CN114626604A - Distributed photovoltaic observation method and system based on reference station perception - Google Patents
Distributed photovoltaic observation method and system based on reference station perception Download PDFInfo
- Publication number
- CN114626604A CN114626604A CN202210243212.7A CN202210243212A CN114626604A CN 114626604 A CN114626604 A CN 114626604A CN 202210243212 A CN202210243212 A CN 202210243212A CN 114626604 A CN114626604 A CN 114626604A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic
- power
- power generation
- reference station
- total
- 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 44
- 230000008447 perception Effects 0.000 title abstract description 6
- 238000010248 power generation Methods 0.000 claims abstract description 216
- 238000004422 calculation algorithm Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000013473 artificial intelligence Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 239000013307 optical fiber Substances 0.000 description 4
- 238000012797 qualification Methods 0.000 description 4
- 229910052799 carbon Inorganic materials 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000009133 cooperative interaction Effects 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000012549 training 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
-
- 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
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a distributed photovoltaic observation method and a distributed photovoltaic observation system based on reference station perception, belonging to the technical field of new energy operation control, wherein the method comprises the following steps: collecting real-time power generation power data of each reference station in each photovoltaic cluster area; acquiring historical generated power data of all photovoltaic power stations in each photovoltaic cluster area; calculating a power generation power proportion coefficient of each reference station in each photovoltaic cluster area according to historical power generation power data; predicting the future generating power of each reference station in each photovoltaic cluster area; and calculating the distributed photovoltaic real-time/predicted total power generation power of the photovoltaic cluster region where each reference station is located according to the power generation power proportion coefficient of each reference station and the real-time/predicted power generation power data of the reference station, and calculating the distributed photovoltaic real-time/predicted total power generation power of each administrative region. The invention fully utilizes the existing data to observe the distributed photovoltaic, and improves the accuracy and the real-time property of the dispatching system to observe the power of the distributed photovoltaic generation.
Description
Technical Field
The invention belongs to the technical field of new energy operation control, and particularly relates to a distributed photovoltaic observation method and system based on reference station sensing.
Background
Solar energy has the advantages of sufficient cleanliness, safety, relative universality, reliable long service life, maintenance-free property, resource sufficiency, potential economy and the like, and has an important position in a long-term energy strategy. New energy such as wind and light and the like continuously increase in the primary energy consumption, and the installed capacity of photovoltaic power generation is rapidly increased. Distributed photovoltaic grid connection and local absorption pressure is increasing day by day, and the characteristics of randomness, fluctuation and intermittence are large, so that greater challenges are brought to safe and stable operation of a power grid. In order to guarantee the sufficient consumption of the distributed photovoltaic and the safe and stable operation of the power grid, the power grid must comprehensively observe the distributed photovoltaic, sense the power generation condition of the photovoltaic in real time and accurately evaluate the future power generation trend of the photovoltaic.
At present, distributed photovoltaic is mainly connected into a power grid through low voltage 380/220V and medium voltage 10 kV. The operation information of the medium-voltage distributed photovoltaic is directly accessed to a power grid dispatching system according to the management requirement; the low-voltage distributed photovoltaic is not incorporated into dispatching management, and only the marketing acquisition system (power consumer electricity utilization information acquisition system) acquires information through the electric energy meter. The data acquisition frequency of the acquisition system is low, the time delay is large, the real-time observation requirement of the dispatching system cannot be met, and the prediction information of future power generation is also lacked, so that the power load curve observed in dispatching is distorted, and the dispatching management of the system is influenced. The low-voltage distributed photovoltaic single station has small capacity, large dispersibility and wide points, and if an acquisition device is additionally arranged for acquiring real-time information, the outstanding problems of high investment cost, large operation and maintenance workload, unclear power grid and user interface and the like exist, and the field can not be implemented.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides the distributed photovoltaic observation method and system based on the reference station sensing, which can observe the distributed photovoltaic by fully utilizing the existing data and improve the accuracy and the real-time property of the dispatching system for observing the power generation power of the distributed photovoltaic.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, a distributed photovoltaic observation method is provided, in which a photovoltaic power station to be observed is divided into a plurality of photovoltaic cluster areas according to a set condition, and at least one photovoltaic power station is selected as a reference station in each photovoltaic cluster area, the method including: collecting real-time power generation power data of each reference station in each photovoltaic cluster area; acquiring historical generated power data of all photovoltaic power stations in each photovoltaic cluster area; calculating a power generation power proportion coefficient of each reference station in each photovoltaic cluster area according to historical power generation power data; calculating the total distributed photovoltaic real-time power generation power of the photovoltaic cluster region where each reference station is located according to the power generation power proportion coefficient of each reference station and the real-time power generation power data of the reference station; and calculating the total distributed photovoltaic real-time power generation power of each administrative region according to the total distributed photovoltaic real-time power generation power of each photovoltaic cluster region.
Further, the dividing the photovoltaic power station to be observed into a plurality of photovoltaic cluster areas according to the set conditions includes: a region range in which the meteorological conditions in an administrative area meet set requirements is divided into a photovoltaic cluster area, and one administrative area can be divided into one or more photovoltaic cluster areas according to the meteorological conditions.
Further, the generated power proportionality coefficient is obtained by the following method:
wherein k isiIs the power generation power proportionality coefficient, P, of the ith reference stationZone-history-sThe total distributed photovoltaic power generation power P of the photovoltaic cluster region at the s momentbase-History-i-sThe generated power of the ith reference station at the s-th time is s, which is the historical time, and s is 1.
Further, the total distributed photovoltaic real-time power generation power P of the photovoltaic cluster region where each reference station is locatedZone(s)Obtained by the following method:
wherein, PRadical-iThe real-time power generation data of the ith reference station in the photovoltaic cluster area are obtained, i is an integer from 1 to n, and n is the number of the reference stations in one photovoltaic cluster area.
Further, the total distributed photovoltaic real-time power generation power of each administrative region is obtained by the following method:
county/regional distributed photovoltaic real-time power generation total power PCounty areaComprises the following steps:
wherein, PRegion-jThe total distributed photovoltaic real-time power generation power of the jth photovoltaic cluster region is divided into u photovoltaic cluster regions in a county/district; distributed photovoltaic real-time power generation total power P in urban areaUrban areaComprises the following steps:
wherein, PCounty area-lThe total power of distributed photovoltaic real-time power generation in the ith county/region is v counties/regions in the whole city; provincial distributed photovoltaic real-time power generation total power PProvincial regionComprises the following steps:
wherein, PCity area-hThe total distributed photovoltaic real-time power generation power of the h city area is w cities in total province.
Further, acquiring meteorological forecast data of future moments of the positions of the reference stations; inputting the obtained meteorological prediction data into the established reference station photovoltaic power generation power prediction model to obtain the predicted power generation power of each reference station; calculating the total distributed photovoltaic prediction power generation power of the photovoltaic cluster region where each reference station is located according to the power generation power proportion coefficient of each reference station and the predicted power generation power of the reference station; and calculating the total power generation power of the distributed photovoltaic prediction of each administrative region according to the total power generation power of the distributed photovoltaic prediction of each photovoltaic cluster region.
Further, the reference station photovoltaic power generation power prediction model is trained through an artificial intelligence algorithm by using historical power generation power data of a reference station and historical meteorological data of a position where the reference station is located, wherein the historical power generation power data of the reference station correspond to the historical meteorological data.
Further, the artificial intelligence algorithm includes, but is not limited to, a long-short term memory algorithm, a support vector machine algorithm, a random forest algorithm, a markov chain algorithm, and a gradient boosting decision tree algorithm.
Further, the total power P of distributed photovoltaic prediction power generation of the photovoltaic cluster region where each reference station is locatedZone-preObtained by the following method:
distributed photovoltaic prediction total power generation power P of photovoltaic cluster regionZone-preComprises the following steps:
wherein, PRadical-pre-iPredicting photovoltaic power generation power data of an ith reference station in a photovoltaic cluster area, wherein i is an integer from 1 to n, and n is the number of the reference stations in one photovoltaic cluster area;
further, the total power generation power of the distributed photovoltaic prediction of each administrative region is obtained by the following method:
county/regional distributed photovoltaic prediction total power generation power PCounty area-forecastComprises the following steps:
wherein, PZone-pre-jPredicting the total power generation power for the distributed photovoltaic of the jth photovoltaic cluster area, wherein the prefecture/district is divided into u photovoltaic cluster areas; distributed photovoltaic prediction power generation total power P in urban areaCity region-preComprises the following steps:
wherein, PCounty area-Pre-lPredicting the total power generation power for the distributed photovoltaic in the ith county/district, wherein the total number of the counties/districts in the city is v; provincial distributed photovoltaic prediction power generation total power PProvincial-level-prefectural-level-partComprises the following steps:
wherein, PCity area-pre-hAnd predicting the total power generation power for the h-th city domain distributed photovoltaic, wherein the total province has w cities.
In a second aspect, a distributed photovoltaic observation system is provided, in which a photovoltaic power station to be observed is divided into a plurality of photovoltaic cluster areas according to a set condition, and at least one photovoltaic power station is selected as a reference station in each photovoltaic cluster area, the system including: the first data acquisition module is used for acquiring real-time power generation power data of each reference station in each photovoltaic cluster area; the second data acquisition module is used for acquiring historical generated power data of all photovoltaic power stations in each photovoltaic cluster area; the generating power proportion coefficient calculating module is used for calculating the generating power proportion coefficient of each reference station in each photovoltaic cluster area according to historical generating power data; the photovoltaic cluster area power calculation module is used for calculating the total distributed photovoltaic real-time power generation power of the photovoltaic cluster area where each reference station is located according to the power generation power proportion coefficient of each reference station and the real-time photovoltaic power generation power data of the reference station; and each administrative area power calculation module is used for calculating the total distributed photovoltaic real-time power generation power of each administrative area according to the total distributed photovoltaic real-time power generation power of each photovoltaic cluster area.
Compared with the prior art, the invention has the following beneficial effects:
(1) calculating the power generation power proportion coefficient of each reference station in each photovoltaic cluster area according to the historical power generation power data of all photovoltaic power stations in each photovoltaic cluster area, and calculating the total distributed photovoltaic real-time power generation power of the photovoltaic cluster area where each reference station is located and the total distributed photovoltaic real-time power generation power of each administrative area according to the power generation power proportion coefficient of each reference station and the real-time photovoltaic power generation power data of the reference station; the existing data can be fully utilized to observe the distributed photovoltaic, so that the accuracy and the real-time performance of the dispatching system in observing the power of the distributed photovoltaic are improved;
(2) the method fully utilizes the existing facilities and conditions, fully excavates the potential value of data, calculates the operation power generation condition of the distributed photovoltaic in real time, predicts the future power generation condition, improves the observation real-time and accuracy of the power grid on the distributed photovoltaic, provides basic conditions for source grid load storage cooperative interaction regulation and control, and assists in the development and construction of the distributed photovoltaic in the whole county and the realization of a double-carbon target;
(3) the invention can observe and accurately predict the operation state of the distributed photovoltaic in real time, promote the effective management of the distributed photovoltaic and reduce the equipment investment and the labor input.
Drawings
Fig. 1 is a schematic flow chart of a distributed photovoltaic observation method based on reference station sensing according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The first embodiment is as follows:
a distributed photovoltaic observation method based on reference station perception divides photovoltaic power stations into a plurality of photovoltaic cluster areas according to set conditions, at least one photovoltaic power station is selected as a reference station in each photovoltaic cluster area, and the method comprises the following steps: collecting real-time power generation power data of each reference station in each photovoltaic cluster area; acquiring historical generated power data of all photovoltaic power stations in each photovoltaic cluster area; calculating a power generation power proportion coefficient of each reference station in each photovoltaic cluster area according to historical power generation power data; calculating the total distributed photovoltaic real-time power generation power of the photovoltaic cluster region where each reference station is located according to the power generation power proportion coefficient of each reference station and the collected real-time power generation power data of the reference station; and calculating the total distributed photovoltaic real-time power generation power of each administrative region according to the total distributed photovoltaic real-time power generation power of each photovoltaic cluster region.
The method comprises the steps of reasonably dividing geographical photovoltaic cluster areas, selecting proper photovoltaic reference stations, collecting photovoltaic power generation power of the reference stations, obtaining all distributed photovoltaic power generation power data in the areas, dynamically calculating power generation power proportion coefficients of all distributed photovoltaic power generation power and reference station photovoltaic power generation power in each photovoltaic cluster area, and calculating the total distributed photovoltaic real-time power generation power of the photovoltaic cluster areas where the reference stations are located according to the real-time power generation power data of the reference stations and the power generation power proportion coefficients. The photovoltaic future generation power of the reference station is predicted, the predicted generation power of distributed photovoltaic in the photovoltaic cluster region is calculated through the photovoltaic predicted power data of the reference station and the generation power proportional coefficient, so that accurate monitoring of county (district), city and provincial region distributed photovoltaic real-time generation states and prediction and evaluation of future generation states can be achieved through photovoltaic cluster region data accumulation, the monitoring requirement of large-scale access of current new energy to a power grid is met, a large amount of equipment investment and manpower investment are avoided, the whole county distributed photovoltaic development construction and the double-carbon target realization are assisted, and the method has a good application prospect. The main flow of the present invention is shown in FIG. 1.
The method comprises the following steps: and (2) photovoltaic cluster area division, namely dividing a region range with similar meteorological conditions in an administrative range into a photovoltaic cluster area according to administrative divisions, geographic positions, solar irradiation amount, temperature, humidity and other meteorological conditions, and dividing an administrative area into a photovoltaic cluster area or a plurality of photovoltaic cluster areas according to the meteorological conditions.
In the specific implementation process, a power supply network in an administrative area range is divided into a plurality of power supply grids by a power grid company, distributed photovoltaics are connected to one power supply grid, therefore, power supply grids divided by the administrative area and the power grid company are combined to divide a photovoltaic cluster area, one power supply grid is divided into one photovoltaic cluster area, or a plurality of power supply grids with similar meteorological conditions are divided into one photovoltaic cluster area, and the meteorological conditions of the power supply grids are judged according to the similarity of solar daily exposure, temperature and humidity in the grids.
Step two: the method comprises the steps of selecting a reference station, selecting a photovoltaic power station which is stable in operation and has information directly accessed to a scheduling system in each photovoltaic cluster area as the reference station, selecting 1 or more reference stations in one photovoltaic cluster area, uploading real-time power generation power data to the scheduling system by the reference station, enabling an information uploading link to be stable and reliable, enabling the uploading information to be excellent in quality (invalid data or few bad data), enabling a communication medium for uploading the information to be an optical fiber private network or a wireless private network, and recording and storing the real-time data to form historical data.
In a specific implementation process, a centralized photovoltaic power station and a 10kV distributed photovoltaic power station in a photovoltaic cluster area can be selected as reference stations, and the following conditions are met:
a) a photovoltaic power station serving as a reference station and a dispatching system have a direct data interaction channel to ensure the reliability and real-time performance of the photovoltaic power generation power data uploading to the dispatching system, a centralized photovoltaic power station is accessed to the dispatching system through a dispatching data network (a special optical fiber network), and a 10kV distributed photovoltaic power station is accessed to the dispatching system through the dispatching data network (the special optical fiber network) or a special wireless network.
b) The equipment of the photovoltaic power station serving as the reference station runs stably, the data quality is high, the qualification rate is higher than a set threshold value, and the calculation formula of the qualification rate Q is as follows:
wherein, NerrorNumber of data anomalies in one day for the reference station, NdayThe total number of data of a reference station in one day, when the qualification rate meets a set threshold value, the output data of the distributed photovoltaic station is qualified, the output data can be used for calculating the power of the distributed photovoltaic power generation, and the threshold value of the data qualification rate is based onThe condition requirement may be set to 95%.
Step three: and the generated power acquisition comprises the real-time generated power data acquisition of a reference station and the historical generated power data acquisition of all distributed photovoltaic cells in a photovoltaic cluster area.
The reference station is directly connected with the dispatching system through a dispatching data network (optical fiber private network) or a wireless private network, real-time generated power data of the reference station is uploaded to the dispatching system in real time through a telecontrol device or equipment with a telecontrol function in the station, the dispatching system acquires the uploaded data of the reference station in real time to obtain real-time generated power data P of the reference stationBase ofAnd recording and storing the historical generated power data P forming the reference stationBase-history。
The historical power generation power data of all distributed photovoltaic systems in the region are acquired from a marketing and utilization acquisition system, the marketing and utilization acquisition system regularly acquires data of each distributed photovoltaic grid-connected electric energy meter, wherein the data comprise voltage, current, power generation power and daily generated energy, the data of the electric energy meter are generally 1 min/point, 15 min/point or 1 h/point and are determined by the performance of the distributed grid-connected electric energy meter, and the frequency of acquiring the data of the electric energy meter by the marketing and utilization system is generally 15 min/time, 1 h/time or 1 day/time and is also determined by the performance of the distributed grid-connected electric energy meter. Therefore, in order to ensure the integrity of data acquisition, the dispatching system can acquire the power generation power data of 1 h/point of all the distributed photovoltaic in the previous day through the marketing acquisition system every day, and then accumulate the power of all the distributed photovoltaic in the same photovoltaic cluster area at the same time according to the corresponding relation between the distributed photovoltaic and the photovoltaic cluster area to obtain the total power data P of the distributed photovoltaic power generation in the photovoltaic cluster areaRegion-history。
Step four: calculating a value of a generated power proportionality coefficient k, and calculating the generated power proportionality coefficient of each reference station in each photovoltaic cluster area according to historical generated power data; the generating power proportion coefficient k is the generating total power P of all distributed photovoltaics in the photovoltaic cluster regionRegion-historyThe photovoltaic power generation power P of the reference station at the same momentBase-historyIf there are multiple reference stations in a region, each reference station needs to calculate a power generation function separatelyAnd the rate proportionality coefficient k is the ratio of the historical photovoltaic power generation power of all distributed photovoltaic power generation in the photovoltaic cluster area to the historical photovoltaic power generation power of the reference station at the same moment. In order to improve the accuracy of the generated power proportionality coefficient k, a plurality of proportionality coefficients are calculated by adopting historical data at a plurality of moments, and then an average value is taken. Specifically, historical photovoltaic power generation power data of x days (such as the last 7 days, the last 15 days or the last 30 days) in the near period from 6 to 18 points every day (considering that photovoltaic power generation generally starts from 6 points in the morning and stops after 18 points in the evening) can be selected for calculation, and then a plurality of calculated data are averaged to obtain a power generation power proportion coefficient k, and the power generation power proportion coefficient k of the ith reference stationiThe calculation method comprises the following steps:
wherein, PZone-history-sThe total distributed photovoltaic power generation power P of the photovoltaic cluster region at the s momentbase-History-i-sAnd the generated power of the ith reference station at the s-th time is the historical time, and the m-th time is the historical time, wherein s is 1, x, m, and the m-th time is the historical time.
The calculation of the generated power proportionality coefficient k value is performed periodically and continuously, the calculation can be performed once every day or once every multiple days, the historical data used for calculation are also updated in a continuous mode, and each calculation is performed by using the historical data which are calculated from x days before when the day is 0.
Step five: calculating photovoltaic real-time power generation power, namely calculating the total distributed photovoltaic real-time power generation power of a photovoltaic cluster area where each reference station is located according to the power generation power proportion coefficient of each reference station and the collected real-time power generation power data of the reference station; distributed photovoltaic real-time power generation total power P of photovoltaic cluster regionZone(s)Real-time generated power data P through reference stationBase ofMultiplying the power generation power proportional coefficient k to obtain PZone(s)＝PBase ofX k. If a region has a plurality of reference stations, each reference station independently calculates the total distributed photovoltaic real-time power generation power of the regionThen, the final distributed photovoltaic real-time power generation total power P of the photovoltaic cluster area is obtained by taking an average valueZone(s)The specific calculation method comprises the following steps:
wherein, PRadical-iThe real-time power generation data of the ith reference station in the photovoltaic cluster area are obtained, i is an integer from 1 to n, and n is the number of the reference stations in one photovoltaic cluster area.
The historical photovoltaic power generation power data of the distributed photovoltaic of the photovoltaic cluster area is formed by recording and storing the real-time photovoltaic power generation power of the distributed photovoltaic of the photovoltaic cluster area.
And calculating the total distributed photovoltaic real-time power generation power of each administrative region according to the total distributed photovoltaic real-time power generation power of each photovoltaic cluster region.
Obtaining total power P of distributed photovoltaic real-time power generation of photovoltaic cluster regionZone(s)The county (district) region distributed photovoltaic power generation total power is obtained by accumulating the power generation power of all the photovoltaic cluster region distributed photovoltaic within the county (district) range at the same time, and the county (district) region distributed photovoltaic real-time power generation total power PCounty areaThe method is characterized in that the method is a sum of distributed photovoltaic real-time power generation power of all photovoltaic cluster regions within a county (district):
wherein, PRegion-jThe total distributed photovoltaic real-time power generation power of the jth photovoltaic cluster region is divided into u photovoltaic cluster regions in a county/district; the county (district) distributed photovoltaic historical power generation total power can be formed by recording and storing county (district) distributed photovoltaic real-time power generation total power, and can also be obtained by accumulating historical power generation power of all photovoltaic cluster regional distributed photovoltaic in the county (district) range at the same time.
Obtaining county (district) distributed photovoltaic real-time power generation total power PCounty areaDistributed photovoltaic real-time power generation in urban areaTotal power PUrban areaThe total power P is obtained by accumulating the total power generation power of all county-area distributed photovoltaics in the whole city range at the same time, and the total power P is generated by the distributed photovoltaics in the city area in real timeUrban areaThe total power sum of distributed photovoltaic real-time power generation of all counties (regions) in the whole city range is as follows:
wherein, PCounty area-lThe total power of distributed photovoltaic real-time power generation in the ith county/region is v counties/regions in the whole city; the total power of the urban distributed photovoltaic historical power generation can be stored and formed by urban distributed photovoltaic real-time power generation total power records, and can also be obtained by accumulating the total power of the historical power generation of all county (district) distributed photovoltaic in the whole city range at the same time.
Obtaining total power P of distributed photovoltaic real-time power generation in urban areaUrban areaThen, the total power P of distributed photovoltaic real-time power generation of provincial regionProvincial regionThe total power P of distributed photovoltaic real-time power generation of provincial domains is obtained by the total accumulation of power generation of all urban distributed photovoltaic in the whole provincial scope at the same timeProvincial regionThe method is the sum of the total power of distributed photovoltaic real-time power generation in all urban areas within the whole province range:
wherein, PCity area-hAnd for the h city distributed photovoltaic real-time power generation total power, the total province has w cities. The total historical power generation power of the provincial region distributed photovoltaic can be formed by recording and storing the total power generation power of the provincial region distributed photovoltaic in real time, and can also be obtained by accumulating the total historical power generation power of all urban region distributed photovoltaic in the whole provincial region at the same time.
Step six: forecasting the photovoltaic power generation power of the reference station, and training a photovoltaic power generation power forecasting model of the reference station through artificial intelligence algorithms through the photovoltaic historical power generation power of the reference station and historical meteorological data (solar irradiance, temperature, humidity and air pressure) of the position of the reference station, wherein the artificial intelligence algorithms include but are not limited to a long-short term memory (LSTM) algorithm, a Support Vector Machine (SVM) algorithm, a random forest algorithm, a Markov chain algorithm and a gradient lifting decision tree (XGboost) algorithm; and inputting weather prediction data (solar irradiation amount, temperature, humidity and air pressure) at the future moment into the trained prediction model to obtain the predicted power generation power of the photovoltaic future moment of the reference station. The weather prediction data may be acquired from a weather forecasting center (chinese national weather information center, the united states aviation and space agency, the european mid-term weather forecasting center, etc.). The method for predicting the photovoltaic power generation power of the reference station comprises the following specific steps: acquiring weather prediction data of future moments of positions of all reference stations; inputting the obtained meteorological prediction data into the established reference station photovoltaic power generation power prediction model to obtain the predicted power generation power of each reference station; calculating the total distributed photovoltaic prediction power generation power of the photovoltaic cluster region where each reference station is located according to the power generation power proportion coefficient of each reference station and the predicted power generation power of the reference station; and calculating the total power generation power of the distributed photovoltaic prediction of each administrative region according to the total power generation power of the distributed photovoltaic prediction of each photovoltaic cluster region.
Step seven: calculating the photovoltaic predicted power generation power, after acquiring the photovoltaic predicted power generation power of the reference station, calculating the predicted total power generation power of the distributed photovoltaic of the photovoltaic cluster region, county (district) region, city region and provincial region by adopting the same method in the fifth step based on the power generation power proportionality coefficient k in the fourth step, wherein the predicted total power generation power P of the distributed photovoltaic predicted total power generation power of the photovoltaic cluster regionZone-preComprises the following steps:
wherein, PRadical-pre-iPredicting photovoltaic power generation power data of an ith reference station in a photovoltaic cluster area, wherein i is an integer from 1 to n, and n is the number of the reference stations in one photovoltaic cluster area;
county/regional distributed photovoltaic prediction total power generation power PCounty area-forecastComprises the following steps:
wherein, PRegion-pre-jThe total power generation power is predicted for the distributed photovoltaic of the jth photovoltaic cluster region, and the prefecture/district is divided into u photovoltaic cluster regions;
distributed photovoltaic prediction power generation total power P in urban areaCity region-preComprises the following steps:
wherein, PCounty area-Pre-lPredicting the total power generation power for the distributed photovoltaic in the ith county/district, wherein the total number of the counties/districts in the city is v;
provincial distributed photovoltaic prediction power generation total power PProvincial-prefectureComprises the following steps:
wherein, PCity area-pre-hThe total distributed photovoltaic real-time power generation power of the h city area is w cities in total province.
The distributed photovoltaic power generation monitoring system can observe the distributed photovoltaic by fully utilizing the existing data, improves the accuracy and the real-time property of the dispatching system for observing the power generation power of the distributed photovoltaic, improves the effective management of the distributed photovoltaic, and can reduce the equipment investment and the labor input; the method fully utilizes the existing facilities and conditions, fully excavates the potential value of data, calculates the running power generation condition of the distributed photovoltaic in real time, predicts the future power generation condition, improves the real-time performance and accuracy of the power grid for observing the distributed photovoltaic, provides basic conditions for the source grid load storage cooperative interaction regulation and control, and assists the development and construction of the distributed photovoltaic in the whole county and the realization of a double-carbon target.
Example two:
based on a distributed photovoltaic observation method based on reference station perception in the first embodiment, the first embodiment provides a distributed photovoltaic observation system based on reference station perception, a photovoltaic power station to be observed is divided into a plurality of photovoltaic cluster areas according to a set condition, at least one photovoltaic power station is selected as a reference station in each photovoltaic cluster area, and the system comprises: the first data acquisition module is used for acquiring real-time power generation power data of each reference station in each photovoltaic cluster area; the second data acquisition module is used for acquiring historical generated power data of all photovoltaic power stations in each photovoltaic cluster area; the generating power proportion coefficient calculating module is used for calculating the generating power proportion coefficient of each reference station in each photovoltaic cluster area according to historical generating power data; the photovoltaic cluster area power calculation module is used for calculating the total distributed photovoltaic real-time power generation power of the photovoltaic cluster area where each reference station is located according to the power generation power proportion coefficient of each reference station and the collected real-time power generation power data of the reference station; and each administrative area power calculation module is used for calculating the total distributed photovoltaic real-time power generation power of each administrative area according to the total distributed photovoltaic real-time power generation power of each photovoltaic cluster area.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, it is possible to make various improvements and modifications without departing from the technical principle of the present invention, and those improvements and modifications should be considered as the protection scope of the present invention.
Claims (11)
1. A distributed photovoltaic observation method is characterized in that a photovoltaic power station to be observed is divided into a plurality of photovoltaic cluster areas according to set conditions, at least one photovoltaic power station is selected as a reference station in each photovoltaic cluster area, and the method comprises the following steps:
collecting real-time power generation power data of each reference station in each photovoltaic cluster area;
acquiring historical generated power data of all photovoltaic power stations in each photovoltaic cluster area;
calculating a power generation power proportion coefficient of each reference station in each photovoltaic cluster area according to historical power generation power data;
calculating the total distributed photovoltaic real-time power generation power of the photovoltaic cluster region where each reference station is located according to the power generation power proportion coefficient of each reference station and the real-time power generation power data of the reference station;
and calculating the total distributed photovoltaic real-time power generation power of each administrative region according to the total distributed photovoltaic real-time power generation power of each photovoltaic cluster region.
2. The distributed photovoltaic observation method according to claim 1, wherein the dividing of the photovoltaic power plant to be observed into a plurality of photovoltaic cluster areas according to the set conditions comprises: a region range in which the meteorological conditions in an administrative area meet set requirements is divided into one photovoltaic cluster area, and one administrative area can be divided into one or more photovoltaic cluster areas according to the meteorological conditions.
3. The distributed photovoltaic observation method of claim 1, wherein the generated power scaling factor is obtained by:
wherein k isiIs the power generation scale factor, P, of the ith reference stationZone-history-sThe total distributed photovoltaic power generation power P of the photovoltaic cluster region at the s momentbase-History-i-sThe generated power of the ith reference station at the time of s is the historical time, and s is 1.
4. The distributed photovoltaic observation method according to claim 1, wherein the total distributed photovoltaic real-time power generation power P of the photovoltaic cluster region in which each reference station is locatedZone(s)Obtained by the following method:
wherein, PRadical-iThe real-time power generation data of the ith reference station in the photovoltaic cluster area are obtained, i is an integer from 1 to n, and n is the number of the reference stations in one photovoltaic cluster area.
5. The distributed photovoltaic observation method according to claim 2, wherein the total power of distributed photovoltaic real-time power generation of each administrative region is obtained by:
county/regional distributed photovoltaic real-time power generation total power PCounty areaComprises the following steps:
wherein, PRegion-jThe total distributed photovoltaic real-time power generation power of the jth photovoltaic cluster area is divided into u photovoltaic cluster areas in a county/district;
distributed photovoltaic real-time power generation total power P in urban areaUrban areaComprises the following steps:
wherein, PCounty area-lThe total power of distributed photovoltaic real-time power generation in the ith county/region is v counties/regions in the whole city;
provincial distributed photovoltaic real-time power generation total power PProvincial regionComprises the following steps:
wherein, PCity area-hThe total distributed photovoltaic real-time power generation power of the h city area is w cities in total province.
6. Distributed photovoltaic observation method according to claim 1,
acquiring weather prediction data of future moments of positions of all reference stations;
inputting the obtained meteorological prediction data into an established reference station photovoltaic power generation power prediction model to obtain the predicted power generation power of each reference station;
calculating the total distributed photovoltaic prediction power generation power of the photovoltaic cluster region where each reference station is located according to the power generation power proportion coefficient of each reference station and the predicted power generation power of the reference station;
and calculating the total power generation power of the distributed photovoltaic prediction of each administrative region according to the total power generation power of the distributed photovoltaic prediction of each photovoltaic cluster region.
7. The distributed photovoltaic observation method according to claim 6, wherein the reference station photovoltaic power generation power prediction model is trained through an artificial intelligence algorithm by using historical power generation power data of a reference station and historical meteorological data of a position where the reference station is located, wherein the historical power generation power data of the reference station corresponds to the historical meteorological data.
8. The distributed photovoltaic observation method of claim 7, wherein the artificial intelligence algorithm comprises, but is not limited to, a long-short term memory algorithm, a support vector machine algorithm, a random forest algorithm, a Markov chain algorithm, a gradient boosting decision tree algorithm.
9. The distributed photovoltaic observation method according to claim 6, wherein the total power P is predicted by distributed photovoltaic of the photovoltaic cluster region where each reference station is locatedZone-preObtained by the following method:
distributed photovoltaic prediction total power generation power P of photovoltaic cluster regionZone-preComprises the following steps:
wherein, PRadical-pre-iIs the ith base in the photovoltaic cluster regionAnd (3) predicting photovoltaic power generation power data of the quasi-stations, wherein i is an integer from 1 to n, and n is the number of the reference stations in one photovoltaic cluster area.
10. The distributed photovoltaic observation method according to claim 6, wherein the total power generation power of the distributed photovoltaic prediction of each administrative region is obtained by the following method:
county/regional distributed photovoltaic prediction total power generation power PCounty area-forecastComprises the following steps:
wherein, PRegion-pre-jPredicting the total power generation power for the distributed photovoltaic of the jth photovoltaic cluster area, wherein the prefecture/district is divided into u photovoltaic cluster areas;
distributed photovoltaic prediction power generation total power P in urban areaCity region-preComprises the following steps:
wherein, PCounty area-Pre-lThe total power generation power is predicted for the distributed photovoltaic in the ith county/district, and the total city is v counties/districts;
provincial distributed photovoltaic prediction power generation total power PProvincial-level-prefectural-level-partComprises the following steps:
wherein, PCity area-pre-hAnd predicting the total power generation power for the h-th city domain distributed photovoltaic, wherein the total province has w cities.
11. A distributed photovoltaic observation system is characterized in that a photovoltaic power station to be observed is divided into a plurality of photovoltaic cluster areas according to set conditions, at least one photovoltaic power station is selected as a reference station in each photovoltaic cluster area, and the system comprises:
the first data acquisition module is used for acquiring real-time power generation power data of each reference station in each photovoltaic cluster area;
the second data acquisition module is used for acquiring historical generated power data of all photovoltaic power stations in each photovoltaic cluster area;
the generating power proportion coefficient calculating module is used for calculating the generating power proportion coefficient of each reference station in each photovoltaic cluster area according to historical generating power data;
the photovoltaic cluster area power calculation module is used for calculating the total distributed photovoltaic real-time power generation power of the photovoltaic cluster area where each reference station is located according to the power generation power proportion coefficient of each reference station and the real-time photovoltaic power generation power data of the reference station;
and each administrative area power calculation module is used for calculating the total distributed photovoltaic real-time power generation power of each administrative area according to the total distributed photovoltaic real-time power generation power of each photovoltaic cluster area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210243212.7A CN114626604B (en) | 2022-03-11 | 2022-03-11 | Distributed photovoltaic observation method and system based on reference station perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210243212.7A CN114626604B (en) | 2022-03-11 | 2022-03-11 | Distributed photovoltaic observation method and system based on reference station perception |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114626604A true CN114626604A (en) | 2022-06-14 |
| CN114626604B CN114626604B (en) | 2024-07-12 |
Family
ID=81902108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210243212.7A Active CN114626604B (en) | 2022-03-11 | 2022-03-11 | Distributed photovoltaic observation method and system based on reference station perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114626604B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116070728A (en) * | 2022-10-25 | 2023-05-05 | 国网河北省电力有限公司营销服务中心 | Photovoltaic power generation system power generation amount prediction method, device, system and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636076A (en) * | 2019-02-14 | 2019-04-16 | 国能日新科技股份有限公司 | A kind of distributed photovoltaic power prediction main station system |
| CN109978242A (en) * | 2019-03-12 | 2019-07-05 | 国网冀北电力有限公司 | The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics |
| CN112365053A (en) * | 2020-11-11 | 2021-02-12 | 河海大学 | Method, system and computer readable medium for predicting total power of distributed photovoltaic power generation in load region |
| WO2021204226A1 (en) * | 2020-04-09 | 2021-10-14 | 国网江苏省电力有限公司苏州供电分公司 | Photovoltaic power prediction method under lightning condition based on thundercloud trajectory tracking |
-
2022
- 2022-03-11 CN CN202210243212.7A patent/CN114626604B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636076A (en) * | 2019-02-14 | 2019-04-16 | 国能日新科技股份有限公司 | A kind of distributed photovoltaic power prediction main station system |
| CN109978242A (en) * | 2019-03-12 | 2019-07-05 | 国网冀北电力有限公司 | The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics |
| WO2021204226A1 (en) * | 2020-04-09 | 2021-10-14 | 国网江苏省电力有限公司苏州供电分公司 | Photovoltaic power prediction method under lightning condition based on thundercloud trajectory tracking |
| CN112365053A (en) * | 2020-11-11 | 2021-02-12 | 河海大学 | Method, system and computer readable medium for predicting total power of distributed photovoltaic power generation in load region |
Non-Patent Citations (1)
| Title |
|---|
| 张小萌;白恺;柳玉;李智;卢玺宁;周少祥;: "大规模分布式光伏短期集群功率预测综述", 华北电力技术, no. 06, 25 June 2017 (2017-06-25) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116070728A (en) * | 2022-10-25 | 2023-05-05 | 国网河北省电力有限公司营销服务中心 | Photovoltaic power generation system power generation amount prediction method, device, system and medium |
| CN116070728B (en) * | 2022-10-25 | 2024-05-07 | 国网河北省电力有限公司营销服务中心 | Photovoltaic power generation system power generation amount prediction method, device, system and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114626604B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105826944B (en) | A kind of power forecasting method and system of micro-capacitance sensor group | |
| Chaichan et al. | Optimization of stand-alone and grid-connected hybrid solar/wind/fuel cell power generation for green islands: Application to Koh Samui, southern Thailand | |
| CN112510703B (en) | Multi-energy access power grid optimal scheduling method considering coal consumption curve correction | |
| CN105373842A (en) | Micro-grid energy optimization and evaluation method based on full energy flow model | |
| CN109449987A (en) | The power system simulation method and system of new energy power generation grid-connection | |
| Michaelides et al. | The effect of electric vehicle energy storage on the transition to renewable energy | |
| CN114626604B (en) | Distributed photovoltaic observation method and system based on reference station perception | |
| CN111478374B (en) | Dynamic evaluation method for probability distribution and prediction of wind-solar output characteristics | |
| CN116885840A (en) | Distributed new energy online monitoring method and system based on real-time data | |
| CN116247745A (en) | Hydrogen energy micro-grid rolling optimization scheduling method considering unplanned off-grid risk | |
| Feng et al. | Hybrid energy storage sizing in energy hubs: A continuous spectrum splitting approach | |
| CN112491049B (en) | Multi-energy access power grid optimized scheduling method considering on-line coal consumption curve | |
| CN115173464A (en) | Distributed photovoltaic absorption capacity evaluation method and system based on big data analysis | |
| Xu et al. | Dual-layer self-healing strategy for standalone building energy systems: A case study of a tropical island | |
| Onaolapo | Reliability study under the smart grid paradigm using computational intelligent techniques and renewable energy sources. | |
| Lu et al. | Distributed dispatching method of active distribution network considering multiple regulation resources | |
| Huan et al. | Research on Wide-Area Distributed PV Regional Power Prediction Technology | |
| Xiong et al. | Graph Convolutional Network based Electricity Demand Forecasting in Power Distribution Networks | |
| Han et al. | Load regulation application of university campus based on solar power generation forecasting | |
| CN117200340A (en) | New energy consumption capability assessment method based on uncertainty | |
| Liang et al. | Allowable Capacity Analysis of Distributed Renewable Energy Resources in Active Distribution Network | |
| CN116014810A (en) | Optimal configuration method and system for optical storage system of grid distribution network | |
| Jin et al. | Research on providing data and space calculation support for site selection of power transmission and transformation projects | |
| Zhang | Simulation Method for Multiperiod Panoramic Operation of New Energy Power System in Complex Environment | |
| Anwar | Development of Energy Management System for Microgrid Operations |
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 |