A Active CN108573327B (en) | 2018-04-26 | 2018-04-26 | Weather data-based wireless sensor network node solar energy collection power prediction algorithm |
Country Status (3)
Country | Link |
---|---|
KR (1) | KR102439722B1 (en) |
CN (1) | CN108573327B (en) |
WO (1) | WO2019205528A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109818859A (en) * | 2019-03-07 | 2019-05-28 | 南京邮电大学 | Radio multimedia sensor network distributed image compression mechanism based on solar energy collecting |
CN109919380A (en) * | 2019-03-07 | 2019-06-21 | 南京邮电大学 | Improvement prediction technique based on exponential average UD-WCMA solar energy collecting power |
CN110070214A (en) * | 2019-04-02 | 2019-07-30 | 南京邮电大学 | D-WSMA solar energy collecting power forecasting method based on weather similarity |
WO2019205528A1 (en) * | 2018-04-26 | 2019-10-31 | 南京邮电大学 | Antenna data-based algorithm for predicting solar energy collection power of wireless sensor network node |
CN111800209A (en) * | 2020-07-01 | 2020-10-20 | 重庆邮电大学 | Solar energy prediction method based on energy model and dynamic weight factor |
CN113870531A (en) * | 2021-09-17 | 2021-12-31 | 成都理工大学 | Monitoring frequency adjusting method for geological disaster monitoring and early warning system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345227A (en) * | 2013-07-02 | 2013-10-09 | 东南大学 | Micro grid monitoring and energy management device and method |
CN103390202A (en) * | 2013-07-18 | 2013-11-13 | 华北电力大学 | Output power prediction method based on similarity data selection for photovoltaic plant |
JP2015167439A (en) * | 2014-03-03 | 2015-09-24 | 国立大学法人岐阜大学 | Power generation amount prediction system of photovoltaic power generator, and power generation amount prediction method |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102339066B (en) * | 2010-07-20 | 2013-05-08 | 中国科学院软件研究所 | Adaptive solar energy tracking method facing wireless sensor network |
KR20120072224A (en) * | 2010-12-23 | 2012-07-03 | 한국전자통신연구원 | Apparatus for controlling power of sensor nodes based on estimation of power acquisition and method thereof |
CN104219682B (en) * | 2014-08-20 | 2017-10-31 | 北京农业信息技术研究中心 | The network layer construction method and system of farmland hybrid power supply wireless sensor network |
KR101635450B1 (en) * | 2015-01-02 | 2016-07-01 | 상명대학교서울산학협력단 | PV (Photo-Voltaic) generation forecasting system for the city energy management system based on weather information |
CN106681206B (en) * | 2016-12-21 | 2018-11-02 | 南京邮电大学 | A kind of Energy-aware method of the environment self-adaption towards WSNs |
CN107182063A (en) * | 2017-05-26 | 2017-09-19 | 上海电机学院 | A kind of Cluster-Based Routing Protocols for Wireless Sensor based on natural energy |
CN108573327B (en) * | 2018-04-26 | 2022-03-29 | 南京邮电大学 | Weather data-based wireless sensor network node solar energy collection power prediction algorithm |
-
2018
- 2018-04-26 CN CN201810383872.9A patent/CN108573327B/en active Active
- 2018-10-24 KR KR1020207033814A patent/KR102439722B1/en active IP Right Grant
- 2018-10-24 WO PCT/CN2018/111550 patent/WO2019205528A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345227A (en) * | 2013-07-02 | 2013-10-09 | 东南大学 | Micro grid monitoring and energy management device and method |
CN103390202A (en) * | 2013-07-18 | 2013-11-13 | 华北电力大学 | Output power prediction method based on similarity data selection for photovoltaic plant |
JP2015167439A (en) * | 2014-03-03 | 2015-09-24 | 国立大学法人岐阜大学 | Power generation amount prediction system of photovoltaic power generator, and power generation amount prediction method |
Non-Patent Citations (2)
Title |
---|
JOAQU´IN RECAS PIORNO等: ""Prediction and management in energy harvested wireless sensor nodes"", 《2009 1STINTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATION,VEHICULAR TECHNOLOGY,INFORMATION THEORY AND AEROSPACE & ELECTRONIC SYSTEM TECHNOLOGY》 * |
李玲生等: ""基于BP神经网络的太阳能收集功率预测研究"", 《软件导刊》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019205528A1 (en) * | 2018-04-26 | 2019-10-31 | 南京邮电大学 | Antenna data-based algorithm for predicting solar energy collection power of wireless sensor network node |
CN109818859A (en) * | 2019-03-07 | 2019-05-28 | 南京邮电大学 | Radio multimedia sensor network distributed image compression mechanism based on solar energy collecting |
CN109919380A (en) * | 2019-03-07 | 2019-06-21 | 南京邮电大学 | Improvement prediction technique based on exponential average UD-WCMA solar energy collecting power |
CN109818859B (en) * | 2019-03-07 | 2020-10-09 | 南京邮电大学 | Wireless multimedia sensor network distributed image compression method based on solar energy collection |
CN109919380B (en) * | 2019-03-07 | 2022-07-29 | 南京邮电大学 | Improved prediction method based on exponential average UD-WCMA solar energy collection power |
CN110070214A (en) * | 2019-04-02 | 2019-07-30 | 南京邮电大学 | D-WSMA solar energy collecting power forecasting method based on weather similarity |
CN110070214B (en) * | 2019-04-02 | 2022-07-26 | 南京邮电大学 | D-WSMA solar energy collection power prediction method based on weather similarity |
CN111800209A (en) * | 2020-07-01 | 2020-10-20 | 重庆邮电大学 | Solar energy prediction method based on energy model and dynamic weight factor |
CN111800209B (en) * | 2020-07-01 | 2022-02-01 | 重庆邮电大学 | Solar energy prediction method based on energy model and dynamic weight factor |
CN113870531A (en) * | 2021-09-17 | 2021-12-31 | 成都理工大学 | Monitoring frequency adjusting method for geological disaster monitoring and early warning system |
Also Published As
Publication number | Publication date |
---|---|
KR20210013565A (en) | 2021-02-04 |
CN108573327B (en) | 2022-03-29 |
WO2019205528A1 (en) | 2019-10-31 |
KR102439722B1 (en) | 2022-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108573327A (en) | Wireless sensing net node solar energy collecting power prediction algorithm based on weather data | |
Bergonzini et al. | Algorithms for harvested energy prediction in batteryless wireless sensor networks | |
US20120166085A1 (en) | Solar power monitoring and predicting of solar power output | |
CN110110912A (en) | A kind of photovoltaic power multi-model interval prediction method | |
JP6003247B2 (en) | Information processing apparatus, information processing apparatus control method, and program | |
KR20210011745A (en) | Big data based energy demand and supply forecasting system and method for zero-energy town building | |
US20210305937A1 (en) | Device and method for determining whether power generation system is abnormal | |
US20220352714A1 (en) | System for estimating renewable energy generation quantity in real-time | |
Maitanova et al. | Quantifying power and energy fluctuations of photovoltaic systems | |
Jeong et al. | Predicting the long-term behavior of a micro-solar power system | |
Ren et al. | Prediction algorithm based on weather forecast for energy-harvesting wireless sensor networks | |
Agrawal et al. | Transformer‐based time series prediction of the maximum power point for solar photovoltaic cells | |
KR102478684B1 (en) | Method for predicting energy consumption for using ensemble learning, and computing apparatus for performing the method | |
CN115587664B (en) | Solar radiation prediction method and system based on graph convolution long-short-term memory network | |
Kor | Global solar radiation prediction model with random forest algorithm | |
Li et al. | Evaluation index system for photovoltaic systems statistical characteristics under hazy weather conditions in central China | |
KR20230103984A (en) | Apparatus and method for prediction of photovoltaic power generation applying algorithm based on climate cloud data | |
Jankovic et al. | Prediction of harvested energy for wireless sensor node | |
Song et al. | Combination model for day-ahead solar forecasting using local and global model input | |
KR20180023078A (en) | Prediction method of generation quantity in solar energy generation using weather information | |
Pham et al. | LS-SPP: A LSTM-Based Solar Power Prediction Method from Weather Forecast Information | |
Fu et al. | Revolutionizing solar greenhouses: A lighting environment control system for renewable vegetable cultivation, empowered by roller shutter control | |
CN116957223B (en) | Photovoltaic power prediction method and device based on illumination image | |
KR102650627B1 (en) | Power generation prediction method for distributed power plant using reinforcement learning | |
Balaji et al. | Energy prediction in IoT systems using machine learning models |
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 |