CN114662800A - Wind power prediction method and system based on artificial neural network - Google Patents
Wind power prediction method and system based on artificial neural network Download PDFInfo
- Publication number
- CN114662800A CN114662800A CN202210536724.2A CN202210536724A CN114662800A CN 114662800 A CN114662800 A CN 114662800A CN 202210536724 A CN202210536724 A CN 202210536724A CN 114662800 A CN114662800 A CN 114662800A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- power
- wind
- level
- machine
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 60
- 238000010248 power generation Methods 0.000 claims abstract description 38
- 238000009825 accumulation Methods 0.000 claims description 10
- 238000007664 blowing Methods 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 6
- 238000003379 elimination reaction Methods 0.000 claims description 6
- 230000003203 everyday effect Effects 0.000 claims description 6
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Wind Motors (AREA)
Abstract
The invention provides a wind power prediction method and a wind power prediction system based on an artificial neural network, wherein the prediction system comprises a wind speed model establishing module, a single-machine power prediction module and a regional power prediction module; the wind speed model building module is used for acquiring and processing annual wind speed data of a prediction area; the wind speed model building module comprises a wind speed classification unit, a single-day wind speed processing unit, a single-month wind speed summarizing unit and a whole-year wind speed summarizing unit; the wind speed classification unit is used for classifying effective wind speeds; the single-day wind speed processing unit is used for summarizing the wind speed duration of a single day; the method can predict annual generated power of a certain region based on the annual wind speed model and the power conversion efficiency of the wind driven generator, and solves the problems that the existing wind power generation power prediction is more general and the prediction is not accurate enough.
Description
Technical Field
The invention relates to the technical field of wind power prediction, in particular to a wind power prediction method and a wind power prediction system based on an artificial neural network.
Background
The wind power prediction technology is used for predicting the power output by a wind power place in a future period of time so as to arrange a scheduling plan. This is because wind energy belongs to unstable energy with random fluctuation, and large-scale wind power is incorporated into the system, which inevitably brings new challenges to the stability of the system. The power generation dispatching mechanism needs to know the wind power output power for hours in the future, the artificial neural network abstracts the human brain neural network from the information processing perspective, establishes a certain simple model, and forms different networks according to different connection modes. The neural network is an operational model, which is formed by connecting a large number of nodes (or called neurons). Each node represents a particular output function.
In the prior art, in the process of predicting the wind power, single wind speed conversion is generally adopted to obtain, and in the process, the data of the wind speed is not comprehensive enough, and meanwhile, the power conversion of a final generator is not accurate enough, so that the final power generation prediction result is not accurate enough, and misleading is caused to the power generation construction in the early stage.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a wind power prediction method and system based on an artificial neural network, which can predict annual generated power of a certain region based on an annual wind speed model and the power conversion efficiency of a wind driven generator, so as to solve the problems that the existing wind power prediction is more general and the prediction is not accurate enough.
In order to achieve the purpose, the invention is realized by the following technical scheme: a wind power prediction system based on an artificial neural network comprises a wind speed model building module, a single machine power prediction module and an area power prediction module; the wind speed model building module is used for acquiring and processing annual wind speed data of a prediction area; the wind speed model building module comprises a wind speed classification unit, a single-day wind speed processing unit, a single-month wind speed summarizing unit and a whole-year wind speed summarizing unit; the wind speed classification unit is used for classifying effective wind speeds; the single-day wind speed processing unit is used for summarizing the wind speed duration of a single day; the single-month wind speed summarizing unit is used for summarizing the whole-month wind speed based on the single-day wind speed processing result; the annual wind speed summarizing unit is used for summarizing the comprehensive wind speed based on the summarizing result of the monthly wind speed summarizing unit;
the single-machine power prediction module is used for predicting the annual power generation power of the single machine in the prediction region based on annual wind speed data; the regional power prediction module is used for predicting regional generated power in a prediction region based on the annual generated power of the single machine.
Further, the wind speed classification unit is configured with a wind speed classification strategy comprising: dividing the effective wind speed into a first level to a tenth level according to the grade of the wind speed;
the single-day wind speed processing unit is configured with a single-day wind speed summarizing strategy, and the single-day wind speed summarizing strategy comprises the following steps: respectively counting the effective wind speed durations of the first level to the tenth level in a single day, and respectively marking the effective wind speed durations of the first level to the tenth level in the single day as Vd 1-Vd 12;
the single-month wind speed summarizing unit is configured with a single-month wind speed summarizing strategy, and the single-month wind speed summarizing strategy comprises the following steps: respectively accumulating the wind speed durations from the first level to the twelfth level every day in a single month, and respectively marking the wind speed durations from the first level to the twelfth level in the single month as Vm 1-Vm 12;
the annual wind speed summarizing unit is configured with an annual wind speed summarizing strategy, and the annual wind speed summarizing strategy comprises the following steps: wind speed durations of the first level to the tenth level in each month in the whole year are respectively accumulated, and the wind speed durations of the first level to the tenth level in a single month are respectively marked as Vy1 to Vy 12.
Further, the stand-alone power prediction module includes a wind speed conversion unit configured with a wind speed conversion strategy, the wind speed conversion strategy including: when the annual generated power of a single machine is predicted, the wind speed time from the first level to the twelfth level of the year is respectively substituted into a wind speed power conversion formula to obtain the wind speed conversion power from the first level to the twelfth level;
substituting the wind speed conversion power from the first stage to the twelfth stage into a single-machine power accumulation formula to obtain the single-machine standard annual power generation power;
the stand-alone power prediction module further comprises a loss cancellation unit configured with a loss cancellation strategy comprising: placing a single-machine wind driven generator in a wind power generation laboratory, blowing the single-machine wind driven generator to the wind driven generator at the wind speeds of the first stage to the twelfth stage respectively, continuously generating power for a first test duration in the wind speed test state of each stage, and acquiring the actual power generation power of each stage of wind driven generator in the first test duration;
substituting the wind speed duration from the first stage to the twelfth stage of the whole year and the actual generated power corresponding to the wind speed of each stage into a loss elimination power conversion formula to obtain the single-machine actual whole year generated power.
Further, the wind speed power conversion formula is configured to:(ii) a The stand-alone power accumulation formula is configured to:(ii) a Wfz is wind speed conversion power, Wfz 1-Wfz 12 is wind speed conversion power of first-level to twelfth-level wind speeds all year around, Vi is a representative character of wind speed duration of the first-level to twelfth-level all year around, Wbdq is single-machine standard all year electricity generation power, a1 is smaller than zero, b1 is larger than zero, the absolute value of a1 is smaller than b1, and w1 is a single-machine all year around month compensation coefficient;
the loss cancellation power conversion equation is configured to:(ii) a Wherein, Wsdq is the actual annual generated power of the single machine, Vc1 is the first test duration, and Wsi represents the actual generated power of each stage of wind driven generator under the first test duration.
Further, the area power prediction module is configured with an area power prediction strategy, which includes: acquiring installed power of wind driven generators needing to be arranged in a prediction region, and substituting the installed power of each wind driven generator, the test power of the wind driven generators in the single-machine power prediction module and the actual annual generating power of the single machine into a single-machine power conversion formula to obtain the predicted power of each wind driven generator;
and accumulating the predicted power of each wind driven generator to obtain the regional predicted power generation power.
Further, the stand-alone power conversion formula is configured to:(ii) a Wyc is the predicted power of each generator, Wzjn is the installed power of each generator, and Wyzj is the test power of the wind driven generator in the single-machine power prediction module.
A wind power prediction method based on an artificial neural network comprises the following steps:
step S1, classifying the wind speeds, respectively acquiring the wind speed duration of a single day, then acquiring the wind speed duration of a single month, and finally summarizing the wind speed duration of the whole year;
step S2, predicting annual generated power of the single machines in the prediction area based on annual wind speed data;
step S3, the regional generated power in the predicted region is predicted based on the annual generated power of the single machine.
Further, the step S1 further includes: dividing the effective wind speed into a first level to a tenth level according to the grade of the wind speed; respectively counting the effective wind speed durations of the first level to the tenth level in a single day, and respectively marking the effective wind speed durations of the first level to the tenth level in the single day as Vd 1-Vd 12; respectively accumulating the wind speed durations from the first level to the twelfth level every day in a single month, and respectively marking the wind speed durations from the first level to the twelfth level in the single month as Vm 1-Vm 12; wind speed durations from the first level to the twelfth level of each month in the whole year are respectively accumulated, and the wind speed durations from the first level to the eleventh level in a single month are respectively marked as Vy1 to Vy 12.
Further, the step S2 further includes:
when the annual generated power of a single machine is predicted, the wind speed time from the first level to the twelfth level of the year is respectively substituted into a wind speed power conversion formula to obtain the wind speed conversion power from the first level to the twelfth level;
substituting the wind speed conversion power from the first stage to the twelfth stage into a single-machine power accumulation formula to obtain the single-machine standard annual power generation power;
placing a single-machine wind driven generator in a wind power generation laboratory, blowing the single-machine wind driven generator to the wind driven generator at the wind speeds of the first stage to the twelfth stage respectively, continuously generating power for a first test duration in the wind speed test state of each stage, and acquiring the actual power generation power of each stage of wind driven generator in the first test duration;
substituting the wind speed duration from the first stage to the twelfth stage of the whole year and the actual generated power corresponding to the wind speed of each stage into a loss elimination power conversion formula to obtain the single-machine actual whole year generated power.
Further, the step S3 further includes: obtaining the installed power of the wind driven generators needing to be arranged in the prediction region, and substituting the installed power of each wind driven generator, the predicted test power of the wind driven generators and the actual annual generating power of the single machine into a single machine power conversion formula to obtain the predicted power of each wind driven generator; and accumulating the predicted power of each wind driven generator to obtain the regional predicted power generation power.
The invention has the beneficial effects that: in the process of acquiring annual wind speed data, the grade of the wind speed is classified firstly, then the classified wind speed is subjected to cascade accumulation, the wind speed data of a single day is acquired firstly, then the wind speed data of a single month is summarized, and finally the annual wind speed data is summarized, so that a relatively accurate annual wind speed model can be obtained;
according to the method, after annual wind speed data are acquired, firstly, the generated power of the single machine is subjected to prediction conversion, and then the regional generated power in the prediction region is predicted based on the annual generated power of the single machine, so that the prediction accuracy of the wind power generation efficiency in the region can be improved.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic block diagram of the system of the present invention.
FIG. 2 is a flow chart of the method of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further explained by combining the specific embodiments.
Referring to fig. 1, a wind power prediction system based on an artificial neural network includes a wind speed model building module, a single-machine power prediction module, and a regional power prediction module; the invention utilizes the artificial neural network calculation model to accumulate the wind power generation power of the cascade, thereby accurately predicting the wind power generation power in the prediction region.
The wind speed model building module is used for acquiring and processing annual wind speed data of a prediction area; the wind speed model building module comprises a wind speed classification unit, a single-day wind speed processing unit, a single-month wind speed summarizing unit and a whole-year wind speed summarizing unit; the wind speed classification unit is used for classifying effective wind speeds; the wind speed classification unit is configured with a wind speed classification strategy, and the wind speed classification strategy comprises the following steps: dividing the effective wind speed into a first level to a tenth level according to the grade of the wind speed; in the process of counting the wind speed, wind speed sampling is carried out in the area in advance, wind with certain wind speed in a certain wind direction range is divided into effective wind speeds, and then the duration of the effective wind speeds is counted, so that the effectiveness of wind speed statistical data can be improved.
The single-day wind speed processing unit is used for summarizing the wind speed duration of a single day; the single-day wind speed processing unit is configured with a single-day wind speed summarizing strategy, and the single-day wind speed summarizing strategy comprises the following steps: respectively counting the effective wind speed duration from the first level to the tenth level in a single day, and respectively marking the effective wind speed duration from the first level to the tenth level in the single day as Vd 1-Vd 12; firstly, single-day wind speed data are counted, and a starting point is set according to a minimum counting base point.
The single-month wind speed summarizing unit is used for summarizing the whole-month wind speed based on the single-day wind speed processing result; the single-month wind speed summarizing unit is configured with a single-month wind speed summarizing strategy, and the single-month wind speed summarizing strategy comprises the following steps: respectively accumulating the wind speed durations from the first level to the twelfth level every day in a single month, and respectively marking the wind speed durations from the first level to the twelfth level in the single month as Vm 1-Vm 12; the annual wind speed summarizing unit is used for summarizing the comprehensive wind speed based on the summarizing result of the monthly wind speed summarizing unit; the annual wind speed summarizing unit is configured with an annual wind speed summarizing strategy, and the annual wind speed summarizing strategy comprises the following steps: wind speed durations from the first level to the twelfth level of each month in the whole year are respectively accumulated, and the wind speed durations from the first level to the eleventh level in a single month are respectively marked as Vy1 to Vy 12.
The single-machine power prediction module is used for predicting the annual power generation power of the single machine in the prediction region based on annual wind speed data; the single-machine power prediction module comprises a wind speed conversion unit, the wind speed conversion unit is configured with a wind speed conversion strategy, and the wind speed conversion strategy comprises the following steps: when the annual generated power of a single machine is predicted, the wind speed time from the first level to the twelfth level of the year is respectively substituted into a wind speed power conversion formula to obtain the wind speed conversion power from the first level to the twelfth level;
substituting the wind speed conversion power from the first stage to the twelfth stage into a single-machine power accumulation formula to obtain the single-machine standard annual power generation power; the wind speed power conversion formula is configured to:(ii) a The stand-alone power accumulation formula is configured to:(ii) a w1 is a single machine annual month compensation coefficient, w1 is between 0 and 2, wherein Wfz is windThe method comprises the steps of converting speed into power, wherein Wfz 1-Wfz 12 are the annual wind speed conversion power of first-level to twelfth-level wind speeds, Vi is a representative character of annual wind speed duration of the first-level to the twelfth-level, Wbdq is single-machine standard annual power generation, the value of a1 is smaller than zero, the value of b1 is larger than zero, and the absolute value of a1 is smaller than b 1; in the wind speed power conversion formula, it can be obviously known that when the wind speed is higher or lower, the obtained wind speed power is also lower, and the wind speed has an obvious peak value in the middle interval.
The stand-alone power prediction module further comprises a loss cancellation unit configured with a loss cancellation strategy comprising: placing a single-machine wind driven generator in a wind power generation laboratory, blowing the single-machine wind driven generator to the wind driven generator at the wind speeds of the first stage to the twelfth stage respectively, continuously generating power for a first test duration in the wind speed test state of each stage, and acquiring the actual power generation power of each stage of wind driven generator in the first test duration; substituting the wind speed duration from the first stage to the twelfth stage of the whole year and the actual generated power corresponding to the wind speed of each stage into a loss elimination power conversion formula to obtain the single-machine actual whole year generated power.
The loss cancellation power conversion equation is configured to:(ii) a Wherein, Wsdq is the actual annual generated power of the single machine, Vc1 is the first test duration, and Wsi represents the actual generated power of each stage of wind driven generator under the first test duration.
The regional power prediction module is used for predicting regional generated power in a prediction region based on the annual generated power of a single machine, and is configured with a regional power prediction strategy, wherein the regional power prediction strategy comprises the following steps: acquiring installed power of wind driven generators needing to be arranged in a prediction region, and substituting the installed power of each wind driven generator, the test power of the wind driven generators in the single-machine power prediction module and the actual annual generating power of the single machine into a single-machine power conversion formula to obtain the predicted power of each wind driven generator; accumulating the predicted power of each wind driven generator to obtain a regionPredicting the generated power by the domain; the stand-alone power conversion formula is configured to:(ii) a Wyc is the predicted power of each generator, Wzjn is the installed power of each generator, Wyzj is the test power of the wind driven generator in the single-machine power prediction module, the installed power and the test power belong to the standard output power of the generator in the early stage, no loss is calculated, and therefore the actual output power needs to be referred.
Referring to fig. 2, a wind power prediction method based on an artificial neural network includes the following steps:
step S1, classifying the wind speeds, respectively acquiring the wind speed duration of a single day, then acquiring the wind speed duration of a single month, and finally summarizing the wind speed duration of the whole year; dividing the effective wind speed into a first level to a tenth level according to the grade of the wind speed; respectively counting the effective wind speed duration from the first level to the tenth level in a single day, and respectively marking the effective wind speed duration from the first level to the tenth level in the single day as Vd 1-Vd 12; respectively accumulating the wind speed durations from the first level to the twelfth level in a single month every day, and respectively marking the wind speed durations from the first level to the twelfth level in the single month as Vm 1-Vm 12; wind speed durations from the first level to the twelfth level of each month in the whole year are respectively accumulated, and the wind speed durations from the first level to the eleventh level in a single month are respectively marked as Vy1 to Vy 12.
Step S2, predicting annual generated power of the single machine in the prediction area based on annual wind speed data; when the annual generated power of a single machine is predicted, the wind speed time from the first level to the twelfth level of the year is respectively substituted into a wind speed power conversion formula to obtain the wind speed conversion power from the first level to the twelfth level;
substituting the wind speed conversion power from the first stage to the twelfth stage into a single-machine power accumulation formula to obtain the single-machine standard annual power generation power;
placing a single-machine wind driven generator in a wind power generation laboratory, blowing the single-machine wind driven generator to the wind driven generator at the wind speeds of the first stage to the twelfth stage respectively, continuously generating power for a first test duration in the wind speed test state of each stage, and acquiring the actual power generation power of each stage of wind driven generator in the first test duration;
substituting the wind speed duration from the first stage to the twelfth stage of the whole year and the actual generated power corresponding to the wind speed of each stage into a loss elimination power conversion formula to obtain the single-machine actual whole year generated power.
Step S3, predicting the regional power generation power in the prediction region based on the annual power generation power of the single machine, acquiring the installed power of the wind driven generators needing to be arranged in the prediction region, and substituting the installed power of each wind driven generator, the predicted test power of the wind driven generator and the actual annual power generation power of the single machine into a single machine power conversion formula to obtain the predicted power of each wind driven generator; and accumulating the predicted power of each wind driven generator to obtain the regional predicted power generation power.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: those skilled in the art can still make modifications or changes to the embodiments described in the foregoing embodiments, or make equivalent substitutions for some features, within the scope of the disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A wind power prediction system based on an artificial neural network is characterized by comprising a wind speed model building module, a single-machine power prediction module and a regional power prediction module; the wind speed model building module is used for acquiring and processing annual wind speed data of a prediction area; the wind speed model building module comprises a wind speed classification unit, a single-day wind speed processing unit, a single-month wind speed summarizing unit and a whole-year wind speed summarizing unit; the wind speed classification unit is used for classifying effective wind speeds; the single-day wind speed processing unit is used for summarizing the wind speed duration of a single day; the single-month wind speed summarizing unit is used for summarizing the whole-month wind speed based on the single-day wind speed processing result; the annual wind speed summarizing unit is used for summarizing the comprehensive wind speed based on the summarizing result of the monthly wind speed summarizing unit;
the single-machine power prediction module is used for predicting the annual power generation power of the single machines in the prediction area based on annual wind speed data; the regional power prediction module is used for predicting regional generated power in a prediction region based on the annual generated power of the single machine.
2. The artificial neural network-based wind power prediction system of claim 1, wherein the wind speed classification unit is configured with a wind speed classification strategy comprising: dividing the effective wind speed into a first level to a tenth level according to the grade of the wind speed;
the single-day wind speed processing unit is configured with a single-day wind speed summarizing strategy, and the single-day wind speed summarizing strategy comprises the following steps: respectively counting the effective wind speed duration from the first level to the tenth level in a single day, and respectively marking the effective wind speed duration from the first level to the tenth level in the single day as Vd 1-Vd 12;
the single-month wind speed summarizing unit is configured with a single-month wind speed summarizing strategy, and the single-month wind speed summarizing strategy comprises the following steps: respectively accumulating the wind speed durations from the first level to the twelfth level in a single month every day, and respectively marking the wind speed durations from the first level to the twelfth level in the single month as Vm 1-Vm 12;
the annual wind speed summarizing unit is configured with an annual wind speed summarizing strategy, and the annual wind speed summarizing strategy comprises the following steps: wind speed durations of the first level to the tenth level in each month in the whole year are respectively accumulated, and the wind speed durations of the first level to the tenth level in a single month are respectively marked as Vy1 to Vy 12.
3. The artificial neural network-based wind power prediction system of claim 2, wherein the stand-alone power prediction module comprises a wind speed conversion unit configured with a wind speed conversion strategy, and the wind speed conversion strategy comprises: when the annual generated power of a single machine is predicted, the wind speed time from the first level to the twelfth level of the year is respectively substituted into a wind speed power conversion formula to obtain the wind speed conversion power from the first level to the twelfth level;
substituting the wind speed conversion power from the first stage to the twelfth stage into a single-machine power accumulation formula to obtain the single-machine standard annual power generation power;
the stand-alone power prediction module further comprises a loss cancellation unit configured with a loss cancellation strategy comprising: placing a single-machine wind driven generator in a wind power generation laboratory, blowing the single-machine wind driven generator to the wind driven generator at the wind speeds of the first stage to the twelfth stage respectively, continuously generating power for a first test duration in the wind speed test state of each stage, and acquiring the actual power generation power of each stage of wind driven generator in the first test duration;
substituting the wind speed duration from the first stage to the twelfth stage of the whole year and the actual generated power corresponding to the wind speed of each stage into a loss elimination power conversion formula to obtain the single-machine actual whole year generated power.
4. The artificial neural network-based wind power prediction system of claim 3, wherein the wind speed power conversion formula is configured to:(ii) a The stand-alone power accumulation formula is configured to:(ii) a Wherein Wfz is wind speed conversion power, Wfz 1-Wfz 12 is the wind speed conversion power of the first-level to twelfth-level wind speed all year, Vi is the wind speed duration of the first-level to twelfth-level all yearThe Wbdq is single-machine standard annual power generation power, the value of a1 is smaller than zero, the value of b1 is larger than zero, the absolute value of a1 is smaller than b1, and w1 is a single-machine annual month compensation coefficient;
5. The artificial neural network-based wind power prediction system of claim 4, wherein the regional power prediction module is configured with a regional power prediction strategy, the regional power prediction strategy comprising: acquiring installed power of wind driven generators needing to be arranged in a prediction region, and substituting the installed power of each wind driven generator, the test power of the wind driven generators in the single-machine power prediction module and the actual annual generating power of the single machine into a single-machine power conversion formula to obtain the predicted power of each wind driven generator;
and accumulating the predicted power of each wind driven generator to obtain the regional predicted power generation power.
6. The artificial neural network-based wind power prediction system of claim 5, wherein the stand-alone power conversion formula is configured to:(ii) a Wyc is the predicted power of each generator, Wzjn is the installed power of each generator, and Wyzj is the test power of the wind driven generator in the single-machine power prediction module.
7. The method of the wind power prediction system based on the artificial neural network as claimed in any one of claims 1 to 6, wherein the method comprises the following steps:
step S1, classifying the wind speeds, respectively acquiring the wind speed duration of a single day, then acquiring the wind speed duration of a single month, and finally summarizing the wind speed duration of the whole year;
step S2, predicting annual generated power of the single machine in the prediction area based on annual wind speed data;
step S3, the regional generated power in the predicted region is predicted based on the annual generated power of the single machine.
8. The method for predicting wind power based on artificial neural network as claimed in claim 7, wherein the step S1 further includes: dividing the effective wind speed into a first level to a tenth level according to the grade of the wind speed; respectively counting the effective wind speed duration from the first level to the tenth level in a single day, and respectively marking the effective wind speed duration from the first level to the tenth level in the single day as Vd 1-Vd 12; respectively accumulating the wind speed durations from the first level to the twelfth level in a single month every day, and respectively marking the wind speed durations from the first level to the twelfth level in the single month as Vm 1-Vm 12; wind speed durations from the first level to the twelfth level of each month in the whole year are respectively accumulated, and the wind speed durations from the first level to the eleventh level in a single month are respectively marked as Vy1 to Vy 12.
9. The method for predicting wind power based on artificial neural network as claimed in claim 8, wherein said step S2 further includes:
when the annual generated power of a single machine is predicted, the wind speed time from the first level to the twelfth level of the year is respectively substituted into a wind speed power conversion formula to obtain the wind speed conversion power from the first level to the twelfth level;
substituting the wind speed conversion power from the first stage to the twelfth stage into a single-machine power accumulation formula to obtain the single-machine standard annual power generation power;
placing a single-machine wind driven generator in a wind power generation laboratory, blowing the single-machine wind driven generator to the wind driven generator at the wind speeds of the first stage to the twelfth stage respectively, continuously generating power for a first test duration in the wind speed test state of each stage, and acquiring the actual power generation power of each stage of wind driven generator in the first test duration;
substituting the wind speed duration from the first stage to the twelfth stage of the whole year and the actual generated power corresponding to the wind speed of each stage into a loss elimination power conversion formula to obtain the single-machine actual whole year generated power.
10. The method for predicting wind power based on artificial neural network as claimed in claim 9, wherein the step S3 further includes: obtaining the installed power of the wind driven generators needing to be arranged in the prediction region, and substituting the installed power of each wind driven generator, the predicted test power of the wind driven generators and the actual annual generating power of the single machine into a single machine power conversion formula to obtain the predicted power of each wind driven generator; and accumulating the predicted power of each wind driven generator to obtain the regional predicted power generation power.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210536724.2A CN114662800A (en) | 2022-05-18 | 2022-05-18 | Wind power prediction method and system based on artificial neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210536724.2A CN114662800A (en) | 2022-05-18 | 2022-05-18 | Wind power prediction method and system based on artificial neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114662800A true CN114662800A (en) | 2022-06-24 |
Family
ID=82037440
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210536724.2A Pending CN114662800A (en) | 2022-05-18 | 2022-05-18 | Wind power prediction method and system based on artificial neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114662800A (en) |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050192779A1 (en) * | 2004-02-27 | 2005-09-01 | Mertins Karl-Heinz O. | Method and system for determining a location of a wind-powered electrical energy facility |
KR20070119285A (en) * | 2006-06-15 | 2007-12-20 | 한국에너지기술연구원 | Forecasting method of wind power generation by classification of wind speed patterns |
CN102236795A (en) * | 2011-06-30 | 2011-11-09 | 内蒙古电力勘测设计院 | Method for forecasting wind speed in wind power station |
CN103683274A (en) * | 2013-07-16 | 2014-03-26 | 国家电网公司 | Regional long-term wind power generation capacity probability prediction method |
US20150154504A1 (en) * | 2012-12-17 | 2015-06-04 | Arizona Board Of Regents On Behalf Of Arizona State University | Support vector machine enhanced models for short-term wind farm generation forecasting |
US20150204922A1 (en) * | 2012-08-07 | 2015-07-23 | Korea Institute Of Energy Research | Method for Predicting Wind Power Density |
CN106447086A (en) * | 2016-09-07 | 2017-02-22 | 中国农业大学 | Wind electricity power combined prediction method based on wind farm data pre-processing |
CN106779203A (en) * | 2016-12-08 | 2017-05-31 | 贵州电网有限责任公司电力科学研究院 | A kind of plateau mountain area wind power forecasting method based on different wind speed section |
US20180223812A1 (en) * | 2017-02-07 | 2018-08-09 | International Business Machines Corporation | Reducing curtailment of wind power generation |
CN108736513A (en) * | 2018-05-04 | 2018-11-02 | 国网青海省电力公司 | Consider the wind-powered electricity generation field frequencies range methods of risk assessment in the year of second grade wind speed correlation |
CN109242218A (en) * | 2018-11-05 | 2019-01-18 | 南方电网科学研究院有限责任公司 | A kind of wind power forecasting method and device in the plateau mountain area based on SVM |
CN109460856A (en) * | 2018-10-08 | 2019-03-12 | 国网青海省电力公司 | Consider wind speed-wind direction correlation wind-powered electricity generation field frequencies range methods of risk assessment |
US20190203696A1 (en) * | 2016-05-23 | 2019-07-04 | General Electric Company | System and method for forecasting power output of a wind farm |
CN110210657A (en) * | 2019-05-22 | 2019-09-06 | 国网冀北电力有限公司 | A kind of power of fan prediction technique, system and computer storage medium based on single machine model |
CN111931967A (en) * | 2019-12-20 | 2020-11-13 | 南京南瑞继保电气有限公司 | Wind power plant short-term power prediction method |
CN114444378A (en) * | 2021-12-27 | 2022-05-06 | 上海电力大学 | Short-term power prediction method for regional wind power cluster |
CN114492923A (en) * | 2021-12-14 | 2022-05-13 | 电力规划总院有限公司 | Long-time scale power prediction method |
-
2022
- 2022-05-18 CN CN202210536724.2A patent/CN114662800A/en active Pending
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050192779A1 (en) * | 2004-02-27 | 2005-09-01 | Mertins Karl-Heinz O. | Method and system for determining a location of a wind-powered electrical energy facility |
KR20070119285A (en) * | 2006-06-15 | 2007-12-20 | 한국에너지기술연구원 | Forecasting method of wind power generation by classification of wind speed patterns |
CN102236795A (en) * | 2011-06-30 | 2011-11-09 | 内蒙古电力勘测设计院 | Method for forecasting wind speed in wind power station |
US20150204922A1 (en) * | 2012-08-07 | 2015-07-23 | Korea Institute Of Energy Research | Method for Predicting Wind Power Density |
US20150154504A1 (en) * | 2012-12-17 | 2015-06-04 | Arizona Board Of Regents On Behalf Of Arizona State University | Support vector machine enhanced models for short-term wind farm generation forecasting |
CN103683274A (en) * | 2013-07-16 | 2014-03-26 | 国家电网公司 | Regional long-term wind power generation capacity probability prediction method |
US20190203696A1 (en) * | 2016-05-23 | 2019-07-04 | General Electric Company | System and method for forecasting power output of a wind farm |
CN106447086A (en) * | 2016-09-07 | 2017-02-22 | 中国农业大学 | Wind electricity power combined prediction method based on wind farm data pre-processing |
CN106779203A (en) * | 2016-12-08 | 2017-05-31 | 贵州电网有限责任公司电力科学研究院 | A kind of plateau mountain area wind power forecasting method based on different wind speed section |
US20180223812A1 (en) * | 2017-02-07 | 2018-08-09 | International Business Machines Corporation | Reducing curtailment of wind power generation |
CN108736513A (en) * | 2018-05-04 | 2018-11-02 | 国网青海省电力公司 | Consider the wind-powered electricity generation field frequencies range methods of risk assessment in the year of second grade wind speed correlation |
CN109460856A (en) * | 2018-10-08 | 2019-03-12 | 国网青海省电力公司 | Consider wind speed-wind direction correlation wind-powered electricity generation field frequencies range methods of risk assessment |
CN109242218A (en) * | 2018-11-05 | 2019-01-18 | 南方电网科学研究院有限责任公司 | A kind of wind power forecasting method and device in the plateau mountain area based on SVM |
CN110210657A (en) * | 2019-05-22 | 2019-09-06 | 国网冀北电力有限公司 | A kind of power of fan prediction technique, system and computer storage medium based on single machine model |
CN111931967A (en) * | 2019-12-20 | 2020-11-13 | 南京南瑞继保电气有限公司 | Wind power plant short-term power prediction method |
CN114492923A (en) * | 2021-12-14 | 2022-05-13 | 电力规划总院有限公司 | Long-time scale power prediction method |
CN114444378A (en) * | 2021-12-27 | 2022-05-06 | 上海电力大学 | Short-term power prediction method for regional wind power cluster |
Non-Patent Citations (6)
Title |
---|
GANG CHEN 等: "Research on Wind Power Prediction Method Based on Convolutional Neural Network and Genetic Algorithm", 《2019 IEEE INNOVATIVE SMART GRID TECHNOLOGIES - ASIA (ISGT ASIA)》 * |
XIN WANG 等: "An LSTM-attention wind power prediction method considering multiple factors", 《8TH RENEWABLE POWER GENERATION CONFERENCE (RPG 2019)》 * |
刘旭 等: "风力发电场可行性研究阶段的风资源评价", 《山东气象》 * |
樊国伟等: "基于最优划分聚类和人工神经网络的地区风力发电预测", 《青海电力》 * |
白永祥等: "内蒙古电网区域风电功率预测系统", 《电网技术》 * |
邵振国 等: "基于实测数据的风电场风速-功率特性仿射建模方法", 《电力自动化设备》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102236795B (en) | Method for forecasting wind speed in wind power station | |
CN102738792B (en) | Wind power predicting method | |
CN106570790B (en) | Wind power plant output data restoration method considering wind speed data segmentation characteristics | |
Sung et al. | Causality between public policies and exports of renewable energy technologies | |
CN103345585A (en) | Wind power prediction correction method and system based on support vector machine | |
CN102945509A (en) | Wind electric field power prediction method | |
Manco et al. | A Markovian approach to model power availability of a wind turbine | |
CN108847679A (en) | Wind power generating set and for its sub-synchronous oscillation recognition methods, apparatus and system | |
Kennedy et al. | A probabilistic model for simulating long-term wind-power output | |
CN104933471A (en) | Phase space reconstruction method for use in short-term wind speed prediction method | |
CN114662800A (en) | Wind power prediction method and system based on artificial neural network | |
Cheggaga et al. | A neural network solution for extrapolation of wind speeds at heights ranging for improving the estimation of wind producible | |
CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
CN114358550A (en) | Power grid analysis system and method based on big data | |
Huang et al. | Improving machine learning-based weather forecast post-processing with clustering and transfer learning | |
Li et al. | Extraction of abnormal points from on-line operation data of intelligent meter based on LSTM | |
CN110889491A (en) | Weather factor-based power load prediction method and prediction system | |
CN116502070B (en) | Intelligent monitoring system for state of miniature wind turbine generator | |
CN117791626B (en) | Intelligent comprehensive power box power supply optimization method | |
Pang et al. | Research on wind power output reconstruction technology based on multiple time scales | |
Guan et al. | Multi-scale wind power time series modeling method based on mathematical morphology | |
Mandal et al. | Solar power forecasting for smart grid system by using deep learning techniques | |
CN116090671A (en) | Photovoltaic power prediction system and method | |
CN118246695A (en) | Photovoltaic new energy operation and maintenance scheduling system | |
Xiao et al. | Research on Power Quality Feature Extraction and Traceability Based on Multi-Source Information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220624 |