CN106503848A - The load forecasting method of many small power station's bulk sale area power grids - Google Patents
The load forecasting method of many small power station's bulk sale area power grids Download PDFInfo
- Publication number
- CN106503848A CN106503848A CN201610935600.6A CN201610935600A CN106503848A CN 106503848 A CN106503848 A CN 106503848A CN 201610935600 A CN201610935600 A CN 201610935600A CN 106503848 A CN106503848 A CN 106503848A
- Authority
- CN
- China
- Prior art keywords
- rainfall
- load
- power station
- model
- critical point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013277 forecasting method Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 7
- 238000001556 precipitation Methods 0.000 claims description 6
- HEFNNWSXXWATRW-UHFFFAOYSA-N Ibuprofen Chemical compound CC(C)CC1=CC=C(C(C)C(O)=O)C=C1 HEFNNWSXXWATRW-UHFFFAOYSA-N 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000007430 reference method Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- 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
-
- 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
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/16—Energy services, e.g. dispersed generation or demand or load or energy savings aggregation
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of load forecasting method of many small power station's bulk sale area power grids, the step of including obtaining basic data；The step of load forecasting model that sets up under not condition of raining；Set up that critical point under condition of raining increases exert oneself between rainfall functional relationship model the step of；To the load forecasting model under the not condition of raining that obtains and repair the functional relationship model that exerts oneself between rainfall that critical point increases under condition of raining and be overlapped and revise, obtain final many small power station's bulk sale area power grids load forecasting model the step of.The inventive method analyzes the relation of small power station's power producing characteristics and rainfall, propose a kind of decomposition-reduction method of many small power station's bulk sale local power networks of prediction, it is specifically designed for the load prediction in many small power station's bulk sale areas, when network for the load is decomposed into not rainfall, the off line confession load prediction of equal meteorological condition and rainfall cause the load prediction of exerting oneself that small power station increases, both are reduced and obtains synthetic load curve, and predicted accurately and reliably.
Description
Technical field
The invention belongs to power system automatic field, and in particular to a kind of load of many small power station's bulk sale area power grids is pre-
Survey method.
Background technology
Short-term load forecasting is a daily groundwork of power system, and accurate load prediction curve is to formulating generating
The work of the aspects such as plan, regulating system voltage and electrical network daily operation management has important reference value.As system is advised
Mould and the continuous increase of load level, load configuration and composition tend to complicated, and various uncertain factors increase, and give load prediction work
Bring new difficulty and challenge.For improving the accuracy of load prediction, ensure supply of electric power, various places electric power to greatest extent
Department has worked out this area load prediction management evaluation method successively.
In produce reality, the factor of load level is affected mainly to have geographical environment, temperature, precipitation, big customer, great section
Holiday and socio-economic factor etc..The area such as south China, western part hydroelectric resources enriches, the small power station that certain areas are connected to the grid
Total installation of generating capacity has exceeded the peak load value of electrical network.And the electrical network of some areas property, its internal radial flow type small power station crowd
Many, the impact of the uncertainty of small power station's generation load to regional load is extremely obvious, once there is precipitation, water power inside its electrical network
, the workload demand of electrical network is greatly decreased, severe challenge is brought to load prediction work by big.
Current Load Forecasting is all concentrated on for the research of the bulk power grids such as regional grid, or is concentrated on
Load forecasting method to the area such as Large Watershed, large hydropower station, and the load of bulk power grid, large hydropower station or Large Watershed
Forecasting Methodology, the object being directed to because of which and the difference of characteristics of objects, if which is for the load prediction in the abundant area of small power station, will
Larger error can be produced, the accuracy of load prediction is had a strong impact on.
Content of the invention
It is an object of the invention to provide a kind of be specifically designed for many small power station's bulk sale area, predict accurately and reliably how little
The load forecasting method of water power bulk sale area power grid.
The load forecasting method of this many small power station's bulk sale area power grids that the present invention is provided, comprises the steps：
The step of historical load data of the geographic information data and bulk sale local power network in acquisition area to be predicted；
The step of load forecasting model that sets up under not condition of raining；
Set up that critical point under condition of raining increases exert oneself between rainfall functional relationship model the step of；
To the load forecasting model under the not condition of raining that obtains and exerting oneself and rainfall of repairing that critical point under condition of raining increases
Functional relationship model between amount is overlapped, and obtains comprehensive load prediction model, and comprehensive load prediction model is repaiied
Just, obtain final many small power station's bulk sale area power grids load forecasting model the step of.
The described load forecasting model that sets up under not condition of raining, specifically includes following steps：
I according to obtain data, grid load curve during not rainfall is analyzed, set up not rainfall when temperature,
Forecast model between festivals or holidays factor and network load；
II forecast model obtained according to step I carries out load prediction to network for the load during not rainfall, and set up temperature,
Model between festivals or holidays and prediction deviation, and pass through variance analyses correction step 1) coefficient in the forecast model that obtains, obtain
Load forecasting model under revised not condition of raining.
Described in step I set up not rainfall when temperature, the forecast model between festivals or holidays factor and network load, specifically
It is using temperature during short-term load forecasting method foundation not rainfall, the forecast model between festivals or holidays factor and network load.
Described sets up the functional relationship model that exerts oneself between rainfall that critical point increases under condition of raining, specifically includes
Following steps：
A. according to the data for obtaining, the size according to rainfall is classified to rainfall, and chooses only to go out containing small power station
The metering critical point data of power are analyzed and are obtained the critical point in the case of different rainfall classifications and exert oneself change function as sample；
B. the critical point in the case of the different rainfalls for being obtained according to step A is exerted oneself change function, for each class rainfall
Situation, the critical point increased after obtaining rainfall is exerted oneself change function, and change function that the critical point increased after rainfall is exerted oneself is carried out
Weighted average, obtains the function that exerts oneself between rainfall of critical point increase；
C. according to the data for obtaining, the function that exerts oneself between rainfall that the critical point obtained by step B increases is repaiied
Just, the function that exerts oneself between rainfall that revised critical point increases is obtained.
The size according to rainfall described in step A is classified to rainfall, specially according to existing meteorological rule,
Rainfall is divided into light rain, moderate rain, four grades of heavy rain and heavy rain.
Described in step A～step C obtain critical point increase the function that exerts oneself between rainfall and revise, specifically include
Following steps：
1) search history sample day one by one, if jth day t has precipitation, recurrence sample set R=is included into the day
{D1, D2..., DrIn, wherein r is sample size；
2) according to light rain, moderate rain, heavy rain, four grades of heavy rain, the data in sample set R are screened, is included into new
Sample set R1={ D1, D2..., Dm, R2={ D1, D2..., Dm, R3={ D1, D2..., Dm, R4={ D1, D2..., DmIn, its
Middle R1For light rain sample set, R2For moderate rain sample set, R3For heavy rain sample set, R4For heavy rain sample set；
3) respectively the data in four sample sets are processed, the power curve in each sample set is entered using following formula
Row weighted average：
In formula, βiFor weight coefficient, β is met1+β2+…+βm=1, and βi=βi-1+1/m(1<i<M), LDiFor DiDrop
Rainfall；
Choose sample set RmThe middle quadratic sum for calculating each sample curve and weighted average curve difference, carries out deviation point
Analysis, i.e.,：
Different βs are chosen respectivelyiBring calculating Q in above formula intom, work as QmWhen minimum, the aim curve that obtainsAs the drop
The prediction curve that small power station exerts oneself under the conditions of rain；
4) Function Fitting is carried out to prediction curve, obtains small power station and exert oneself and rainfall and the relational expression at rainfall moment：
Pit=f (T, D)
In formula, T is rainfall start time, and D is rainfall；
5) water power power curve { P i+1 day increased using function model(i+1}1, P(i+1}2, P(i+1}3..., P(i+1}T}
Be predicted, will predict the outcome and variance analyses 3) are carried out with repeat step of actually exerting oneself, and revise forecast model.
The load forecasting method of this many small power station's bulk sale area power grids that the present invention is provided, for many small power station's bulk sale ground
The characteristic of area's electrical network is analyzed, and considers rainfall and the operation of power networks historical data in area, by many small power station's bulk sale area
Load prediction during load prediction and rainfall when the load prediction of electrical network is decomposed into not rainfall, is not dropped using prior art
Load forecasting model during rain, and load forecasting model when setting up rainfall according to history run condition, finally will not rainfall when
Load forecasting model and load forecasting model during rainfall be overlapped, so as to obtain final many small power station's bulk sale areas electricity
The load forecasting model of net；The inventive method analyzes the relation of small power station's power producing characteristics and rainfall, proposes a kind of prediction many
The decomposition-reduction method of small power station's bulk sale local power network, is specifically designed for the load prediction in many small power station's bulk sale areas, by network for the load
When being decomposed into not rainfall, the off line confession load prediction of equal meteorological condition and rainfall cause the load prediction of exerting oneself that small power station increases, will
Both reduction obtain synthetic load curve, and predict accurately and reliably, give valuable many small power station's bulk sale area power grids
Load prediction reference method.
Description of the drawings
Schematic diagrams of the Fig. 1 for the inventive method.
Flow charts of the Fig. 2 for the inventive method.
Specific embodiment
It is illustrated in figure 1 the schematic diagram of the inventive method：This many small power station's bulk sale areas electricity that the inventive method is provided
The load forecasting method of net, its core concept are that and network for the load are decomposed into load that small power station increases because of rainfall and are not dropped
Equal weather during rain, under the conditions of festivals or holidays, critical point bulk sale load is predicted respectively.For critical point load prediction during not rainfall, can profit
With conventional method, such as pattern-recongnition method, superimposed curves method etc. is predicted；For the load that small power station increases, by analysis
The regularity that small power station exerts oneself inside electrical network, individually predicts other side's electrical network water power load using specific process, then by two parts
Predict the outcome and synthesize and restore network for the load, its thinking is decomposition → prediction → reduction.
It is illustrated in figure 2 the flow chart of the inventive method：This many small power station's bulk sale areas electricity that the inventive method is provided
The load forecasting method of net, comprises the steps：
S1. the historical load data of the geographic information data and bulk sale local power network in area to be predicted is obtained；
S2. the data for being obtained according to step S1, are analyzed to grid load curve during not rainfall, using short term
Temperature, the forecast model between festivals or holidays factor and network load during Forecasting Methodology foundation not rainfall；
S3. the forecast model for being obtained according to step S2 carries out load prediction to network for the load during not rainfall, and sets up gas
Coefficient in temperature, the model between festivals or holidays and prediction deviation, and the forecast model obtained by variance analyses correction step S2,
Obtain the load forecasting model under revised not condition of raining；
S4. the data for being obtained according to step S1, the size according to rainfall are classified to rainfall, according to existing gas
As rule, rainfall is divided into light rain, moderate rain, four grades of heavy rain and heavy rain；And the metering critical point that only exerts oneself is chosen containing small power station
Data are analyzed and are obtained the critical point in the case of different rainfall classifications and exert oneself change function as sample；
S5. the critical point in the case of the different rainfalls for being obtained according to step S4 is exerted oneself change function, for each class rainfall
The situation of amount, the critical point increased after obtaining rainfall are exerted oneself change function, and change function that the critical point increased after rainfall is exerted oneself enters
Row weighted average, obtains the function that exerts oneself between rainfall of critical point increase；
S6. the data for being obtained according to step S1, the letter that exerts oneself between rainfall that the critical point obtained by step S5 increases
Number is modified, and obtains the function that exerts oneself between rainfall that revised critical point increases；
The function that exerts oneself between rainfall for obtaining critical point increase described in step S4～step S6 is simultaneously revised, and concrete is wrapped
Include following steps：
1) search history sample day one by one, if jth day t has precipitation, recurrence sample set R=is included into the day
{D1, D2..., DrIn, wherein r is sample size；
2) according to light rain, moderate rain, heavy rain, four grades of heavy rain, the data in sample set R are screened, is included into new
Sample set R1={ D1, D2..., Dm, R2={ D1, D2..., Dm, R3={ D1, D2..., Dm, R4={ D1, D2..., DmIn, its
Middle R1For light rain sample set, R2For moderate rain sample set, R3For heavy rain sample set, R4For heavy rain sample set；
3) respectively the data in four sample sets are processed, the power curve in each sample set is entered using following formula
Row weighted average：
In formula, βiFor weight coefficient, β is met1+β2+…+βm=1, and βi=βi-1+1/m(1<i<M), LDiFor DiDrop
Rainfall；
Choose sample set RmThe middle quadratic sum for calculating each sample curve and weighted average curve difference, carries out deviation point
Analysis, i.e.,：
Different βs are chosen respectivelyiBring calculating Q in above formula intom, work as QmWhen minimum, the aim curve that obtainsAs the drop
The prediction curve that small power station exerts oneself under the conditions of rain；
4) Function Fitting is carried out to prediction curve, obtains small power station and exert oneself and rainfall and the relational expression at rainfall moment：
Pit=f (T, D)
In formula, T is rainfall start time, and D is rainfall；
5) water power power curve { P i+1 day increased using function model(i+1}1, P(i+1}2, P(i+1}3..., P(i+1}T}
Be predicted, will predict the outcome and variance analyses 3) are carried out with repeat step of actually exerting oneself, and revise forecast model；
S7. the load forecasting model under the revised not condition of raining for step S3 being obtained, and repairing of obtaining of step S6
The function that exerts oneself between rainfall that critical point after just increases is overlapped, and obtains comprehensive load prediction model, and to synthesis
Load forecasting model is modified, and obtains the load forecasting model of final many small power station's bulk sale area power grids.
Method schematic diagram according to Fig. 1 is it is recognised that step S2 and step S3 in the inventive method are to set up not
Load forecasting model during rainfall under equal conditions, step S4～step S6 be the small power station increased when setting up rainfall exert oneself negative
Lotus forecast model；Therefore the step of the inventive method in, step S2 and step S3 are overall as first, step S4 and step S6
Overall as second, described first overall and second overall can exchange, i.e., the inventive method the step of can also be as
Lower form：
S1. the historical load data of the geographic information data and bulk sale local power network in area to be predicted is obtained；
S2. the data for being obtained according to step S1, the size according to rainfall are classified to rainfall, according to existing gas
As rule, rainfall is divided into light rain, moderate rain, four grades of heavy rain and heavy rain；And the metering critical point that only exerts oneself is chosen containing small power station
Data are analyzed and are obtained the critical point in the case of different rainfall classifications and exert oneself change function as sample；
S3. the critical point in the case of the different rainfalls for being obtained according to step S2 is exerted oneself change function, for each class rainfall
The situation of amount, the critical point increased after obtaining rainfall are exerted oneself change function, and change function that the critical point increased after rainfall is exerted oneself enters
Row weighted average, obtains the function that exerts oneself between rainfall of critical point increase；
S4. the data for being obtained according to step S1, the letter that exerts oneself between rainfall that the critical point obtained by step S3 increases
Number is modified, and obtains the function that exerts oneself between rainfall that revised critical point increases；
The function that exerts oneself between rainfall for obtaining critical point increase described in step S2～step S4 is simultaneously revised, and concrete is wrapped
Include following steps：
1) search history sample day one by one, if jth day t has precipitation, recurrence sample set R=is included into the day
{D1, D2..., DrIn, wherein r is sample size；
2) according to light rain, moderate rain, heavy rain, four grades of heavy rain, the data in sample set R are screened, is included into new
Sample set R1={ D1, D2..., Dm, R2={ D1, D2..., Dm, R3={ D1, D2..., Dm, R4={ D1, D2..., DmIn, its
Middle R1For light rain sample set, R2For moderate rain sample set, R3For heavy rain sample set, R4For heavy rain sample set；
3) respectively the data in four sample sets are processed, the power curve in each sample set is entered using following formula
Row weighted average：
In formula, βiFor weight coefficient, β is met1+β2+…+βm=1, and βi=βi-1+1/m(1<i<M), LDiFor DiDrop
Rainfall；
Choose sample set RmThe middle quadratic sum for calculating each sample curve and weighted average curve difference, carries out deviation point
Analysis, i.e.,：
Different βs are chosen respectivelyiBring calculating Q in above formula intom, work as QmWhen minimum, the aim curve that obtainsAs the drop
The prediction curve that small power station exerts oneself under the conditions of rain；
4) Function Fitting is carried out to prediction curve, obtains small power station and exert oneself and rainfall and the relational expression at rainfall moment：
Pit=f (T, D)
In formula, T is rainfall start time, and D is rainfall；
5) water power power curve { P i+1 day increased using function model(i+1}1, P(i+1}2, P(i+1}3..., P(i+1}T}
Be predicted, will predict the outcome and variance analyses 3) are carried out with repeat step of actually exerting oneself, and revise forecast model；
S5. the data for being obtained according to step S1, are analyzed to grid load curve during not rainfall, using short term
Temperature, the forecast model between festivals or holidays factor and network load during Forecasting Methodology foundation not rainfall；
S6. the forecast model for being obtained according to step S5 carries out load prediction to network for the load during not rainfall, and sets up gas
Coefficient in temperature, the model between festivals or holidays and prediction deviation, and the forecast model obtained by variance analyses correction step S5,
Obtain the load forecasting model under revised not condition of raining；
S7. the load forecasting model under the revised not condition of raining for step S6 being obtained, and repairing of obtaining of step S4
The function that exerts oneself between rainfall that critical point after just increases is overlapped, and obtains comprehensive load prediction model, and to synthesis
Load forecasting model is modified, and obtains the load forecasting model of final many small power station's bulk sale area power grids.
Claims (6)
1. a kind of load forecasting method of many small power station's bulk sale area power grids, comprises the steps：
The step of historical load data of the geographic information data and bulk sale local power network in acquisition area to be predicted；
The step of load forecasting model that sets up under not condition of raining；
Set up that critical point under condition of raining increases exert oneself between rainfall functional relationship model the step of；
To the load forecasting model under the not condition of raining that obtains and exerting oneself of repairing that critical point under condition of raining increases and rainfall it
Between functional relationship model be overlapped, obtain comprehensive load prediction model, and comprehensive load prediction model be modified, obtain
To final many small power station's bulk sale area power grids load forecasting model the step of.
2. the load forecasting method of many small power station's bulk sale area power grids according to claim 1, it is characterised in that described
The load forecasting model that sets up under not condition of raining, specifically includes following steps：
I, according to the data for obtaining, is analyzed to grid load curve during not rainfall, and the temperature, section during foundation not rainfall is false
Forecast model between day factor and network load；
II forecast model obtained according to step I carries out load prediction to network for the load during not rainfall, and it is false to set up temperature, section
Day and the model between prediction deviation, and pass through variance analyses correction step 1) coefficient in the forecast model that obtains, repaiied
The load forecasting model under not condition of raining after just.
3. the load forecasting method of many small power station's bulk sale area power grids according to claim 2, it is characterised in that step I institute
Temperature, the forecast model between festivals or holidays factor and network load during the foundation not rainfall that states, specially adopts short term
Temperature, the forecast model between festivals or holidays factor and network load during Forecasting Methodology foundation not rainfall.
4. the load forecasting method of many small power station's bulk sale area power grids according to one of claims 1 to 3, it is characterised in that
Described sets up the functional relationship model that exerts oneself between rainfall that critical point increases under condition of raining, specifically includes following step
Suddenly：
A. according to the data that obtain, the size according to rainfall is classified to rainfall, and chooses and only exert oneself containing small power station
Metering critical point data are analyzed and are obtained the critical point in the case of different rainfall classifications and exert oneself change function as sample；
B. the critical point in the case of the different rainfalls for being obtained according to step A is exerted oneself change function, for the feelings of each class rainfall
Condition, the critical point increased after obtaining rainfall are exerted oneself change function, and change function that the critical point increased after rainfall is exerted oneself is weighted
Averagely, the function that exerts oneself between rainfall of critical point increase is obtained；
C. according to the data for obtaining, the function that exerts oneself between rainfall that the critical point obtained by step B increases is modified, obtains
To the function that exerts oneself between rainfall that revised critical point increases.
5. the load forecasting method of many small power station's bulk sale area power grids according to claim 14, it is characterised in that step A
The described size according to rainfall is classified to rainfall, specially according to existing meteorological rule, rainfall is divided into little
Rain, moderate rain, four grades of heavy rain and heavy rain.
6. the load forecasting method of many small power station's bulk sale area power grids according to claim 5, it is characterised in that step A～
Described in step C obtain critical point increase the function that exerts oneself between rainfall and revise, specifically include following steps：
1) search history sample day one by one, if jth day t has precipitation, recurrence sample set R={ D is included into the day1,
D2..., DrIn, wherein r is sample size；
2) according to light rain, moderate rain, heavy rain, four grades of heavy rain, the data in sample set R is screened, new sample is included into
Collection R1={ D1, D2..., Dm, R2={ D1, D2..., Dm, R3={ D1, D2..., Dm, R4={ D1, D2..., DmIn, wherein R1
For light rain sample set, R2For moderate rain sample set, R3For heavy rain sample set, R4For heavy rain sample set；
3) respectively the data in four sample sets are processed, the power curve in each sample set is carried out using following formula plus
Weight average：
In formula, βiFor weight coefficient, β is met1+β2+…+βm=1, and βi=βi-1+ 1/m, 1<i<M, LDiFor DiRainfall；
Choose sample set RmThe middle quadratic sum for calculating each sample curve and weighted average curve difference, carries out variance analyses,
I.e.：
Different βs are chosen respectivelyiBring calculating Q in above formula intom, work as QmWhen minimum, the aim curve that obtainsAs the rainfall bar
The prediction curve that Jian Xia small power stations exert oneself；
4) Function Fitting is carried out to prediction curve, obtains small power station and exert oneself and rainfall and the relational expression at rainfall moment：
Pit=f (T, D)
In formula, T is rainfall start time, and D is rainfall；
5) water power power curve { P i+1 day increased using function model(i+1}1, P(i+1}2, P(i+1}3..., P(i+1}TCarry out
Prediction, will predict the outcome and 3) carry out variance analyses with repeat step of actually exerting oneself, revise forecast model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610935600.6A CN106503848A (en) | 2016-11-01 | 2016-11-01 | The load forecasting method of many small power station's bulk sale area power grids |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610935600.6A CN106503848A (en) | 2016-11-01 | 2016-11-01 | The load forecasting method of many small power station's bulk sale area power grids |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106503848A true CN106503848A (en) | 2017-03-15 |
Family
ID=58320017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610935600.6A Pending CN106503848A (en) | 2016-11-01 | 2016-11-01 | The load forecasting method of many small power station's bulk sale area power grids |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106503848A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609716A (en) * | 2017-10-12 | 2018-01-19 | 华中科技大学 | A kind of power station load setting Forecasting Methodology |
| CN107769268A (en) * | 2017-10-10 | 2018-03-06 | 三峡大学 | Scope is adjusted to predict that province supplies load method a few days ago in a kind of ground containing small power station |
| CN109934395A (en) * | 2019-03-04 | 2019-06-25 | 三峡大学 | A kind of more small power station areas Short-Term Load Forecasting Method based on timesharing subregion meteorological data |
| CN109978236A (en) * | 2019-03-04 | 2019-07-05 | 三峡大学 | A kind of small power station's short term power fining prediction technique based on feature combination |
| CN115640884A (en) * | 2022-10-11 | 2023-01-24 | 国网浙江省电力有限公司嘉兴供电公司 | Power grid load scheduling method based on rainfall |
-
2016
- 2016-11-01 CN CN201610935600.6A patent/CN106503848A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107769268A (en) * | 2017-10-10 | 2018-03-06 | 三峡大学 | Scope is adjusted to predict that province supplies load method a few days ago in a kind of ground containing small power station |
| CN107769268B (en) * | 2017-10-10 | 2021-03-09 | 三峡大学 | Method for predicting provincial supply load day by day in regional dispatching range containing small hydropower stations |
| CN107609716A (en) * | 2017-10-12 | 2018-01-19 | 华中科技大学 | A kind of power station load setting Forecasting Methodology |
| CN109934395A (en) * | 2019-03-04 | 2019-06-25 | 三峡大学 | A kind of more small power station areas Short-Term Load Forecasting Method based on timesharing subregion meteorological data |
| CN109978236A (en) * | 2019-03-04 | 2019-07-05 | 三峡大学 | A kind of small power station's short term power fining prediction technique based on feature combination |
| CN109978236B (en) * | 2019-03-04 | 2022-07-15 | 三峡大学 | Small hydropower station short-term power refined prediction method based on feature combination |
| CN109934395B (en) * | 2019-03-04 | 2023-05-02 | 三峡大学 | Multi-hydropower-region short-term power load prediction method based on time-sharing and regional meteorological data |
| CN115640884A (en) * | 2022-10-11 | 2023-01-24 | 国网浙江省电力有限公司嘉兴供电公司 | Power grid load scheduling method based on rainfall |
| CN115640884B (en) * | 2022-10-11 | 2023-12-22 | 国网浙江省电力有限公司嘉兴供电公司 | Power grid load scheduling method based on rainfall |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A review of wind power forecasting models | |
| CN106503848A (en) | The load forecasting method of many small power station's bulk sale area power grids | |
| CN103996082B (en) | A kind of intensity of solar radiation Forecasting Methodology theoretical based on dual random | |
| CN103713336B (en) | Based on the hydropower station basin areal rainfall meteorology forecast of GIS subarea | |
| Wang et al. | Reliable-economical equilibrium based short-term scheduling towards hybrid hydro-photovoltaic generation systems: Case study from China | |
| CN107992961A (en) | A kind of adaptive basin Medium-and Long-Term Runoff Forecasting model framework method | |
| Monforti et al. | Comparing the impact of uncertainties on technical and meteorological parameters in wind power time series modelling in the European Union | |
| CN106351793A (en) | System and method for improved wind power generation | |
| CN105631558A (en) | BP neural network photovoltaic power generation system power prediction method based on similar day | |
| CN104463349A (en) | Photovoltaic generated power prediction method based on multi-period comprehensive similar days | |
| CN103683274B (en) | Regional long-term wind power generation capacity probability prediction method | |
| CN107862466A (en) | The source lotus complementary Benefit Evaluation Method spanning space-time of consideration system bilateral randomness | |
| CN106228278A (en) | Photovoltaic power prognoses system | |
| CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
| CN110097220B (en) | Method for predicting monthly electric quantity of wind power generation | |
| CN109934395B (en) | Multi-hydropower-region short-term power load prediction method based on time-sharing and regional meteorological data | |
| CN104463358A (en) | Small hydropower station power generation capacity predicating method combining coupling partial mutual information and CFS ensemble forecast | |
| CN105184388A (en) | Non-linear regression method for urban power load short-period prediction | |
| CN104200289A (en) | Distributed photovoltaic installed capacity prediction method based on investment return rate | |
| Yang et al. | Photovoltaic power forecasting with a rough set combination method | |
| CN104915727A (en) | Multi-dimensional isomorphic heterogeneous BP neural network optical power ultrashort-term prediction method | |
| Deng et al. | A survey of the researches on grid-connected solar power generation systems and power forecasting methods based on ground-based cloud atlas | |
| CN105373847A (en) | Hydropower station reservoir pre-discharge decision method based on CFS forecast product | |
| Jagadeesh et al. | Forecasting the probability of solar power output using logistic regression algorithm | |
| Panjwani et al. | Short-term solar and wind generation forecasting for the western region of india |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |