CN110707688B - Wind power load prediction method based on annual load curve and power grid user equipment change feedforward - Google Patents
Wind power load prediction method based on annual load curve and power grid user equipment change feedforward Download PDFInfo
- Publication number
- CN110707688B CN110707688B CN201910866450.1A CN201910866450A CN110707688B CN 110707688 B CN110707688 B CN 110707688B CN 201910866450 A CN201910866450 A CN 201910866450A CN 110707688 B CN110707688 B CN 110707688B
- Authority
- CN
- China
- Prior art keywords
- load
- power grid
- power
- prediction
- user equipment
- 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.)
- Active
Links
Images
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
-
- 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
- H02J3/008—Circuit arrangements for ac mains or ac distribution networks involving trading of energy or energy transmission rights
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a wind power load prediction method based on an annual load curve and power grid user equipment change feedforward, and belongs to the field of wind power load prediction. The system comprises a historical data server for predicting the annual load curve of the wind power load, a power grid user APP platform, user equipment, a load change prediction feedforward device, a communication cable and an alternating current power supply; the method comprises the steps that a historical data server calls an annual load curve for forecasting wind power loads according to requirements, a power grid user APP platform is a load change condition of big data collection user equipment, and cabinets of the power grid user APP platform and the historical data server are arranged in a row; the load change prediction feedforward device processes big data of user equipment, the load change prediction feedforward device and a cabinet of a power grid user APP platform are arranged in a row, and the historical data server, the power grid user APP platform and the load change prediction feedforward device are connected with an alternating current power supply through communication cables. The invention has strong practicability and is suitable for the wind power industry.
Description
Technical Field
The invention relates to a wind power load prediction method based on an annual load curve and power grid user equipment change feedforward, and belongs to the field of wind power load prediction.
Background
Wind is one of pollution-free energy sources. Moreover, it is inexhaustible. The wind power generation device is very suitable for and can be used for generating electricity by utilizing wind power according to local conditions in coastal islands, grassland pasturing areas, mountain areas and plateau areas with water shortage, fuel shortage and inconvenient traffic. Offshore wind power is an important field of renewable energy development, is an important force for promoting wind power technology progress and industry upgrading, and is an important measure for promoting energy structure adjustment. China is rich in offshore wind energy resources, offshore wind power project construction is accelerated, and the method has important significance for promoting treatment of atmospheric haze, adjustment of energy structures and conversion of economic development modes in coastal areas.
The wind power generator is used for continuously converting wind energy into standard commercial power for home use, and the saving degree is obvious. The performance of the existing wind driven generator is greatly improved compared with that of the existing wind driven generator in years, the existing wind driven generator is only used in a few remote areas, and the wind driven generator is directly powered by a 15W bulb, so that the bulb is always damaged. Due to the technical progress, the prior wind power generation system adopts an advanced charger and an advanced inverter, becomes a small system with certain technological content, and can replace normal commercial power under certain conditions. The mountain area can be used as a street lamp which does not cost money all the year round by the system; the highway can be used as a road sign lamp at night; children in mountain areas can learn the method at night under the daylight lamp; the wind power motor can be used on the roof of the small and high-rise building in the city, which not only saves energy but also is a real green power supply. The household wind driven generator can not only prevent power failure, but also increase the life interest. In tourist attractions, frontiers, schools, troops and even backward mountainous areas, wind driven generators are becoming the purchasing hotspot of people. The wireless amateurs can use their own technology to serve people in mountainous areas in the aspect of wind power generation, so that people can use electricity for watching TV and lighting synchronously with cities, and can also make their own labor rich.
Since wind power generation is used as clean energy to replace traditional energy in a large area in the future, load prediction of wind power is imperative.
The load prediction is to determine load data of a certain future moment according to various factors such as the operating characteristics, capacity increase decision, natural conditions and social influence of a system under the condition of meeting a certain precision requirement, wherein the load refers to the power demand (power) or the power consumption. Load prediction is an important content in economic dispatch of a power system and is an important module of an Energy Management System (EMS). Since the load prediction is to estimate its future value from the past and present of the power load, the object of the load prediction work is an event of no certainty. Only the uncertain events and the random events need people to adopt proper prediction technology to deduce the development trend and the possible achieved condition of the load. The methods for load prediction are mainly classified into classical prediction methods and modern prediction methods. The power load prediction is one of the important work of the power department, the accurate load prediction can economically and reasonably arrange the start and stop of the generator set in the power grid, maintain the safety and stability of the power grid operation, reduce the unnecessary rotation reserve capacity, reasonably arrange the unit maintenance plan, ensure the normal production and life of the society, effectively reduce the power generation cost and improve the economic benefit and the social benefit.
Wind power load prediction is one of important work of an electric power department, accurate load prediction can economically and reasonably arrange the start and stop of a generator set in a power grid, the safety and stability of the operation of the power grid are kept, unnecessary rotation reserve capacity is reduced, a unit maintenance plan is reasonably arranged, normal production and life of the society are guaranteed, the power generation cost is effectively reduced, and economic benefits and social benefits are improved, so the wind power load prediction also has important significance for a wind power generation station.
At present, no relevant research is carried out on a wind power load prediction method based on an annual load curve and power grid user equipment change feedforward.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a wind power load prediction method based on an annual load curve and a change feedforward of power grid user equipment.
The technical scheme adopted by the invention for solving the problems is as follows: a wind power load prediction method based on annual load curve and power grid user equipment change feedforward is characterized in that: the system comprises a historical data server for predicting the annual load curve of the wind power load, a power grid user APP platform, user equipment, a load change prediction feedforward device, a communication cable and an alternating current power supply; the historical data server calls an annual load curve for forecasting wind power loads according to requirements, the power grid user APP platform is the load change condition of the big data collection user equipment, and the power grid user APP platform and the cabinets of the historical data server are arranged in a row; the load change prediction feedforward device is used for processing big data of user equipment, the load change prediction feedforward device and a cabinet of a power grid user APP platform are arranged in a row, and the historical data server, the power grid user APP platform and the load change prediction feedforward device are connected with an alternating current power supply through communication cables.
The loads of the power system can be generally divided into urban civil loads, commercial loads, rural loads, industrial loads, other loads and the like, and different types of loads have different characteristics and laws.
The urban civil load mainly comes from the power consumption load of urban resident household appliances, and has the trend of annual growth and obvious seasonal fluctuation characteristics, and the characteristics of the civil load are closely related to the daily life and work rules of residents.
The commercial load mainly refers to the electric loads of lighting, air conditioning, power and the like in the commercial department, the coverage area is large, the electric increase is stable, and the commercial load also has the characteristic of seasonal fluctuation. Lighting-like loads in commercial loads occupy power system peak hours. In addition, business departments become one of the important factors affecting the power load during holidays because business behaviors increase business hours during the holidays.
The industrial load refers to electricity used for industrial production, the proportion of the general industrial load is the first place in the composition of the electricity, the industrial load not only depends on the working mode of industrial users (including equipment utilization conditions, work shift systems of enterprises and the like), but also has close relation with the industrial characteristics and seasonal factors of various industries, and the general load is relatively constant.
The rural load refers to electricity consumption of rural residents and agricultural production. Such loads are greatly affected by natural conditions such as weather and season, as compared with industrial loads, and are determined by the characteristics of agricultural production. The agricultural power load is also influenced by the types of crops and cultivation habits, but the power grid is beneficial to improving the load rate of the power grid because the time of concentration of the agricultural power load is different from the peak time of urban industrial load.
The load prediction can be classified into ultra-short term, medium term and long term according to the purpose:
the ultra-short-term load prediction is load prediction within 1h in the future, under the safety monitoring state, a prediction value of 5-10 s or 1-5 min is needed, and a prediction value of 10 min-1 h is needed for preventive control and emergency state processing.
And secondly, short-term load prediction refers to daily load prediction and weekly load prediction and is respectively used for arranging a daily scheduling plan and a weekly scheduling plan, wherein the daily scheduling plan and the weekly scheduling plan comprise the steps of determining start and stop of a wind turbine generator, link line exchange power, load economic distribution, equipment maintenance and the like, and for the short-term prediction, the load change rule of a power grid needs to be fully researched, and load change related factors, particularly the relation between weather factors, daily types and the like and short-term load change is analyzed.
And thirdly, medium-term load forecasting refers to load forecasting from month to year and mainly comprises the steps of determining the running mode of the wind turbine generator, determining an equipment overhaul plan and the like.
And fourthly, long-term load prediction refers to load prediction within a period of 3-5 years or even longer in the future, and is mainly the prospective planning of power grid transformation and extension work performed by a power grid planning department according to the development of national economy and the demand on power load. The impact of national economic development, national policy and the like is especially researched for medium and long-term load prediction.
The method for predicting the wind power load based on the annual load curve and the change feedforward of the power grid user equipment comprises the following simplified steps:
1) searching a historical annual load curve by a historical data server and preprocessing the historical annual load curve;
2) when a power grid user pays the electric charge on the power grid user APP platform, filling the load change condition of user equipment, such as rated power consumption of a refrigerator filling specification added by the user, power consumption reduced by the user replacing more energy-saving equipment filling compared with the original equipment, design power consumption of a factory filling factory newly built by the user for a legal person, and the like, wherein after the user fills corresponding information, the power grid user APP platform automatically provides preferential service for the user to pay the electric charge;
3) after the power grid user APP platform obtains the load change condition of the big data collection user equipment, the data are transmitted to a load change prediction feedforward device;
4) the load change prediction feedforward device combines the types of the loads, provides calculation feedforward for the annual load curve of the wind power load according to the load rules of time division, day, month and year of different load types and algorithms, and calculates the final wind power load prediction curve value.
Compared with the prior art, the invention has the following advantages and effects:
1. the method is high in practicability, suitable for being used in the wind power industry, has operability, and is a good method proved by practice.
2. Has scientificity.
3. The method has strong operability, indexes are reasonably based on scientific consideration, original data are convenient to obtain, and the method has operability.
4. The comparability is strong.
5. The method is highly conductive, quantifies statistics, and can provide data for scientific research.
6. Has wide applicability.
Drawings
Fig. 1 is a schematic structural diagram of an embodiment of the present invention.
In the figure: historical data server 1, electric wire netting user APP platform 2, user equipment 3, load change prediction feedforward device 4, communication cable 5, alternating current power supply 6.
Detailed Description
The present invention will be described in further detail below by way of examples with reference to the accompanying drawings, which are illustrative of the present invention and are not to be construed as limiting the present invention.
Examples are given.
Referring to fig. 1, the wind power load prediction method based on the annual load curve and the change feedforward of the power grid user equipment in the embodiment includes a historical data server 1 for predicting the annual load curve of the wind power load, a power grid user APP platform 2, user equipment 3, a load change prediction feedforward device 4, a communication cable 5 and an alternating current power supply 6; the historical data server 1 calls an annual load curve for forecasting wind power loads according to requirements, the power grid user APP platform 2 is the load change condition of the big data collection user equipment 3, and cabinets of the power grid user APP platform 2 and the historical data server 1 are arranged in a row; the load change prediction feed-forward device 4 processes big data of the user equipment 3, the load change prediction feed-forward device 4 and a cabinet of the power grid user APP platform 2 are arranged in a row, and the historical data server 1, the power grid user APP platform 2 and the load change prediction feed-forward device 4 are connected with an alternating current power supply 6 through a communication cable 5.
The loads of the power system can be generally divided into urban civil loads, commercial loads, rural loads, industrial loads, other loads and the like, and different types of loads have different characteristics and laws.
The urban civil load mainly comes from the power consumption load of urban resident household appliances, and has the trend of annual growth and obvious seasonal fluctuation characteristics, and the characteristics of the civil load are closely related to the daily life and work rules of residents.
The commercial load mainly refers to the electric loads of lighting, air conditioning, power and the like in the commercial department, the coverage area is large, the electric increase is stable, and the commercial load also has the characteristic of seasonal fluctuation. Lighting-like loads in commercial loads occupy power system peak hours. In addition, business departments become one of the important factors affecting the power load during holidays because business behaviors increase business hours during the holidays.
The industrial load refers to electricity used for industrial production, the proportion of the general industrial load is the first place in the composition of the electricity, the industrial load not only depends on the working mode of industrial users (including equipment utilization conditions, work shift systems of enterprises and the like), but also has close relation with the industrial characteristics and seasonal factors of various industries, and the general load is relatively constant.
The rural load refers to electricity consumption of rural residents and agricultural production. Such loads are greatly affected by natural conditions such as weather and season, as compared with industrial loads, and are determined by the characteristics of agricultural production. The agricultural power load is also influenced by the types of crops and cultivation habits, but the power grid is beneficial to improving the load rate of the power grid because the time of concentration of the agricultural power load is different from the peak time of urban industrial load.
The different loads are classified into a first type load and a second type load.
One type of load: if major equipment damage occurs, a large amount of waste products appear in products, which causes production disorder, blockage of important traffic hubs and main lines, interruption of broadcast communication or urban water sources, serious environmental pollution and the like; war factories, large steel mills, rocket launching bases, hospitals and the like belong to a class of loads; uninterrupted power supply is guaranteed for such loads. One type of load is the predicted base load, and the area under the curve is always present.
The second type of load: the power supply interruption causes serious production halt, shutdown, traffic jam in local areas, disorder of normal life order of most urban residents and the like; enterprise factories, large towns, rural irrigation and drainage stations and the like belong to the second type of loads; uninterrupted power supply is also to be ensured for such loads, where possible. The area under the curve also always exists as the predicted base load for the class two loads.
Three types of loads: the general loads except the first-class load and the second-class load refer to air conditioning systems (including a water chilling unit, a chilled water pump, a cooling water pump and a cooling tower fan) in a public area and a management area, advertisement lighting, a maintenance power supply, cleaning machinery, domestic electricity and the like, and the loads are called as three-class loads, wherein the loss caused by short-time power failure is small; the plant auxiliary workshop, small town, rural residents use electricity and the like belong to three types of loads; a short power outage can occur for such loads.
The method for predicting the wind power load based on the annual load curve and the change feedforward of the power grid user equipment comprises the following simplified steps:
1) searching a historical annual load curve by the historical data server 1 and preprocessing the historical annual load curve;
2) when a power grid user pays the electric charge on the power grid user APP platform 2, filling the load change condition of the user equipment 3, such as the fact that a refrigerator is additionally added by the user to fill the rated power consumption on a refrigerator specification, the user replaces more energy-saving equipment to fill the power consumption reduced compared with the original equipment, the user creates the design power consumption of a factory filling factory for a legal person, and the like, and after the user fills corresponding information, the power grid user APP platform 2 automatically provides preferential service for the user to pay the electric charge;
3) after the power grid user APP platform 2 obtains the load change condition of the big data collection user equipment 3, the data are transmitted to a load change prediction feedforward device 4;
4) the load change prediction feedforward device 4 combines the types of the loads, provides calculation feedforward for the annual load curve of the wind power load according to the load rules of time division, day, month and year of different load types and algorithms, and calculates the final wind power load prediction curve value.
Examples include, somewhere, urban civil load, commercial load, rural load, industrial load.
The industrial load is a first-class load, the commercial load is a second-class load, and the civil load and the rural load are third-class loads.
Example sites time a month 10 am: the historical data server 1 of the annual load curve of the wind power load of the industrial load is 5000MW, the commercial load is 2000MW, the historical annual load curve is searched by the historical data server 1 of the annual load curve of the wind power load of the civil load, the historical annual load curve is 1500MW after the pretreatment, the historical data server 1 of the annual load curve of the wind power load of the rural load is searched by the historical data server 1, and the historical annual load curve is 800MW after the pretreatment.
The civil load and the rural load power grid users pay the electricity charges on the power grid user APP platform 2, the load change condition of the user equipment 3 is filled, big data shows that the new equipment for purchasing the civil load is increased by 200MW, and the rural load is reduced by 100MW due to the replacement of the energy-saving equipment.
The load change prediction feedforward device 4 combines the load types and gives a new equipment utilization coefficient of 0.9 for civil load purchase and a utilization coefficient of 0.8 for rural loads due to replacement of energy-saving equipment according to the load rules of time division, day, month and year of different load types.
The load prediction value of 10 am at a certain month in the example is as follows: after the industrial load is 5000MW + the commercial load is 2000MW + the civil load historical data server 1 is preprocessed, 1500MW + the civil load purchases new equipment, 200MW 0.9+ the rural load historical data server 1 is preprocessed, and then 800 MW-rural load reduces the load by 100MW 0.8=9400MW because of replacing energy-saving equipment.
Therefore, the load of the predicted embodiment is 9400MW at 10 am in a certain month, and the loads of other time points can be predicted in the same way to form a prediction curve to guide the management of the wind power company.
Although the present invention has been described with reference to the above embodiments, it should be understood that the scope of the present invention is not limited thereto, and that various changes and modifications can be made by those skilled in the art without departing from the spirit and scope of the present invention.
Claims (1)
1. A wind power load prediction method based on annual load curve and power grid user equipment change feedforward is characterized in that: the system comprises a historical data server (1) for predicting the annual load curve of the wind power load, a power grid user APP platform (2), user equipment (3), a load change prediction feedforward device (4), a communication cable (5) and an alternating current power supply (6); the method comprises the following steps that an annual load curve used for forecasting wind power loads is called by the historical data server (1) according to requirements, the power grid user APP platform (2) is the load change condition of big data collection user equipment (3), and cabinets of the power grid user APP platform (2) and the historical data server (1) are arranged in a row; the load change prediction feedforward device (4) processes big data of user equipment (3), the load change prediction feedforward device (4) and a cabinet of a power grid user APP platform (2) are arranged in a row, and the historical data server (1), the power grid user APP platform (2) and the load change prediction feedforward device (4) are connected with an alternating current power supply (6) through a communication cable (5);
the prediction method comprises the following steps:
1) searching a historical annual load curve by a historical data server (1) and preprocessing the historical annual load curve;
2) when a power grid user pays the electric charge on the power grid user APP platform (2), filling the load change condition of the user equipment (3), and after the user fills corresponding information, the power grid user APP platform (2) automatically provides preferential service for the user to pay the electric charge;
3) after the power grid user APP platform (2) obtains the load change condition of the big data collection user equipment (3), data are transmitted to a load change prediction feedforward device (4);
4) the load change prediction feedforward device (4) combines the types of the loads, provides calculation feedforward for the annual load curve of the wind power load according to the load rules of time division, day, month and year of different load types and algorithms, and calculates the final wind power load prediction curve value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910866450.1A CN110707688B (en) | 2019-09-12 | 2019-09-12 | Wind power load prediction method based on annual load curve and power grid user equipment change feedforward |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910866450.1A CN110707688B (en) | 2019-09-12 | 2019-09-12 | Wind power load prediction method based on annual load curve and power grid user equipment change feedforward |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110707688A CN110707688A (en) | 2020-01-17 |
| CN110707688B true CN110707688B (en) | 2020-12-22 |
Family
ID=69194948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910866450.1A Active CN110707688B (en) | 2019-09-12 | 2019-09-12 | Wind power load prediction method based on annual load curve and power grid user equipment change feedforward |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110707688B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063651B (en) * | 2010-11-10 | 2014-04-23 | 中国电力科学研究院 | Urban power grid risk evaluation system based on on-line data acquisition |
| CN102999791A (en) * | 2012-11-23 | 2013-03-27 | 广东电网公司电力科学研究院 | Power load forecasting method based on customer segmentation in power industry |
| CN108090620A (en) * | 2017-12-27 | 2018-05-29 | 国网北京市电力公司 | Electrically-charging equipment market demand forecast method and device |
| CN109272205B (en) * | 2018-08-24 | 2022-03-29 | 国网河南省电力公司电力科学研究院 | Generalized load characteristic analysis method and device |
| CN109494876A (en) * | 2018-11-28 | 2019-03-19 | 国网江苏省电力有限公司南京供电分公司 | A kind of distribution web information system |
-
2019
- 2019-09-12 CN CN201910866450.1A patent/CN110707688B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110707688A (en) | 2020-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ren et al. | Overview of wind power intermittency: Impacts, measurements, and mitigation solutions | |
| CN112178756B (en) | Intelligent heat supply management system and working method thereof | |
| Zeng et al. | Orderly grid connection of renewable energy generation in China: Management mode, existing problems and solutions | |
| CN102611127A (en) | Control method for unifying self-balancing and self-smoothing of micro-grid | |
| Zhang et al. | The flexibility pathways for integrating renewable energy into China’s coal dominated power system: The case of Beijing-Tianjin-Hebei Region | |
| Liu et al. | Impacts of distributed renewable energy generations on smart grid operation and dispatch | |
| CN102427244A (en) | Large-scale photovoltaic wind power information accessing system | |
| CN103577901A (en) | Method of intertidal zone wind power for accessing power grid | |
| CN105406515A (en) | Hierarchically-controlled independent microgrid | |
| Kubatko et al. | Economic and environmental aspects of Smart Grid technologies implementation in Ukraine | |
| CN117175543A (en) | Load-adjustable power distribution network planning strategy optimization method and system | |
| Cai et al. | Electric power big data and its applications | |
| CN110707688B (en) | Wind power load prediction method based on annual load curve and power grid user equipment change feedforward | |
| CN115965291A (en) | Green evaluation method for intelligent power distribution network | |
| CN114626604B (en) | Distributed photovoltaic observation method and system based on reference station perception | |
| Qian et al. | A hybrid power system using wind and diesel generator: A case study at Masirah Island in Oman | |
| CN113093675A (en) | Regional-level multi-energy complementary intelligent energy scheduling control system | |
| Liu et al. | Research on Operation Mode of New Distribution System with Integrating Large Scales of Distributed Photovoltaic | |
| Varho | Environmental impact of photovoltaic electrification in rural areas | |
| CN205178528U (en) | Road distributing type photovoltaic power plant | |
| Xin et al. | Power System Operation Optimization Process and Network System Design Based on Power Big Data | |
| Chen et al. | Evaluation indices set and decision-making method for regional “coal to electricity” optimal development mode | |
| Matheri et al. | Future Distribution Generation in an Intelligent Smart Energy Network | |
| Shao et al. | Research on the Planning of Jiangsu Yancheng New Power System Demonstration Zone with New Energy Resources | |
| Li et al. | Study on Improving the Utilization Efficiency of Distribution Transformer Under Seasonal Special Application Situation |
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 |