CN109508835A - A kind of wisdom Power Network Short-Term Electric Load Forecasting method of integrated environment feedback - Google Patents
A kind of wisdom Power Network Short-Term Electric Load Forecasting method of integrated environment feedback Download PDFInfo
- Publication number
- CN109508835A CN109508835A CN201910000264.XA CN201910000264A CN109508835A CN 109508835 A CN109508835 A CN 109508835A CN 201910000264 A CN201910000264 A CN 201910000264A CN 109508835 A CN109508835 A CN 109508835A
- Authority
- CN
- China
- Prior art keywords
- power
- block
- day
- cycle
- sample
- 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
- 238000013277 forecasting method Methods 0.000 title claims abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 37
- 230000007613 environmental effect Effects 0.000 claims abstract description 26
- 230000005611 electricity Effects 0.000 claims abstract description 25
- 238000004088 simulation Methods 0.000 claims description 62
- 238000012549 training Methods 0.000 claims description 61
- 238000012360 testing method Methods 0.000 claims description 43
- 238000001514 detection method Methods 0.000 claims description 42
- 238000013528 artificial neural network Methods 0.000 claims description 40
- 238000012706 support-vector machine Methods 0.000 claims description 16
- 239000012634 fragment Substances 0.000 claims description 15
- 238000012935 Averaging Methods 0.000 claims description 9
- 240000002853 Nelumbo nucifera Species 0.000 claims description 8
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims description 8
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims description 8
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 230000000052 comparative effect Effects 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 claims 1
- 230000035772 mutation Effects 0.000 abstract description 4
- 238000013507 mapping Methods 0.000 abstract description 3
- 230000037431 insertion Effects 0.000 abstract 1
- 238000003780 insertion Methods 0.000 abstract 1
- 238000002360 preparation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000013481 data capture Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000035945 sensitivity Effects 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
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- H02J3/00—Circuit arrangements for ac mains or ac distribution 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
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses a kind of wisdom Power Network Short-Term Electric Load Forecasting methods of integrated environment feedback, clustering is carried out according to the essential laws of the Power system load data of each electricity unit variation, by target prediction region division block, it establishes prediction model group respectively for block, avoids the interference of excessive correlation model；The electric load time series of each block in one week are analyzed as unit of day and prediction model is established according to its fluctuation pattern division period respectively, promote the precision of prediction of load forecast；Simultaneously, in view of the influence factor of electric load mutation, mean temperature, medial humidity and wind speed are established with the mapping relations between load forecast error, intelligence insertion external environmental factor, obtain the power load forecasting module of integrated environment feedback, significant increase susceptibility and adaptability of the prediction model to electric load catastrophic event, ensure that the robustness of prediction technique, improves the precision of prediction of short-term electric load prediction.
Description
Technical field
The invention belongs to Techniques for Prediction of Electric Loads fields, and in particular to a kind of wisdom power grid of integrated environment feedback is short-term
Methods of electric load forecasting.
Background technique
Load forecast connects the power grid energy and user demand, significant for electric energy scheduling and green power utilization, essence
Quasi- Power Network Short-Term Electric Load Forecasting method can be realized the precision management of power grid energy, be that resident stablizes electricity consumption, economy surely
Surely the important leverage developed.
Electric load time series are the synthesis results of various activities relevant to power grid, and there are certain periodicity, together
When, electric load time series have also contained the influence of external environment variable, the precision of short-term electric load prediction vulnerable to temperature,
The interference of the weather elements such as humidity.According to statistics, the big cities such as the Shenzhen of first half of the year China in 2012, Nanchang, Haikou, Xi'an are sent out
Raw totally 11 a wide range of power outages accidents, power industry think that Changes in weather causes electric load to increase sharply in a short time, and electric energy is dispatched not
It is the major reason that accident occurs in time.
Summary of the invention
For existing because of short-term electric load mutation problems caused by Climate and Environment Variation, the present invention provides a kind of fusion
The wisdom Power Network Short-Term Electric Load Forecasting method of environmental feedback is realized and promotes prediction model to the quick of electric load catastrophic event
Sensitivity and adaptability guarantee the robustness of prediction technique, improve the precision of prediction of short-term electric load prediction.
To realize the above-mentioned technical purpose, the technical solution adopted by the present invention are as follows:
A kind of wisdom Power Network Short-Term Electric Load Forecasting method of integrated environment feedback, comprising the following steps:
Step 1, all electricity unit N in target prediction region are obtained1The voltage and current historical data of a continuous cycle,
The voltage and current historical data of each electricity unit is handled to obtain corresponding power sequence, the power of all electricity units
The power training sample in sequence composition target prediction region；
It is identical as the acquisition methods of power training sample, obtain another historical time section N in target prediction region1It is a continuous
The power test sample of cycle；Every day that obtains target prediction region in the historical time section of power test sample simultaneously it is flat
Equal temperature, medial humidity and air speed data, constitute the environmental samples in target prediction region；
Step 2, according to the power sequence of electricity unit each in power training sample, each electricity unit is clustered, it will
Target prediction region division is N3A block；
Step 3, using power training sample, the power load forecasting module group based on PID neural network is established；
Step 3.1, it using all power sequences in the power training sample in each block, establishes respectively and N3A block pair
The N answered3A block power load forecasting module group；Each block power load forecasting module group includes 7 days time power load
Lotus prediction model group, wherein 7 day time power load forecasting module groups are corresponding with 7 days one week respectively；Each day time power load
Lotus prediction model group includes N4A power load forecasting module based on PID neural network, wherein N4A power load forecasting module
Respectively with one day N4A period is corresponding；
Step 3.2, all power sequences in the power training sample in each block are handled, each block is equal
Obtain corresponding electric load training sample；
Step 3.3, successively with the b days of the continuous cycle of any two in the electric load training sample of a block times the
n2The power load charge values of period as input data, with the b days of next cycle time n-th2The power load charge values of period are as output
Data, the b days times n-th of training a block2The power load forecasting module based on PID neural network of period；Wherein, a=
1,2,…,N3, b=1,2 ..., 7, n2=1,2 ..., N4；
Step 4, using power test sample and environmental samples, the environmental feedback model based on support vector machines is established:
Step 4.1, power test sample is handled by step 3.2, each block obtains corresponding electric load and surveys
Sample sheet；
Step 4.2, the current cycle of simulation and forecast, simulation and forecast cycle w are arbitrarily determined0+m0With simulation and forecast day time b0；
Step 4.3, each block is selected to correspond to simulation and forecast day time b0Day time power load forecasting module group, successively will be electric
Corresponding w in power Road test sample0- 1 cycle b0It time and w0Cycle b0The power load charge values of it each block day part are made
Day time b is corresponded to for corresponding block0The input data of the power load forecasting module based on PID neural network of corresponding period, is obtained
Obtain w0+ 1 cycle b0The electric load simulation and forecast value of it each block day part；
Step 4.4, each block is selected to correspond to simulation and forecast day time b0Day time power load forecasting module group, successively will be electric
Corresponding w in power Road test sample0Cycle b0The power load charge values and w of it each block day part0+ 1 cycle b0It time each
The electric load simulation and forecast value of block day part corresponds to day time b as corresponding block0The corresponding period based on PID neural network
Power load forecasting module input data, obtain w0+ 2 cycle b0The electric load simulation of it each block day part is pre-
Measured value；
Step 4.5, and so on, until obtaining w0+m0Cycle b0The electric load simulation of it each block day part is pre-
Measured value, by w0+m0Cycle b0The Electric Load Forecasting measured value summation of it each block day part, obtains w0+m0Cycle b0It time
Electric load simulation and forecast value；
Step 4.6, comparative simulation prediction cycle is w0+m0, simulation and forecast day time be b0Electric load simulation and forecast value with
Cycle is w in electric load test sample0+m0, day time be b0Each block day part the sum of power load charge values, obtain w0+
m0The day time of cycle is b0Electric load simulation and forecast error amount；
Step 4.7, the total N of step 4.2-4.6 is repeated5It is secondary, obtain N5A electric load simulation and forecast value and N5A electric load
Simulation and forecast error amount；
Step 4.8, by the mean temperature in simulation and forecast day in each electric load simulation and forecast value and environmental samples time, flat
Equal humidity and wind speed are used as input data, and each electric load simulation and forecast error amount is used as to output data, trained support to
Amount machine obtains the environmental feedback model based on support vector machines；
Step 5, what the power load forecasting module respectively based on PID neural network and step 4 obtained using step 3 was obtained
The electric load that environmental feedback model based on support vector machines is w+m to target prediction cycle, target prediction day time is d into
Row optimum prediction；Nearest cycle wherein comprising day time d is w；
Step 5.1, the w-1 cycle of all electricity units and the voltage and current data of w cycle are obtained, and presses step
1 is handled to obtain the power prediction sample in target prediction region；
Step 5.2, power prediction sample is handled by step 3.2, each block obtains corresponding Electric Load Forecasting
Test sample sheet；
Step 5.3, select each block day time for the day time power load forecasting module group of d；Successively by load forecast
W-1 cycle d days secondary and d days each block day parts of w cycle power load charge values correspond to day as corresponding block in sample
Secondary d corresponds to the input data of the power load forecasting module respectively based on PID neural network of period, obtains w+1 cycle d days times
The Electric Load Forecasting measured value of each block day part；
Step 5.4, select each block day time for the day time power load forecasting module group of d, successively by load forecast
The electric power of d days each block day parts of power load charge values and w+1 cycle of d days each block day parts of w cycle in sample
Predicted load corresponds to the input data of the power load forecasting module based on PID neural network of day time d as corresponding block,
Obtain the Electric Load Forecasting measured value of d days each block day parts of w+2 cycle；
Step 5.5, and so on, the Electric Load Forecasting measured value until obtaining d days each block day parts of w+m cycle,
By the Electric Load Forecasting measured value summation of d days each block day parts of w+m cycle, d days Electric Load Forecastings of w+m cycle are obtained
Measured value；
Step 5.6, according to weather forecast and weather bureau's information, obtain target prediction region target prediction cycle be w+m,
Target prediction day time is mean temperature, medial humidity and the air speed data of d, and is w+m, target prediction day by target prediction cycle
Secondary is the mean temperature of d, medial humidity, air speed data and Electric Load Forecasting measured value as the environmental feedback based on support vector machines
The input data of model, the electric load that the target prediction cycle for obtaining target prediction region is w+m, target prediction day is d
Optimum prediction value.
Further, the voltage and current historical data of each electricity unit is by the electric power detection device that is respectively arranged with identical
Frequency collection obtains, it is described to voltage and current historical data handled to obtain target prediction region power training sample and
The detailed process of power test sample is equal are as follows:
With sample moment time interval T1Voltage data and current data are divided, each sample moment time interval T is calculated1
Interior average voltage and current average, by each sample moment time interval T1Intermediate time as sample moment, will
Each sample moment time interval T1Voltage value and current value of the interior average voltage and current average as sample moment,
Using the product of each sample moment voltage value and current value as the performance number of sample moment；
The corresponding 2 sections of power being made of the performance number of different all sample moments of historical time section of each electric power detection device
The power sequence of sequence, all electric power detection devices of 2 different historical time sections separately constitutes power training sample and function
Rate test sample.
Further, the detailed process of the step 2 are as follows:
Using with the zero point in 1 day to 24 points for the secondary time interval T in day2, successively obtain in power training sample at random
Each electric power detection device N2A length is T2Power sequence segment, 10≤N2≤15；
Successively by the N of electric power detection device each in power training sample2A power sequence segment is averaged, and obtains each electric power
The power averaging sequence of detection device；
Using each electric power detection device as element p to be clusteredi, i=1,2,3..., n1, n1For the number of electric power detection device
Amount, the coordinate of element to be clustered are the power averaging sequence of corresponding electric power detection device；
Select cluster centre number for N3, k-means cluster is carried out, according to cluster result, by target prediction region division
For N3A block, 4≤N3≤ 8, each block includes several electric power detection devices.
Further, the process for carrying out k-means cluster are as follows:
Step A1 randomly chooses N using the power averaging sequence of each electric power detection device as the coordinate of element to be clustered3
For a element as cluster centre, each cluster centre represents 1 clustering cluster；
Step A2, successively calculate all elements with each cluster centre distance, and successively by each element be assigned to therewith away from
From clustering cluster representated by nearest cluster centre；
Using Euclidean distance quantization element with the distance of each cluster centre, formula is as follows:
In formula, distance (pi,kj) indicate element piWith cluster centre kjDistance,Indicate the n-th of i-th of element
A coordinate,Indicate that n-th of coordinate of j-th of cluster centre, N indicate the sample moment time interval T for including in 1 day1Number
Amount；
Step A3 calculates the average coordinates of all elements in each clustering cluster using Euclidean distance, calculates according to this each
Average coordinates in clustering cluster with each cluster centre distance, if the average coordinates of each clustering cluster are equal with the distance of each cluster centre
Less than or equal to threshold valueCluster is completed, and current cluster result is obtained；The same cluster centre of the average coordinates of any clustering cluster if it exists
Distance be greater than threshold valueUsing the average coordinates of each clustering cluster cluster centre brand new as each cluster, step A2 is gone to.
Further, threshold valueValue be 0.05.
Further, the detailed process of the step 3.2 are as follows:
Step B1 successively sums the power sequence of all electric power detection devices in block same in power training sample,
Acquisition and N3The corresponding N of a block3A block power sequence；
Step B2 successively selects the N in the block power sequence of a block by Zhou Tianci for b1A block power sequence piece
Subsample is trained for the power of b in section, composition a block day time；Wherein a=1,2 ..., N3, b=1,2 ..., 7；
Step B3 randomly chooses 20 block power sequence pieces in the power training subsample of b from a block day time
Section is averaged to obtain the block power sequence average fragment that a block day time is b；Wherein, block power sequence average fragment
In each sample moment correspond to a power average value；
A block day time is divided into N in one day for b using block power sequence average fragment by step B44A period,
Division methods are as follows: in block power sequence average fragment, if meeting latter sample moment power average value and current sample moment
The absolute difference of power average value is greater than 30% of the minimum value in two sample moment power average values, then when current sample
Carve be critical sample moment, and using critical sample moment be used as the finish time of present period, critical sample moment it is rear as
At the beginning of this moment is used as subsequent period；When block power sequence average fragment end sample moment is unsatisfactory for critical sample
Quarter condition；
Step B5 successively calculates the according to Time segments division as a result, being the power training subsample of b using a block day time
Subsample is trained for the electric load of b in a block day time；
By the performance number of each sample moment in the c period and sample moment time interval T1The sum of product, when as c
The power load charge values of section；Wherein, c=1,2 ..., N4, then 1 day N4The power load charge values composition a block day time of a period is b's
1 electric load sequence, time span N1Then correspondence obtains N for the power training subsample of a continuous cycle1A electric load sequence
Column, N1A electric load sequence composition a block day time is the electric load training subsample of b, successively takes b by 7 days of week
=1,2 ..., the electric load training sample of 7 composition a blocks.
Further, time span N1Value are as follows: N1≥50。
Further, the quantity N of electric load simulation and forecast value5Value are as follows: N5≥200。
Further, sample moment time interval T1Value be 20 minutes.
Further, the voltage and current historical data is the data after unscented kalman filter.
Beneficial effect
This programme acquires voltage, the current history data of each electricity unit simultaneously, forms power time series, sufficiently reflects
The essential laws of Power system load data variation, are classified based on Power system load data self-characteristic, study constituent parts in phase
With the rule of peak of power consumption in the period, unit similar in power sequence fluctuation pattern is clustered by clustering algorithm, most end form
At more stable block electric load time series, the complexity and polydispersity of Power system load data are reduced, for block point
Power load forecasting module group is not established and is predicted, the accuracy and stability of load forecast are improved.
Secondly, this programme, on the basis of being divided for each day by week, electricity unit is one in analysis block
The period that electricity consumption is concentrated in it, multiple stable state periods, Mei Geshi will be divided by the block power time series of length of day
Section establishes power load forecasting module respectively, further reduced the unstability of electric load number prediction, greatly improves electricity
Power load prediction precision and robustness.
Again, the influence that this programme combination temperature, humidity and wind speed Weather information go on a journey to crowd and work and rest, establishes base
In the environmental feedback model of support vector machines, Electric Load Forecasting measured value is modified, improves load forecast system, into one
Step promotes the science and accuracy of load forecast.
Detailed description of the invention
Fig. 1 is the wisdom Power Network Short-Term Electric Load Forecasting flow chart of integrated environment of the present invention feedback.
Specific embodiment
Elaborate below to the embodiment of the present invention, the present embodiment with the technical scheme is that according to development,
The detailed implementation method and specific operation process are given, is further explained explanation to technical solution of the present invention.
For short-term electric load mutation problems, the present invention proposes a kind of wisdom power grid short term power of integrated environment feedback
Load forecasting method, by clustering, using the mean power sequence in the certain time span of each department, by target prediction area
Domain divides block, establishes prediction model respectively for block, avoids the interference of excessive correlation model, reduces and calculates the same of cost pair
Guarantee load forecast precision；The electric load time series of each block in one week are analyzed as unit of day and are fluctuated according to it
Rule divides the period, establishes the period with the mapping relations between electric load stable state, reduces input data fluctuation to prediction model
Bring negative effect, promotes the precision of prediction of load forecast；Simultaneously, it is contemplated that the influence factor of electric load mutation,
Mean temperature, medial humidity and wind speed are established with the mapping relations between load forecast error, intelligence is embedded in external environment
Factor obtains the power load forecasting module of integrated environment feedback, and significant increase prediction model is to electric load catastrophic event
Susceptibility and adaptability, ensure that the robustness of prediction technique, improve the precision of prediction of short-term electric load prediction.
The present embodiment will further explain the present invention program in conjunction with attached drawing 1, specifically includes the following steps:
Step 1: installation electric power detection device obtains history voltage and current data.
Electric power detection device is successively installed respectively to electricity unit all in target prediction region；
The voltage and current historical data in each electric power detection device is acquired simultaneously with identical sample frequency, successively to each electricity
Voltage and current historical data in power detection device carries out unscented kalman filter, with sample moment time interval T1Divide filter
Voltage and current historical data after wave calculates each sample moment time interval T1The average value of interior voltage and current, will be every
A sample moment time interval T1Intermediate time as sample moment, by each sample moment time interval T1Interior voltage and electricity
Voltage and current value of the average value of stream as sample moment, using the product of each sample moment voltage value and current value as sample
The performance number at this moment obtains the power sequence of each electric power detection device, the power sequence group success of all electric power detection devices
Rate training sample；
Voltage and current history number of each electric power detection device in another historical time section is acquired with identical sample frequency
According to using data capture method identical with power training sample, acquisition power test sample；It is gentle by weather forecast simultaneously
As mean temperature, medial humidity and the air speed data of every day in office's information acquisition historical time section, environmental samples are obtained；
Voltage and current historical data collected is acquisition starting point with Monday zero point, is with 24 points of weekend
Terminating point is acquired, power training sample and power test sample standard deviation include N1The voltage and current historical data of a continuous cycle, N1
Value is at least 50；
Sample moment time interval T1Value be 20 minutes；
It include the power sequence of all sample moments in corresponding 2 sections different historical times of each electric power detection device；
In power training sample and power test sample, each power sequence contains 3 power datas per hour, respectively
For the 10th minute, the 30th minute and the 50th minute performance number；
Step 2: power training sample is utilized, by target prediction region division block；
Using with the zero point in 1 day to 24 points for the secondary time interval T in day2, successively obtain in power training sample at random
The N of each electric power detection device2A length is T2Power sequence segment, 10≤N2≤15；
Successively by the N of electric power detection device each in power training sample2A power sequence segment is averaged, and obtains power instruction
Practice the power averaging sequence of each electric power detection device in sample；
Using each electric power detection device as element to be clustered, it is denoted as pi, i=1,2,3..., n1, n1It is set for electric power detection
Standby quantity, the coordinate of element to be clustered are the power averaging sequence that electric power detection device is corresponded in power training sample；
Select cluster centre number for N3, k-means cluster is carried out, according to cluster result, by target prediction region division
For N3A block, 4≤N3≤ 8, each block contains multiple electric power detection devices, and same block may not phase on geographical location
Even；
Cluster process is as follows:
Step A1: using the power averaging sequence of electric power detection device each in power training sample as the seat of element to be clustered
Mark randomly chooses N3For a element as cluster centre, each cluster centre represents 1 clustering cluster；
Step A2: successively calculate all elements with each cluster centre distance, and successively by each element be assigned to therewith away from
From clustering cluster representated by nearest cluster centre；
Using Euclidean distance quantization element with the distance of each cluster centre, formula is as follows:
In formula, distance (pi,kj) indicate element piWith cluster centre kjDistance,Indicate the n-th of i-th of element
A coordinate,Indicate n-th of coordinate of j-th of cluster centre；
Step A3: calculating the average coordinates of all elements in each clustering cluster using Euclidean distance, calculates according to this each
Average coordinates in clustering cluster with cluster centre distance, if the average coordinates of each clustering cluster are respectively less than with the distance of cluster centre
Equal to threshold valueCluster is completed, and current cluster result is obtained；If it exists the average coordinates of any clustering cluster with cluster centre away from
From greater than threshold valueUsing the average coordinates of each clustering cluster cluster centre brand new as each cluster, step A2 is gone to；
This example, threshold valueIt is selected as 0.05.
Step 3: utilizing power training sample, establish the power load forecasting module group based on PID neural network；
Successively the power sequence of all electric power detection devices of block same in power training sample is summed, obtains N3A area
Block power sequence；
Utilize N3A block power sequence, establishes N respectively3A block power load forecasting module group, each block power load
Lotus prediction model group includes 7 days time power load forecasting module group, and 7 days time power load forecasting module groups are respectively with one
Zhou Qitian is corresponding；Total N3* 7 respectively correspond the different blocks not secondary load forecast based on PID neural network on the same day
Model group；
It is below the power load forecasting module group based on PID neural network of 7 (being assumed to be Monday) with day in block 2 time
Building process for, as shown in Figure 1, to the Electric Load Forecasting based on PID neural network in each day in one week of each block time
The building process for surveying model group is illustrated:
The N that selection current block power sequence includes1The block power sequence piece of all corresponding Mondays in a continuous cycle
Section, composition current block correspond to the power training subsample of Monday, and the power training subsample that current block corresponds to Monday includes
N1A time span is the block power sequence segment of 1 day and corresponding Monday；
20 block power sequence segments are randomly choosed from the power training subsample that current block corresponds to Monday, it will be upper
It states 20 block power sequence segments and takes 1 block power sequence average fragment of average acquisition, block power sequence average fragment
Comprising 72 (24*3) a sample moments, the corresponding power average value of each sample moment is averaged piece using block power sequence
Section, is divided into N for the Monday of current block4A period, division methods are as follows:
Remember in block power sequence average fragment, meets latter sample moment power average value and current sample moment power
30% sample moment that the absolute difference of average value is greater than the minimum value of above-mentioned two sample moment power average value is critical
Sample moment, finish time of the critical sample moment as present period, under the latter sample moment of critical sample moment is used as
At the beginning of one period；Block power sequence average fragment end sample moment is unsatisfactory for critical sample moment condition；
According to Time segments division as a result, successively calculating current block using the power training subsample that current block corresponds to Monday
The electric load training subsample of corresponding Monday, the electric load training subsample that current block corresponds to Monday includes N1A electric power
Load sequence, each electric load sequence is corresponding with the Monday in a certain week, and each electric load sequence includes N4Power load
Charge values, N4A same N of power load charge values4A period is corresponding；
In the power load charge values of a certain period i.e. period performance number Yu T product of each sample moment and；
The electric load training subsample that current block corresponds to Monday is corresponded into the refreshing based on PID of Monday as current block
The training data of power load forecasting module group through network；
The power load forecasting module group based on PID neural network that current block corresponds to Monday includes N4It is a to be based on PID
The power load forecasting module of neural network, same to N4A period is corresponding；
Successively with any two continuous cycle Monday n-th in electric load training subsample2The power load charge values of period are made
For the input data of the power load forecasting module based on PID neural network of corresponding period, n2=1,2,3 ..., N4, below
One cycle Monday n-th2Load forecast mould based on PID neural network of the power load charge values of period as the corresponding period
The output data of type, training PID neural network, obtains corresponding n-th2The load forecast based on PID neural network of period
Model；
Successively by n2From 1 value until N4, N is obtained altogether4A electric power based on PID neural network corresponding with the period respectively
Load forecasting model, to obtain the power load forecasting module group based on PID neural network that current block corresponds to Monday；
All blocks are successively selected, each block successively selects all days, is analogous to the base that a certain block corresponds to Monday
In the building process of the power load forecasting module group of PID neural network, N is obtained3* 7 power loads based on PID neural network
Lotus prediction model group.
Step 4, using power test sample and environmental samples, the environmental feedback model based on support vector machines is established；
The k-means cluster result and power test sample obtained using step 2 obtains N3A block power prediction sequence,
Each block power test sequence, that is, time span is N1The sample moment time interval of a continuous cycle is T1Continuous power
Value；
The identical sequence fragment in day time in each block power test sequence is successively selected, each block is obtained respectively and corresponds to each day
Secondary total N3* 7 power test subsamples, each power test subsample includes N1The block function that a time span is one day
Rate cycle tests segment；
The Time segments division result and N obtained using step 33* 7 power test subsamples successively calculate power test increment
Power load charge values in this in day part obtain N3* 7 electric loads test subsample, all electric loads test subsample
That is electric load test sample；
The power load forecasting module and electric load test sample respectively based on PID neural network obtained using step 3,
Carry out N5Secondary electric load simulation and forecast, N5Value is at least 200, and electric load simulation and forecast process is as follows:
The current cycle of simulation and forecast is arbitrarily determined, w is denoted as0, it is known that current cycle and pervious electric load situation, arbitrarily
Determine that simulation and forecast cycle and simulation and forecast day, note simulation and forecast cycle are w0+m0, note simulation and forecast day time is b0；
Each block is selected to correspond to simulation and forecast day time b0Time power load forecasting module of the day based on PID neural network
Group, successively by w corresponding in electric load test sample0- 1 cycle b0It time and w0Cycle b0Its secondary each block day part
Power load charge values correspond to day time b as corresponding block0The power load forecasting module based on PID neural network input number
According to acquisition w0+ 1 cycle b0The electric load simulation and forecast value of it each block day part；
Each block is selected to correspond to simulation and forecast day time b0Time power load forecasting module of the day based on PID neural network
Group, successively by w corresponding in electric load test sample0Cycle b0The power load charge values and w of it each block day part0+1
Cycle b0The electric load simulation and forecast value of it each block day part corresponds to day time b as corresponding block0Based on PID nerve
The input data of the power load forecasting module of network obtains w0+ 2 cycle b0The electric load mould of it each block day part
Quasi- predicted value；
The rest may be inferred, until obtaining w0+m0Cycle b0The electric load simulation and forecast value of it each block day part, will
W0+m0Cycle b0The Electric Load Forecasting measured value summation of it each block day part, obtains w0+m0Cycle b0The power load of it time
Lotus simulation and forecast value；
Compare w0+m0Cycle b0W in the Electric Load Forecasting measured value and electric load test sample of it time0+m0Cycle b0
The sum of the power load charge values of it each block day part obtain w0+m0Cycle b0It electric load simulation and forecast error amount；
Repeat above-mentioned electric load simulation and forecast process N5It is secondary, N is obtained altogether5A electric load simulation and forecast value and N5A electricity
Power load simulation prediction error value；
By the simulation and forecast target prediction time in the electric load simulation and forecast value and environmental samples of simulation and forecast each time
Input data as the environmental feedback model based on support vector machines of mean temperature, medial humidity and wind speed, will each time
Output data of the electric load simulation and forecast error amount of simulation and forecast as the environmental feedback model based on support vector machines, instruction
Practice support vector machines, obtains the environmental feedback model based on support vector machines；
Step 5: what the power load forecasting module respectively based on PID neural network and step 4 obtained using step 3 was obtained
Environmental feedback model based on support vector machines carries out electric load optimum prediction；
The voltage and current data that each electric power detection device includes nearest 3 cycles are obtained, according to power test in step 1
The preparation method of preparation method and step 4 the electric load test sample of sample obtains power prediction sample and Electric Load Forecasting
Test sample sheet；The voltage and current data for selecting 3 cycles herein are to guarantee to include at least day time as target prediction day
Data, to input power load forecasting module of the driving respectively based on PID neural network, final acquisition target prediction cycle target is pre-
The Electric Load Forecasting measured value of observation time.
Note target prediction cycle is w+m, and it includes target prediction day in load forecast sample that target prediction day time, which is d,
The nearest cycle of secondary d is w, and each block is selected to correspond to the day based on the PID neural network time power load forecasting module of day time d
Group, successively by w-1 cycle d days corresponding in load forecast sample secondary and d days each block day parts of w cycle electric power
Load value corresponds to the input that day time d corresponds to the power load forecasting module based on PID neural network of period as corresponding block
Data obtain the Electric Load Forecasting measured value of d days each block day parts of w+1 cycle；
Each block is selected to correspond to the power load forecasting module group based on PID neural network of day time d, successively by power load
The power load charge values of d days each block day parts of corresponding w cycle and d days each blocks of w+1 cycle are each in lotus forecast sample
The Electric Load Forecasting measured value of period corresponds to the electric load based on PID neural network that day time d corresponds to the period as corresponding block
The input data of prediction model obtains the Electric Load Forecasting measured value of d days each block day parts of w+2 cycle；
The rest may be inferred, the Electric Load Forecasting measured value until obtaining d days each block day parts of w+m cycle, by the w+m weeks
The Electric Load Forecasting measured value summation of secondary d days each block day parts obtains d days Electric Load Forecasting measured values of w+m cycle.
According to weather forecast and weather bureau's information, obtain w+m cycle d days times mean temperature, medial humidity and wind
Fast data, mean temperature, medial humidity, wind speed and the Electric Load Forecasting measured value of w+m cycle d days time are used as based on support to
The input data of the environmental feedback model of amount machine obtains w+m cycle d days times electric load optimum prediction values.
Above embodiments are preferred embodiment of the present application, those skilled in the art can also on this basis into
The various transformation of row or improvement these transformation or improve this Shen all should belong under the premise of not departing from the application total design
Within the scope of please being claimed.
Claims (10)
1. a kind of wisdom Power Network Short-Term Electric Load Forecasting method of integrated environment feedback, which comprises the following steps:
Step 1, all electricity unit N in target prediction region are obtained1The voltage and current historical data of a continuous cycle, to each
The voltage and current historical data of electricity unit is handled to obtain corresponding power sequence, the power sequence of all electricity units
Form the power training sample in target prediction region；
It is identical as the acquisition methods of power training sample, obtain another historical time section N in target prediction region1A continuous cycle
Power test sample；The average temperature for every day that obtains target prediction region in the historical time section of power test sample simultaneously
Degree, medial humidity and air speed data constitute the environmental samples in target prediction region；
Step 2, according to the power sequence of electricity unit each in power training sample, each electricity unit is clustered, by target
Estimation range is divided into N3A block；
Step 3, using power training sample, the power load forecasting module group based on PID neural network is established；
Step 3.1, it using all power sequences in the power training sample in each block, establishes respectively and N3A block is corresponding
N3A block power load forecasting module group；Each block power load forecasting module group includes 7 days time Electric Load Forecasting
Model group is surveyed, wherein 7 day time power load forecasting module groups are corresponding with 7 days one week respectively；Each day time Electric Load Forecasting
Surveying model group includes N4A power load forecasting module based on PID neural network, wherein N4A power load forecasting module difference
With one day N4A period is corresponding；
Step 3.2, all power sequences in the power training sample in each block are handled, each block obtains
Corresponding electric load training sample；
Step 3.3, successively with the b days of the continuous cycle of any two in the electric load training sample of a block times n-th2Period
Power load charge values as input data, with the b days of next cycle time n-th2The power load charge values of period as output data,
The b days times n-th of training a block2The power load forecasting module based on PID neural network of period；Wherein, a=1,
2,…,N3, b=1,2 ..., 7, n2=1,2 ..., N4；
Step 4, using power test sample and environmental samples, the environmental feedback model based on support vector machines is established:
Step 4.1, power test sample is handled by step 3.2, each block obtains corresponding electric load test specimens
This；
Step 4.2, the current cycle of simulation and forecast, simulation and forecast cycle w are arbitrarily determined0+m0With simulation and forecast day time b0；
Step 4.3, each block is selected to correspond to simulation and forecast day time b0Day time power load forecasting module group, successively by power load
Corresponding w in lotus test sample0- 1 cycle b0It time and w0Cycle b0The power load charge values conduct pair of it each block day part
Block is answered to correspond to day time b0The input data of the power load forecasting module based on PID neural network of corresponding period, obtains w0
+ 1 cycle b0The electric load simulation and forecast value of it each block day part；
Step 4.4, each block is selected to correspond to simulation and forecast day time b0Day time power load forecasting module group, successively by power load
Corresponding w in lotus test sample0Cycle b0The power load charge values and w of it each block day part0+ 1 cycle b0It each block
The electric load simulation and forecast value of day part corresponds to day time b as corresponding block0The electricity based on PID neural network of corresponding period
The input data of power load forecasting model obtains w0+ 2 cycle b0The electric load simulation and forecast value of it each block day part；
Step 4.5, and so on, until obtaining w0+m0Cycle b0The electric load simulation and forecast of it each block day part
Value, by w0+m0Cycle b0The Electric Load Forecasting measured value summation of it each block day part, obtains w0+m0Cycle b0It time
Electric load simulation and forecast value；
Step 4.6, comparative simulation prediction cycle is w0+m0, simulation and forecast day time be b0Electric load simulation and forecast value and electric power
Cycle is w in Road test sample0+m0, day time be b0Each block day part the sum of power load charge values, obtain w0+m0Week
Secondary day time is b0Electric load simulation and forecast error amount；
Step 4.7, the total N of step 4.2-4.6 is repeated5It is secondary, obtain N5A electric load simulation and forecast value and N5A electric load simulation
Prediction error value；
Step 4.8, by the mean temperature in simulation and forecast day in each electric load simulation and forecast value and environmental samples time, average wet
Degree and wind speed are as input data, using each electric load simulation and forecast error amount as output data, Training Support Vector Machines,
Obtain the environmental feedback model based on support vector machines；
Step 5, the power load forecasting module respectively based on PID neural network and step 4 obtained using step 3 obtain based on
The electric load that the environmental feedback model of support vector machines is w+m to target prediction cycle, target prediction day is d carries out most
Excellent prediction；Nearest cycle wherein comprising day time d is w；
Step 5.1, obtain the w-1 cycle of all electricity units and the voltage and current data of w cycle, and by step 1 into
Row processing obtains the power prediction sample in target prediction region；
Step 5.2, power prediction sample is handled by step 3.2, each block obtains corresponding Electric Load Forecasting test sample
This；
Step 5.3, select each block day time for the day time power load forecasting module group of d；Successively by load forecast sample
In the power load charge values of d days each block day parts of w-1 cycle d days time and w cycle as corresponding block to correspond to day d pairs secondary
The input data of the power load forecasting module respectively based on PID neural network of period is answered, the area w+1 cycle d Tian Cige is obtained
The Electric Load Forecasting measured value of block day part；
Step 5.4, select each block day time for the day time power load forecasting module group of d, successively by load forecast sample
In the power load charge values of each block day parts of w cycle d days time and the electric load of w+1 cycle d days secondary each block day parts
Predicted value corresponds to the input data of the power load forecasting module based on PID neural network of day time d as corresponding block, obtains
The Electric Load Forecasting measured value of d days each block day parts of w+2 cycle；
Step 5.5, and so on, the Electric Load Forecasting measured value until obtaining d days each block day parts of w+m cycle, by w
The Electric Load Forecasting measured value summation of d days each block day parts of+m cycle obtains d days Electric Load Forecasting measured values of w+m cycle；
Step 5.6, according to weather forecast and weather bureau's information, the target prediction cycle for obtaining target prediction region is w+m, target
Pre- observation time is mean temperature, medial humidity and the air speed data of d, and by target prediction cycle be w+m, target prediction day is
Mean temperature, medial humidity, air speed data and the Electric Load Forecasting measured value of d is as the environmental feedback model based on support vector machines
Input data, the electric load that the target prediction cycle for obtaining target prediction region is w+m, target prediction day time is d is optimal
Predicted value.
2. the method according to claim 1, wherein the voltage and current historical data of each electricity unit is by respective
The electric power detection device of setting is collected with identical frequency, described to be handled to obtain target to voltage and current historical data
The power training sample of estimation range and the detailed process of power test sample are equal are as follows:
With sample moment time interval T1Voltage data and current data are divided, each sample moment time interval T is calculated1Interior
Average voltage and current average, by each sample moment time interval T1Intermediate time as sample moment, will be each
Sample moment time interval T1Voltage value and current value of the interior average voltage and current average as sample moment, will be every
Performance number of the product of a sample moment voltage value and current value as sample moment；
The corresponding 2 sections of power sequences being made of the performance number of different all sample moments of historical time section of each electric power detection device
The power sequence of column, all electric power detection devices of 2 different historical time sections separately constitutes power training sample and power
Test sample.
3. according to the method described in claim 2, it is characterized in that, the detailed process of the step 2 are as follows:
Using with the zero point in 1 day to 24 points for the secondary time interval T in day2, each electric power in power training sample is successively obtained at random
Detection device N2A length is T2Power sequence segment, 10≤N2≤15；
Successively by the N of electric power detection device each in power training sample2A power sequence segment is averaged, and obtains each electric power detection
The power averaging sequence of equipment；
Using each electric power detection device as element p to be clusteredi, i=1,2,3..., n1, n1For the quantity of electric power detection device,
The coordinate of element to be clustered is the power averaging sequence of corresponding electric power detection device；
Select cluster centre number for N3, k-means cluster is carried out, is N by target prediction region division according to cluster result3It is a
Block, 4≤N3≤ 8, each block includes several electric power detection devices.
4. according to the method described in claim 3, it is characterized in that, the process for carrying out k-means cluster are as follows:
Step A1 randomly chooses N using the power averaging sequence of each electric power detection device as the coordinate of element to be clustered3A element
As cluster centre, each cluster centre represents 1 clustering cluster；
Step A2 successively calculates all elements with the distance of each cluster centre, and successively each element is assigned to therewith apart from most
Clustering cluster representated by close cluster centre；
Using Euclidean distance quantization element with the distance of each cluster centre, formula is as follows:
In formula, distance (pi,kj) indicate element piWith cluster centre kjDistance,Indicate n-th of seat of i-th of element
Mark,Indicate that n-th of coordinate of j-th of cluster centre, N indicate the sample moment time interval T for including in 1 day1Quantity；
Step A3, the average coordinates of all elements in each clustering cluster are calculated using Euclidean distance, calculate each cluster according to this
Average coordinates in cluster with each cluster centre distance, if the average coordinates of each clustering cluster are respectively less than with the distance of each cluster centre
Equal to threshold valueCluster is completed, and current cluster result is obtained；If it exists the average coordinates of any clustering cluster with cluster centre away from
From greater than threshold valueUsing the average coordinates of each clustering cluster cluster centre brand new as each cluster, step A2 is gone to.
5. according to the method described in claim 4, it is characterized in that, threshold valueValue be 0.05.
6. according to the method described in claim 3, it is characterized in that, the detailed process of the step 3.2 are as follows:
Step B1 successively sums the power sequence of all electric power detection devices in block same in power training sample, obtains
With N3The corresponding N of a block3A block power sequence；
Step B2 successively selects the N in the block power sequence of a block by Zhou Tianci for b1A block power sequence segment, group
It is the power training subsample of b at a block day time；Wherein a=1,2 ..., N3, b=1,2 ..., 7；
Step B3 takes from a block day time to randomly choose 20 block power sequence segments in the power training subsample of b
Average value obtains the block power sequence average fragment that a block day time is b；Wherein, every in block power sequence average fragment
A sample moment corresponds to a power average value；
A block day time is divided into N in one day for b using block power sequence average fragment by step B44A period divides
Method are as follows: in block power sequence average fragment, if meeting latter sample moment power average value and current sample moment power
The absolute difference of average value is greater than 30% of the minimum value in two sample moment power average values, then current sample moment is
Critical sample moment, and using critical sample moment as the finish time of present period, when the latter sample of critical sample moment
It carves as at the beginning of subsequent period；Block power sequence average fragment end sample moment is unsatisfactory for critical sample moment item
Part；
Step B5 successively calculates the area a according to Time segments division as a result, being the power training subsample of b using a block day time
Subsample is trained for the electric load of b in block day time；
By the performance number of each sample moment in the c period and sample moment time interval T1The sum of product, as the c period
Power load charge values；Wherein, c=1,2 ..., N4, then 1 day N4The power load charge values composition a block day time of a period is 1 of b
Electric load sequence, time span N1Then correspondence obtains N for the power training subsample of a continuous cycle1A electric load sequence,
N1A electric load sequence composition a block day time is the electric load training subsample of b, successively takes b=1 by 7 days of week,
2 ..., the electric load training sample of 7 composition a blocks.
7. the method according to claim 1, wherein time span N1Value are as follows: N1≥50。
8. the method according to claim 1, wherein the quantity N of electric load simulation and forecast value5Value are as follows: N5
≥200。
9. the method according to claim 1, wherein sample moment time interval T1Value be 20 minutes.
10. the method according to claim 1, wherein the voltage and current historical data is by unwise card
Data after Kalman Filtering.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910000264.XA CN109508835B (en) | 2019-01-01 | 2019-01-01 | Smart power grid short-term power load prediction method integrating environmental feedback |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910000264.XA CN109508835B (en) | 2019-01-01 | 2019-01-01 | Smart power grid short-term power load prediction method integrating environmental feedback |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109508835A true CN109508835A (en) | 2019-03-22 |
| CN109508835B CN109508835B (en) | 2020-11-24 |
Family
ID=65756093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910000264.XA Active CN109508835B (en) | 2019-01-01 | 2019-01-01 | Smart power grid short-term power load prediction method integrating environmental feedback |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109508835B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961187A (en) * | 2019-03-27 | 2019-07-02 | 廊坊新奥泛能网络科技服务有限公司 | ENERGY PLANNING method and ENERGY PLANNING system |
| CN111985701A (en) * | 2020-07-31 | 2020-11-24 | 国网上海市电力公司 | Power utilization prediction method based on power supply enterprise big data model base |
| CN112734096A (en) * | 2020-12-31 | 2021-04-30 | 国网山东省电力公司青岛供电公司 | Urban saturation load prediction method and system |
| CN113255973A (en) * | 2021-05-10 | 2021-08-13 | 曙光信息产业(北京)有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN115237180A (en) * | 2022-09-23 | 2022-10-25 | 济南明鑫制药股份有限公司 | Intelligent control method for crude product preparation in methyl ester production |
| CN115601198A (en) * | 2022-11-30 | 2023-01-13 | 北京志翔科技股份有限公司（Cn） | Power data simulation method, device, equipment and storage medium |
| CN115660233A (en) * | 2022-12-26 | 2023-01-31 | 尚特杰电力科技有限公司 | Photovoltaic power prediction method and device, electronic equipment and storage medium |
| CN116805785A (en) * | 2023-08-17 | 2023-09-26 | 国网浙江省电力有限公司金华供电公司 | Power load hierarchy time sequence prediction method based on random clustering |
| CN117036104A (en) * | 2023-10-08 | 2023-11-10 | 北京前景无忧电子科技股份有限公司 | Intelligent electricity utilization method and system based on electric power Internet of things |
| CN117040029A (en) * | 2023-10-08 | 2023-11-10 | 南方电网数字电网研究院有限公司 | Power distribution network power dispatching method, device, computer equipment and storage medium |
| CN117374973A (en) * | 2023-12-04 | 2024-01-09 | 国网西藏电力有限公司 | Meteorological data-based power grid load prediction method and system |
| CN117559450A (en) * | 2024-01-12 | 2024-02-13 | 吉林大学 | Method for improving non-intrusive load monitoring precision based on feedback model |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218675A (en) * | 2013-05-06 | 2013-07-24 | 国家电网公司 | Short-term load prediction method based on clustering and sliding window |
| CN103617564A (en) * | 2013-12-04 | 2014-03-05 | 国家电网公司 | Whole-network load prediction method based on local load predicted value comprehensive evaluation |
| CN105608512A (en) * | 2016-03-24 | 2016-05-25 | 东南大学 | Short-term load forecasting method |
| CN106022954A (en) * | 2016-05-16 | 2016-10-12 | 四川大学 | Multiple BP neural network load prediction method based on grey correlation degree |
| US20180114283A1 (en) * | 2016-10-21 | 2018-04-26 | Open Access Technology International, Inc. | Systems and Methods for the Optimization of User Rate Charges |
| CN108830487A (en) * | 2018-06-21 | 2018-11-16 | 王芊霖 | Methods of electric load forecasting based on long neural network in short-term |
| CN109034453A (en) * | 2018-06-21 | 2018-12-18 | 南京邮电大学 | A kind of Short-Term Load Forecasting Method based on multiple labeling neural network |
-
2019
- 2019-01-01 CN CN201910000264.XA patent/CN109508835B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218675A (en) * | 2013-05-06 | 2013-07-24 | 国家电网公司 | Short-term load prediction method based on clustering and sliding window |
| CN103617564A (en) * | 2013-12-04 | 2014-03-05 | 国家电网公司 | Whole-network load prediction method based on local load predicted value comprehensive evaluation |
| CN105608512A (en) * | 2016-03-24 | 2016-05-25 | 东南大学 | Short-term load forecasting method |
| CN106022954A (en) * | 2016-05-16 | 2016-10-12 | 四川大学 | Multiple BP neural network load prediction method based on grey correlation degree |
| US20180114283A1 (en) * | 2016-10-21 | 2018-04-26 | Open Access Technology International, Inc. | Systems and Methods for the Optimization of User Rate Charges |
| CN108830487A (en) * | 2018-06-21 | 2018-11-16 | 王芊霖 | Methods of electric load forecasting based on long neural network in short-term |
| CN109034453A (en) * | 2018-06-21 | 2018-12-18 | 南京邮电大学 | A kind of Short-Term Load Forecasting Method based on multiple labeling neural network |
Non-Patent Citations (3)
| Title |
|---|
| XISHUANG DONG等: "《Short-Term Load Forecasting in Smart Grid: A Combined CNN and K-Means Clustering Approach》", 《2017 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP)》 * |
| 刘辉等: "《基于小波分析法与滚动式时间序列法的》", 《中南大学学报（自然科学版）》 * |
| 蔡小华等: "《日电力负荷的分时段多模型组合预测》", 《计算机系统应用》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961187A (en) * | 2019-03-27 | 2019-07-02 | 廊坊新奥泛能网络科技服务有限公司 | ENERGY PLANNING method and ENERGY PLANNING system |
| CN111985701A (en) * | 2020-07-31 | 2020-11-24 | 国网上海市电力公司 | Power utilization prediction method based on power supply enterprise big data model base |
| CN111985701B (en) * | 2020-07-31 | 2024-03-01 | 国网上海市电力公司 | Power consumption prediction method based on power supply enterprise big data model base |
| CN112734096A (en) * | 2020-12-31 | 2021-04-30 | 国网山东省电力公司青岛供电公司 | Urban saturation load prediction method and system |
| CN113255973A (en) * | 2021-05-10 | 2021-08-13 | 曙光信息产业(北京)有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN115237180A (en) * | 2022-09-23 | 2022-10-25 | 济南明鑫制药股份有限公司 | Intelligent control method for crude product preparation in methyl ester production |
| CN115601198A (en) * | 2022-11-30 | 2023-01-13 | 北京志翔科技股份有限公司（Cn） | Power data simulation method, device, equipment and storage medium |
| CN115660233A (en) * | 2022-12-26 | 2023-01-31 | 尚特杰电力科技有限公司 | Photovoltaic power prediction method and device, electronic equipment and storage medium |
| CN116805785B (en) * | 2023-08-17 | 2023-11-28 | 国网浙江省电力有限公司金华供电公司 | Power load hierarchy time sequence prediction method based on random clustering |
| CN116805785A (en) * | 2023-08-17 | 2023-09-26 | 国网浙江省电力有限公司金华供电公司 | Power load hierarchy time sequence prediction method based on random clustering |
| CN117036104A (en) * | 2023-10-08 | 2023-11-10 | 北京前景无忧电子科技股份有限公司 | Intelligent electricity utilization method and system based on electric power Internet of things |
| CN117036104B (en) * | 2023-10-08 | 2024-01-09 | 北京前景无忧电子科技股份有限公司 | Intelligent electricity utilization method and system based on electric power Internet of things |
| CN117040029A (en) * | 2023-10-08 | 2023-11-10 | 南方电网数字电网研究院有限公司 | Power distribution network power dispatching method, device, computer equipment and storage medium |
| CN117040029B (en) * | 2023-10-08 | 2024-03-26 | 南方电网数字电网研究院有限公司 | Power distribution network power dispatching method, device, computer equipment and storage medium |
| CN117374973A (en) * | 2023-12-04 | 2024-01-09 | 国网西藏电力有限公司 | Meteorological data-based power grid load prediction method and system |
| CN117374973B (en) * | 2023-12-04 | 2024-03-29 | 国网西藏电力有限公司 | Meteorological data-based power grid load prediction method and system |
| CN117559450A (en) * | 2024-01-12 | 2024-02-13 | 吉林大学 | Method for improving non-intrusive load monitoring precision based on feedback model |
| CN117559450B (en) * | 2024-01-12 | 2024-03-29 | 吉林大学 | Method for improving non-intrusive load monitoring precision based on feedback model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109508835B (en) | 2020-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109508835A (en) | A kind of wisdom Power Network Short-Term Electric Load Forecasting method of integrated environment feedback | |
| CN108009938B (en) | System load clustering and load period pattern recognition method based on shape | |
| CN109919370B (en) | Power load prediction method and prediction device | |
| Dong et al. | Wind power day-ahead prediction with cluster analysis of NWP | |
| CN109376972A (en) | A kind of wisdom Power Network Short-Term Electric Load Forecasting method based on block cluster | |
| CN105260803B (en) | A kind of system power consumption prediction technique | |
| CN109870600B (en) | Non-invasive load identification method with self-learning capability and intelligent electric meter | |
| Aman et al. | Prediction models for dynamic demand response: Requirements, challenges, and insights | |
| CN104657788B (en) | Key industry electricity demand forecasting method based on Industrial Cycle index | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| CN105760970A (en) | Method for predicting AQI | |
| CN110503256A (en) | Short-term load forecasting method and system based on big data technology | |
| CN115660225A (en) | Electricity load prediction management method and system based on ammeter communication module | |
| CN105303268A (en) | Wind power generation output power prediction method based on similarity theory | |
| CN105373849A (en) | Stepped temperature prediction method for photovoltaic battery assembly | |
| CN112990597A (en) | Ultra-short-term prediction method for industrial park factory electrical load | |
| Zhao et al. | Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression | |
| Mansoor et al. | Past vector similarity for short term electrical load forecasting at the individual household level | |
| CN113988373B (en) | Multi-task massive user load prediction method based on multi-channel convolutional neural network | |
| CN105279582B (en) | Super short-period wind power prediction technique based on dynamic correlation feature | |
| CN110533243A (en) | A kind of building energy consumption prediction technique based on fractal theory | |
| CN101369322A (en) | Heat supply load interval prediction method based on chaos theory | |
| CN109978236A (en) | A kind of small power station's short term power fining prediction technique based on feature combination | |
| CN109388863A (en) | A kind of distributed photovoltaic power output power forecasting method based on ARIMA model | |
| CN109784562A (en) | A kind of wisdom grid power load forecasting method based on big data space-time cluster |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240126 Address after: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee after: Dragon totem Technology (Hefei) Co.,Ltd. Country or region after: China Address before: Yuelu District City, Hunan province 410083 Changsha Lushan Road No. 932 Patentee before: CENTRAL SOUTH University Country or region before: China |
|
| TR01 | Transfer of patent right |