CN117674123A - Wind power short-term power prediction method considering operation cost of power system - Google Patents
Wind power short-term power prediction method considering operation cost of power system Download PDFInfo
- Publication number
- CN117674123A CN117674123A CN202311668764.3A CN202311668764A CN117674123A CN 117674123 A CN117674123 A CN 117674123A CN 202311668764 A CN202311668764 A CN 202311668764A CN 117674123 A CN117674123 A CN 117674123A
- Authority
- CN
- China
- Prior art keywords
- power
- wind
- wind power
- data
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000013507 mapping Methods 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims abstract description 6
- 230000003828 downregulation Effects 0.000 claims description 4
- 230000003827 upregulation Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000012417 linear regression Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Water Supply & Treatment (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
A wind power short-term power prediction method considering the running cost of a power system collects historical power data, historical meteorological data and clear data of a power market of a wind power plant and correspondingly establishes a mapping relation between wind power and meteorological factors; building an electric power market clearing model, building a wind power short-term power prediction model considering the running cost of an electric power system on the basis of the electric power market clearing model, and training the model by using historical power of a wind power plant, meteorological data and electric power market clearing data; and inputting weather prediction data of the prediction period into the trained model to obtain a wind power prediction result. According to the invention, the running cost of the minimized power system is directly taken as an objective function to train the prediction model, an asymmetric loss function is not required to be constructed manually, and an uncertainty optimization method with higher calculation cost is not required to be introduced, so that the running cost of the power system can be effectively reduced.
Description
Technical Field
The invention relates to a technology in the field of power prediction of an electric power system, in particular to a wind power short-term power prediction method considering the running cost of the electric power system.
Background
The wind power short-term power prediction has important significance for reasonably arranging a power generation plan, relieving peak shaving pressure of a power grid, reducing operation cost of a power system and improving wind power grid connection reliability. Most of the existing wind power prediction technologies take minimized statistical errors (such as mean square errors) as target training models, do not consider the running cost of a power system, and have the problem that the prediction performance is not matched with the decision benefit; while decision loss methods and uncertainty optimization methods can make up for the gap between predictive performance and decision benefit to some extent. But the asymmetric loss of accurate weight overestimation and underestimation is difficult and the calculation cost is too large.
Disclosure of Invention
Aiming at the defects that an asymmetric loss function is required to be constructed manually in the existing decision loss method, and the true loss cost is difficult to reflect accurately; the method for predicting the wind power short-term power by taking the running cost of the power system into consideration is provided, the running cost of the power system is directly taken as an objective function to train a prediction model, an asymmetric loss function is not required to be constructed manually, and an uncertainty optimization method with higher calculation cost is not required to be introduced, so that the running cost of the power system can be effectively reduced.
The invention is realized by the following technical scheme:
the invention relates to a wind power short-term power prediction method considering the running cost of a power system, which is used for collecting historical power data, historical meteorological data and clear data of an electric power market of a wind power plant and correspondingly establishing a mapping relation between wind power and meteorological factors; building an electric power market clearing model, building a wind power short-term power prediction model considering the running cost of an electric power system on the basis of the electric power market clearing model, and training the model by using historical power of a wind power plant, meteorological data and electric power market clearing data; and inputting weather prediction data of the prediction period into the trained model to obtain a wind power prediction result.
The wind farm historical power data refer to: the actual power level of each fan in the wind farm over a historical period.
The historical meteorological data refer to: the geographical position of each fan in the wind power plant is provided with wind speed, wind direction, temperature, humidity and air pressure data in a historical period.
The electric power market clear data refer to: reporting price information, reporting unit information, power load data information and power system topological structure information.
The mapping relation refers to: the linear weighting relation between the wind power predicted value and the meteorological factor features, and the weight of each meteorological factor feature is a mapping coefficient.
The electric power market clearing model refers to: the total cost of operation of the power system in three stages of standby market clearing, day-ahead market clearing and in-day market clearing is minimized.
The wind power short-term power prediction model considering the running cost of the power system refers to: and adding a mapping coefficient vector of wind power and meteorological factors on the basis of a clear model of an electric power market, taking the mapping relation between the wind power and the meteorological factors as one of constraint conditions of a wind power short-term power prediction model, and obtaining the optimal mapping relation between the wind power and the meteorological factors with optimal cost by a method of solving an optimization model through a commercial solver (such as Gurobi), so as to realize training of the model.
Technical effects
According to the method, the running cost of the minimized power system is taken as an objective function to train a prediction model, the mapping relation between wind power and meteorological features is taken as a constraint condition of an optimized clear model of the power market, and the mapping coefficient is taken as a decision variable. And solving the optimal parameters of the prediction model, inputting the meteorological feature vector of the prediction period, and obtaining the wind power short-term power prediction result of optimal cost.
Compared with the prior art, the method and the device have the advantages that the operation cost of the power system is effectively reduced, meanwhile, the artificial construction of the loss function is avoided, the effect of reducing the operation cost of the power system is better, on the other hand, the prediction model is still point prediction in nature, the traditional framework of point prediction and deterministic optimization is not changed, and the calculation cost of model solving can be greatly reduced.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of an embodiment electric power market clearing model;
FIG. 3 is a graph comparing the predicted results of the conventional linear regression method and the present method.
Detailed Description
As shown in fig. 1, this embodiment relates to a wind power short-term power prediction method considering the running cost of a power system, including:
s1: acquiring historical power data and historical meteorological data of a wind power plant in a region to be predicted, and obtaining a wind power plant data set with the capacity Z;
s2: acquiring declaration price information, declaration unit information, power load data information and power system topological structure information as power market clearing related data, wherein: the unit comprises a new energy unit and a non-new energy unit;
s3: establishing a mapping relation between meteorological factors including wind speed, wind direction, temperature, humidity, air pressure and wind power prediction power, wherein the mapping relation specifically comprises the following steps:wherein: z epsilon Z is a wind farm dataset sample, +.>For wind power predictive value, x oz Is characteristic of meteorological factors, p is the number of meteorological factors, q o Mapping coefficients for wind power and meteorological factors, m is a constant term, wherein the mapping coefficient q o Unknown.
S4: constructing an electric power market clearing model as shown in fig. 2, wherein the electric power market clearing comprises: three stages of spare market clearing, day-ahead market clearing and daily in-day market clearingThe objective function of the electric power market clearing model is to minimize the total running cost of the three-stage electric power system, and specifically comprises the following steps:wherein: n epsilon N is a system node, I epsilon I n Is a thermal generator set->Up/down spare expense for thermal power unit i, respectively,/-> Respectively the upward/downward spare capacity of the thermal power generating unit i, C i For the day front power cost of the thermal power generating unit i, < ->The output of the thermal power unit i is declared before the day,/->Respectively power up-regulation/down-regulation values of thermal power unit i, J epsilon J n As load node, C Voll For unit cost of load shedding, +.>Cut load amount for load node j, C ct For unit cost of wind disposal->The total air discarding quantity of the electric power system is; />The decision variable set comprises upward and downward spare capacity, daily declaration output, power up-regulation and power down-regulation values of each thermal power generating unit, cut load quantity of each load node and total air rejection of the system.
The constraint conditions of the electric power market clearing model comprise: spare market clearing constraints, day-ahead market clearing constraints and day-in market clearing constraints.
The reserve market clearing constraint includes: standby demand constraint: wherein: />Up/down standby demand for node n; spare capacity constraint:wherein: />The rated power is the rated power of the thermal power unit i before the day; />Maximum upward/downward reserve capacity available for thermal power plant i.
The day-ahead market clearing constraints include: day-ahead stage system power balance constraints:
wherein: l (L) jz The demand size for load j; day-ahead phase generator set output constraint: />
The daily market clearing constraint comprises: system power balance constraint in the daytime phase:
wherein: w (W) z The actual power of wind power is obtained; day-period generator set output constraint:air quantity constraint is abandoned in the daytime: />Load constraint is cut off in a daily stage: />
S5: based on the mapping relation between meteorological factors and wind power predicted power and the constructed power market clearing model, constructing a wind power short-term power prediction model considering the running cost of a power system, training the wind power short-term power prediction model considering the running cost of the power system according to wind power plant related data and power market related data, and specifically comprising the following steps:
5.1 The objective function of the wind power short-term power model considering the running cost of the power system is constructed, which is the same as the objective function of the power market clearing model, and is as follows:
wherein: the decision variable adds the mapping coefficient vector q of wind power and meteorological factors except the related variable set gamma of the electric power market;
5.2 Adding a mapping relation expression between wind power and meteorological factors as constraint conditions of a wind power short-term power prediction model considering the running cost of a power system, wherein the constraint conditions specifically are as follows:
5.3 Other constraint conditions of the wind power short-term power prediction model considering the running cost of the power system are the same as those of the power market clearing model, and the method comprises the following steps: standby demand constraint:
wherein: />Up/down standby demand for node n; spare capacity constraint:
wherein: />The rated power is the rated power of the thermal power unit i before the day; />Maximum upward/downward reserve capacity available for thermal power unit i; day-ahead stage system power balance constraints: />Wherein: l (L) jz The demand size for load j; day-ahead phase generator set output constraint: />System power balance constraint in the daytime phase: />Wherein: w (W) z The actual power of wind power is obtained; day-period generator set output constraint:air quantity constraint is abandoned in the daytime: />Load constraint is cut off in a daily stage: />
5.4 Inputting wind power plant historical power data and power market related data into a wind power short-term power prediction model considering the running cost of a power system, defining model variables, objective functions and constraint conditions in a business solver (such as Gurobi), endowing the historical power data values, historical meteorological data values and power market clear data values of the wind power plant to variables in the model, carrying out model solving to obtain an optimal mapping coefficient between meteorological factors and wind power in the prediction model, determining an optimal solution of the mapping coefficient of wind power and meteorological factors with optimal cost, and obtaining the trained wind power short-term power prediction model considering the running cost of the power system.
S6: and carrying out future wind power short-term power prediction by using the trained wind power short-term power prediction model and future wind power plant weather prediction data.
Through specific practical experiments, the standard-based IEEE30 node system performs market-clearing simulation, and the system is provided with 6 thermal power units and 10 electric loads. And (3) connecting a wind turbine with the rated capacity of 13200MW at the node 1. The upward and downward standby demands of the system are 200MW each. The wind abandoning punishment cost coefficient is 300 yuan/MW, and the load shedding punishment cost coefficient is 5000 yuan/MW. Historical power data and meteorological data of the wind farm are obtained from an actual wind farm in a certain area of China. The length of the data set is 2022, 12 months, 1 day to 2022, 12 months, 31 days, and the time resolution is 15 minutes, wherein 70% of the data is the training set, and 30% of the data is the test set.
Comparing the method with the traditional linear regression method, as shown in fig. 3, since the cut load cost is far greater than the wind abandoning cost, the loss cost of wind power estimated true value is greater than that of underestimated true value, the method tends to be more conservative in prediction so as to realize lower running cost of the electric power system, while the traditional linear regression method tends to be more accurate in prediction, and is neither conservative nor aggressive. The average system running cost of the prediction results of the two methods in the test set is calculated, the method is 965.13 ten thousand yuan, the traditional linear regression method is 1019.50 ten thousand yuan, and the method effectively reduces the running cost of the power system.
The foregoing embodiments may be partially modified in numerous ways by those skilled in the art without departing from the principles and spirit of the invention, the scope of which is defined in the claims and not by the foregoing embodiments, and all such implementations are within the scope of the invention.
Claims (6)
1. A wind power short-term power prediction method considering the running cost of a power system is characterized by collecting historical power data, historical meteorological data and clear data of an electric power market of a wind power plant and correspondingly establishing a mapping relation between wind power and meteorological factors; building an electric power market clearing model, building a wind power short-term power prediction model considering the running cost of an electric power system on the basis of the electric power market clearing model, and training the model by using historical power of a wind power plant, meteorological data and electric power market clearing data; inputting weather forecast data of a forecast period into a trained model to obtain a wind power forecast result;
the mapping relation refers to: the linear weighting relation between the wind power predicted value and the meteorological factor features, and the weight of each meteorological factor feature is a mapping coefficient.
2. The method for predicting short-term power of wind power in consideration of running cost of power system as claimed in claim 1, wherein the historical power data of wind farm is: the actual power of each fan in the wind power plant in the historical period;
the historical meteorological data refer to: wind speed, wind direction, temperature, humidity and air pressure data of the geographic position of each fan in the wind power plant in the historical period; a step of
The electric power market clear data refer to: reporting price information, reporting unit information, power load data information and power system topological structure information.
3. The method for predicting short-term power of wind power in consideration of running cost of electric power system according to claim 1, wherein the electric power market clearing model is: the total cost of operation of the power system in three stages of standby market clearing, day-ahead market clearing and in-day market clearing is minimized.
4. The method for predicting the short-term power of wind power by considering the running cost of the power system according to claim 1, wherein the short-term power prediction model of wind power by considering the running cost of the power system is as follows: adding a mapping coefficient vector of wind power and meteorological factors on the basis of a clear model of an electric power market, and taking a mapping relation between the wind power and the meteorological factors as one of constraint conditions of a wind power short-term power prediction model;
according to the wind power short-term power prediction model, the optimal mapping relation between wind power and meteorological factors with optimal cost is obtained through a method of solving an optimization model by a commercial solver, and training is achieved.
5. The wind power short-term power prediction method considering running cost of electric power system according to any one of claims 1 to 4, comprising:
s1: acquiring historical power data and historical meteorological data of a wind power plant in a region to be predicted, and obtaining a wind power plant data set with the capacity Z;
s2: acquiring declaration price information, declaration unit information, power load data information and power system topological structure information as power market clearing related data, wherein: the unit comprises a new energy unit and a non-new energy unit;
s3: establishing a mapping relation between meteorological factors including wind speed, wind direction, temperature, humidity, air pressure and wind power prediction power, wherein the mapping relation specifically comprises the following steps:wherein: z epsilon Z is a wind farm dataset sample, +.>For wind power predictive value, x oz Is characteristic of meteorological factors, p is the number of meteorological factors, q o For wind power and weather reasonsMapping coefficient of element, m is a constant term, wherein mapping coefficient q o Unknown;
s4: constructing an electric power market clearing model, wherein the electric power market clearing comprises: the objective function of the electric power market clearing model is to minimize the total running cost of the three-stage electric power system, and the three stages of the standby market clearing, the day-ahead market clearing and the day-in market clearing are as follows:wherein: n epsilon N is a system node, I epsilon I n Is a thermal generator set->Up/down spare expense for thermal power unit i, respectively,/->Respectively the upward/downward spare capacity of the thermal power generating unit i, C i For the day front power cost of the thermal power generating unit i, < ->The output of the thermal power unit i is declared before the day,/->Respectively power up-regulation/down-regulation values of thermal power unit i, J epsilon J n As load node, C Voll For unit cost of load shedding, +.>Cut load amount for load node j, C ct For unit cost of wind disposal->The total air discarding quantity of the electric power system is;the method is a decision variable set, and comprises upward and downward spare capacity, daily declaration output, power up-regulation and power down-regulation values of each thermal power unit, cut load quantity of each load node and total air discarding quantity of a system;
the constraint conditions of the electric power market clearing model comprise: reserve market clearing constraints, day-ahead market clearing constraints, and day-in market clearing constraints;
s5: based on the mapping relation between meteorological factors and wind power predicted power and the constructed power market clearing model, constructing a wind power short-term power prediction model considering the running cost of a power system, and training the wind power short-term power prediction model considering the running cost of the power system according to wind power plant related data and power market related data, wherein the wind power short-term power prediction model specifically comprises the following steps:
5.1 The objective function of the wind power short-term power model considering the running cost of the power system is constructed, which is the same as the objective function of the power market clearing model, and is as follows:
wherein: the decision variable adds the mapping coefficient vector q of wind power and meteorological factors except the related variable set gamma of the electric power market;
5.2 Adding a mapping relation expression between wind power and meteorological factors as constraint conditions of a wind power short-term power prediction model considering the running cost of a power system, wherein the constraint conditions specifically are as follows:
5.3 Other constraint conditions of the wind power short-term power prediction model considering the running cost of the power system are the same as those of the power market clearing model, and the method comprises the following steps: standby demand constraint:
wherein: />Up/down standby demand for node n; spare capacity constraint:wherein: />The rated power is the rated power of the thermal power unit i before the day; />Maximum upward/downward reserve capacity available for thermal power unit i;
day-ahead stage system power balance constraints:wherein: l (L) jz The demand size for load j; day-ahead phase generator set output constraint: />System power balance constraint in the daytime phase:wherein: w (W) z The actual power of wind power is obtained; day-period generator set output constraint:air quantity constraint is abandoned in the daytime: />Load constraint is cut off in a daily stage: />
5.4 Inputting wind power plant historical power data and power market related data into a wind power short-term power prediction model considering the running cost of a power system, defining model variables, objective functions and constraint conditions in a business solver, endowing the wind power plant historical power data values, historical meteorological data values and power market clear data values to variables in the model, carrying out model solving to obtain optimal mapping coefficients between meteorological factors and wind power in the prediction model, determining optimal solutions of the mapping coefficients of wind power and meteorological factors with optimal cost, and obtaining the trained wind power short-term power prediction model considering the running cost of the power system;
s6: and carrying out future wind power short-term power prediction by using the trained wind power short-term power prediction model and future wind power plant weather prediction data.
6. The method for predicting short-term power of wind power with consideration of operating costs of electric power system as set forth in claim 5, wherein said reserve market clearing constraint comprises: standby demand constraint:
wherein: />Up/down standby demand for node n; spare capacity constraint:wherein: />The rated power is the rated power of the thermal power unit i before the day; />Maximum upward/downward reserve capacity available for thermal power unit i;
the day-ahead market clearing constraints include: day-ahead stage system power balance constraints:
wherein: l (L) jz The demand size for load j; day-ahead phase generator set output constraint: />
The daily market clearing constraint comprises: system power balance constraint in the daytime phase:
wherein: w (W) z The actual power of wind power is obtained; day-period generator set output constraint:air quantity constraint is abandoned in the daytime: />Load constraint is cut off in a daily stage: />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311668764.3A CN117674123B (en) | 2023-12-07 | 2023-12-07 | Wind power short-term power prediction method considering operation cost of power system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311668764.3A CN117674123B (en) | 2023-12-07 | 2023-12-07 | Wind power short-term power prediction method considering operation cost of power system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117674123A true CN117674123A (en) | 2024-03-08 |
| CN117674123B CN117674123B (en) | 2024-06-14 |
Family
ID=90078463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311668764.3A Active CN117674123B (en) | 2023-12-07 | 2023-12-07 | Wind power short-term power prediction method considering operation cost of power system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117674123B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118172047A (en) * | 2024-05-14 | 2024-06-11 | 山东大学 | Short-term wind power prediction method and system considering available installed capacity |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160273518A1 (en) * | 2014-09-02 | 2016-09-22 | Siemens Industry, Inc. | Systems, methods and apparatus for improved energy management systems with security constrained dynamic dispatch for wind power management |
| CN109636671A (en) * | 2018-12-18 | 2019-04-16 | 中南大学 | A kind of wind electricity digestion optimisation strategy considering multi-level market linkage type |
| US20210088692A1 (en) * | 2015-03-27 | 2021-03-25 | Trustees Of Princeton University | System and method for performing wind forecasting |
| CN112580901A (en) * | 2021-02-23 | 2021-03-30 | 国能日新科技股份有限公司 | Day-ahead trading strategy method and system based on market supply and demand and regional weather prediction |
| CN112733462A (en) * | 2021-01-21 | 2021-04-30 | 国网辽宁省电力有限公司阜新供电公司 | Ultra-short-term wind power plant power prediction method combining meteorological factors |
| CN114493222A (en) * | 2022-01-18 | 2022-05-13 | 中广核风电有限公司 | Wind power plant energy storage power station multi-market participation strategy considering output prediction and price |
| CN115759560A (en) * | 2022-10-11 | 2023-03-07 | 东北电力大学 | Energy storage-new energy-thermal power multi-target optimization scheduling method and system thereof |
| CN116050653A (en) * | 2023-02-23 | 2023-05-02 | 国网上海市电力公司 | Closed-loop prediction-decision scheduling method for power system based on data driving |
| WO2023070960A1 (en) * | 2021-10-29 | 2023-05-04 | 中国华能集团清洁能源技术研究院有限公司 | Wind power prediction method based on convolutional transformer architecture, and system and device |
| CN116542373A (en) * | 2023-04-28 | 2023-08-04 | 南方电网科学研究院有限责任公司 | Optimal scheduling method and device considering new energy guarantee and absorption requirements |
| CN117010946A (en) * | 2023-08-30 | 2023-11-07 | 国能宁夏鸳鸯湖第一发电有限公司 | Thermal power plant production and operation cost accounting system and application method thereof |
-
2023
- 2023-12-07 CN CN202311668764.3A patent/CN117674123B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160273518A1 (en) * | 2014-09-02 | 2016-09-22 | Siemens Industry, Inc. | Systems, methods and apparatus for improved energy management systems with security constrained dynamic dispatch for wind power management |
| US20210088692A1 (en) * | 2015-03-27 | 2021-03-25 | Trustees Of Princeton University | System and method for performing wind forecasting |
| CN109636671A (en) * | 2018-12-18 | 2019-04-16 | 中南大学 | A kind of wind electricity digestion optimisation strategy considering multi-level market linkage type |
| CN112733462A (en) * | 2021-01-21 | 2021-04-30 | 国网辽宁省电力有限公司阜新供电公司 | Ultra-short-term wind power plant power prediction method combining meteorological factors |
| CN112580901A (en) * | 2021-02-23 | 2021-03-30 | 国能日新科技股份有限公司 | Day-ahead trading strategy method and system based on market supply and demand and regional weather prediction |
| WO2023070960A1 (en) * | 2021-10-29 | 2023-05-04 | 中国华能集团清洁能源技术研究院有限公司 | Wind power prediction method based on convolutional transformer architecture, and system and device |
| CN114493222A (en) * | 2022-01-18 | 2022-05-13 | 中广核风电有限公司 | Wind power plant energy storage power station multi-market participation strategy considering output prediction and price |
| CN115759560A (en) * | 2022-10-11 | 2023-03-07 | 东北电力大学 | Energy storage-new energy-thermal power multi-target optimization scheduling method and system thereof |
| CN116050653A (en) * | 2023-02-23 | 2023-05-02 | 国网上海市电力公司 | Closed-loop prediction-decision scheduling method for power system based on data driving |
| CN116542373A (en) * | 2023-04-28 | 2023-08-04 | 南方电网科学研究院有限责任公司 | Optimal scheduling method and device considering new energy guarantee and absorption requirements |
| CN117010946A (en) * | 2023-08-30 | 2023-11-07 | 国能宁夏鸳鸯湖第一发电有限公司 | Thermal power plant production and operation cost accounting system and application method thereof |
Non-Patent Citations (3)
| Title |
|---|
| PEIZHENG XUAN; JIZHONG ZHU; JIN ZOU; PINGPING XIE: "Research on the Electricity Market Clearing Model and Price Fluctuation with Wind Power", 2019 IEEE INNOVATIVE SMART GRID TECHNOLOGIES - ASIA, 24 May 2019 (2019-05-24), pages 2936, XP033638773, DOI: 10.1109/ISGT-Asia.2019.8881806 * |
| 王星凯: "风电并网条件下供需双侧参与备用市场出清策略研究", 工程科技Ⅱ辑, no. 2023, 15 March 2023 (2023-03-15), pages 042 - 221 * |
| 耿鸿冲，张越师: "基于GA-SVM的风机发电功率预测", 电子测试, no. 2019, 30 June 2019 (2019-06-30), pages 38 - 40 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118172047A (en) * | 2024-05-14 | 2024-06-11 | 山东大学 | Short-term wind power prediction method and system considering available installed capacity |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117674123B (en) | 2024-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bludszuweit et al. | Statistical analysis of wind power forecast error | |
| CN103475021B (en) | Statistic model based method for determining discarded wind power quantity of wind power plant | |
| CN117674123B (en) | Wind power short-term power prediction method considering operation cost of power system | |
| CN104978608B (en) | A kind of wind electric powder prediction device and prediction technique | |
| CN106058941B (en) | A kind of wind power plant random optimization dispatching method based on scene analysis | |
| CN103902837B (en) | Method for wind speed prediction based on experience Copula function | |
| CN113935247B (en) | Partition virtual inertia estimation method considering wind speed randomness and correlation | |
| CN110460038A (en) | It is a kind of to be related to more scene method for expansion planning of power transmission network of new-energy grid-connected | |
| Li et al. | Model and procedures for reliable near term wind energy production forecast | |
| CN111950764A (en) | Extreme weather condition power grid wind power prediction correction method | |
| CN116306006A (en) | Optimal scheduling method and device for wind-solar-water combined power generation and computer equipment | |
| CN105046349A (en) | Wind power prediction method considering wake effect | |
| CN113610285A (en) | Power prediction method for distributed wind power | |
| CN112561149A (en) | Wind power prediction method based on power downscaling data fusion and statistical model | |
| Wang et al. | Adequacy assessment of generating systems incorporating wind, PV and energy storage | |
| Ding et al. | A dynamic period partition method for time-of-use pricing with high-penetration renewable energy | |
| Zhong et al. | Wind power forecasting and integration to power grids | |
| Hoxha et al. | Influence of seasonal air density fluctuations on wind speed distribution in complex terrains in the context of energy yield | |
| CN116385053A (en) | Method, system and medium for predicting daily price of electric power spot market | |
| Eltohamy et al. | A novel approach for the power ramping metrics | |
| Badyda et al. | Heat Accumulator in Large District Heating Systems: Simulation and Optimisation | |
| CN113506185A (en) | Power generation optimization scheduling method and device for cascade hydropower station and computer equipment | |
| CN111415041A (en) | Method for evaluating economy of power grid planning scheme | |
| CN112736969A (en) | Distributed photovoltaic data processing method and system based on new energy economic dispatching | |
| El-Shimy | Adequacy-based placement of WECS in Egypt |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |