Energy storage device and method for improving power prediction accuracy of new energy power station

By designing energy storage devices and corresponding methods in new energy power stations, using the power prediction value matrix and real-time power calculation accuracy, and adjusting the power energy adjustment of the energy storage device in combination with the power market rules, the low power prediction accuracy and low power prediction accuracy in the existing technology are solved. The problem of insufficient profitability has achieved higher prediction accuracy and profitability.

CN119070267APending Publication Date: 2024-12-03CHINA POWER INVESTMENT POWER ENG CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310630594.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-31
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing technology has failed to effectively combine the rules of the power market, resulting in low accuracy and insufficient profitability of new energy power plants.

Method used

Design an energy storage device and method, extract the power prediction value from the power prediction system through the data acquisition unit, build a power prediction value matrix, and use the power control unit to calculate the power prediction accuracy in real time, and adjust the energy storage device according to the power market assessment requirements. Electricity is stored or released to optimize power on the internet.

Benefits of technology

It improves the accuracy of medium- and short-term and ultra-short-term power prediction of new energy power plants, reduces the assessment costs of power plants, improves profitability, and does not lose wind energy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119070267A_ABST
    Figure CN119070267A_ABST
Patent Text Reader

Abstract

The invention provides an energy storage device and method for improving the power prediction accuracy of a new energy power station, and the method comprises the following steps: S1, extracting a power prediction value reported to a power grid at each moment from a power prediction system through a data collection unit, constructing a power prediction value matrix, and storing the power prediction value matrix in a storage unit; s2, when a certain selected moment is reached, the power control unit extracts real-time power and a power predicted value matrix from the storage unit, and the real-time power and the power predicted value matrix are used as input parameters to be transmitted to the power control unit; s3, calculating the power prediction accuracy in real time according to the power prediction value matrix and the real-time power; and S4, a control instruction is issued, and the energy storage device stores or releases the electric energy, so that the internet-surfing power is adjusted. The method can improve the medium-short-term and ultra-short-term power prediction accuracy, effectively reduces the assessment of the new energy power station, does not lose wind energy, and facilitates the improvement of the profit level of the new energy power station.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of new energy power prediction, and in particular to an energy storage device and method for improving the accuracy of power prediction of new energy power stations. Background Art

[0002] Accelerating the construction of a new power system with new energy as the main body is the only way for the power industry to promote its own carbon emission reduction and support carbon emission reduction in the whole society. It is also an inevitable choice for achieving high-quality development of the power industry.

[0003] At present, new energy represented by wind power and photovoltaics is gradually replacing conventional energy. However, the intermittent and volatile nature of wind and solar energy affects efficient and safe grid connection. Short-term or long-term prediction of power generation is the main way to solve this problem.

[0004] The current research direction focuses on improving the accuracy of power prediction, so as to improve the competitiveness of renewable energy power generation in the power trading market. Patent CN103683321A solves wind power smoothing, patent CN104638772A improves wind power prediction accuracy, and patent CN103730902B smoothes wind and solar power fluctuations.

[0005] However, the above research directions and patents only improve the power prediction accuracy or smooth the power, but fail to effectively combine the electricity market rules (for example: ancillary service management implementation rules, grid-connected operation management implementation rules, etc.), improve the accuracy of new energy prediction, reduce the assessment of new energy power stations, and fail to effectively improve the profitability of new energy power generation.

[0006] In view of this, the inventors of the present application have designed an energy storage device and method for improving the accuracy of power prediction of new energy power stations, in order to overcome the above-mentioned technical problems. Summary of the invention

[0007] The technical problem to be solved by the present invention is to overcome the defects of the prior art that the power prediction of new energy sources fails to effectively combine with the electricity market rules, has low accuracy and low profitability, and to provide an energy storage device and method for improving the accuracy of power prediction of new energy power stations.

[0008] The present invention solves the above technical problems through the following technical solutions:

[0009] A method for storing energy to improve the accuracy of power prediction of a new energy power station is characterized in that the method comprises the following steps:

[0010] S1, the data acquisition unit extracts the power prediction value reported to the power grid at each moment from the power prediction system, constructs a power prediction value matrix, and stores it in the storage unit;

[0011] S2. When a selected time is reached, the power control unit extracts the real-time power and the power prediction value matrix from the storage unit, and transmits the real-time power and the power prediction value matrix as input parameters to the power control unit;

[0012] S3. Calculate the power prediction accuracy in real time based on the power prediction value matrix and the real-time power;

[0013] S4. Issue a control instruction, and the energy storage device stores or releases electric energy, thereby adjusting the online power.

[0014] According to an embodiment of the present invention, the step S1 further includes: the data acquisition unit extracts real-time power from the new energy power station and stores it in the storage unit.

[0015] According to one embodiment of the present invention, the step S3 further includes:

[0016] Determine whether the power prediction accuracy meets the power market assessment requirements; when the power market assessment requirements are met, do not adjust the online power; when the power market assessment requirements are not met, use an optimization algorithm, combined with the power and capacity constraints of the energy storage device, to meet the assessment requirements or the lowest assessment cost as the criterion, and find the best power.

[0017] According to an embodiment of the present invention, step S4 includes: issuing a control instruction based on the optimization result, and the energy storage device stores or releases electric energy, thereby adjusting the grid power.

[0018] According to an embodiment of the present invention, the optimization algorithm includes a genetic algorithm, an ant colony algorithm or a particle swarm algorithm.

[0019] The present invention also provides an energy storage device for improving the accuracy of power prediction of a new energy power station, wherein the energy storage device adopts the energy storage method for improving the accuracy of power prediction of a new energy power station as described above, and the energy storage device comprises:

[0020] A data acquisition unit, wherein the data acquisition unit is used to collect the predicted power of the power prediction system and the real-time power of the new energy power station;

[0021] A storage unit, the storage unit is used to store the predicted power data collected by the data collection unit;

[0022] A power control unit, which is used to extract the power prediction data matrix and the real-time power of the new energy power station from the data acquisition unit and calculate the power prediction accuracy;

[0023] An energy storage device, the energy storage device is used to receive instructions from the power control unit, store or release electric energy, and adjust the online power;

[0024] The data acquisition unit, the storage unit, the power control unit and the energy storage device are connected in sequence, the power prediction system and the new energy power station are connected to the data acquisition unit, and the energy storage device is connected to the new energy power station and the power grid.

[0025] According to an embodiment of the present invention, the power control unit is further used to determine whether the power prediction accuracy meets the power market assessment requirements.

[0026] According to an embodiment of the present invention, the power control unit sends a control instruction to the energy storage device after optimization, and the energy storage device stores or releases electric energy and adjusts the actual power.

[0027] The positive and progressive effects of the present invention are:

[0028] The energy storage device and method for improving the power prediction accuracy of new energy power stations of the present invention can improve the accuracy of medium-term, short-term and ultra-short-term power predictions under existing power prediction technology conditions by actively adjusting the control device of the generated power, effectively reduce the assessment of new energy power stations, and do not lose wind energy, which helps to improve the profitability of new energy power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other features, properties and advantages of the present invention will become more apparent through the following description in conjunction with the accompanying drawings and embodiments, in which the same reference numerals always represent the same features, wherein:

[0030] Figure 1 The present invention is a flow chart of an energy storage method for improving the accuracy of power prediction of a new energy power station.

[0031] Figure 2 A schematic diagram of an energy storage device for improving the accuracy of power prediction of a new energy power station according to the present invention.

[0032] [Reference Signs]

[0033] Data acquisition unit 10

[0034] Storage unit 20

[0035] Power control unit 30

[0036] Energy storage device 40

[0037] New energy power station50

[0038] Power prediction system 60

[0039] Grid 70 DETAILED DESCRIPTION

[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0041] Embodiments of the present invention will now be described in detail with reference to the accompanying drawings. Reference will now be made in detail to preferred embodiments of the present invention, examples of which are shown in the accompanying drawings. Wherever possible, the same reference numerals will be used throughout the drawings to represent the same or similar parts.

[0042] Furthermore, although the terms used in the present invention are selected from well-known and commonly used terms, some terms mentioned in the present invention specification may be selected by the applicant at his or her discretion, and their detailed meanings are explained in the relevant parts of the description of this document.

[0043] Furthermore, it is required that the present invention be understood not only by the actual terms used but also by the meanings connoted by each term.

[0044] like Figure 1 As shown, the present invention discloses an energy storage method for improving the accuracy of power prediction of a new energy power station, which comprises the following steps:

[0045] Step S1: The data acquisition unit extracts the power prediction value reported to the power grid at each moment from the power prediction system, constructs a power prediction value matrix A, and stores it in a storage unit.

[0046] Meanwhile, the step S1 preferably also includes: the data acquisition unit extracts real-time power from the new energy power station and stores it in the storage unit.

[0047] Step S2: When a selected moment is reached (for example, moment i), the power control unit extracts the real-time power and the power prediction value matrix A from the storage unit, and transmits the real-time power and the power prediction value matrix A as input parameters to the power control unit.

[0048] Step S3: Calculate the power prediction accuracy in real time based on the power prediction value matrix and the real-time power.

[0049] Preferably, the step S3 further includes:

[0050] Determine whether the power prediction accuracy meets the power market assessment requirements. Since each local power grid has different assessment standards for the power prediction accuracy of new energy power stations, the corresponding calculation formula (ie, assessment standard) can be selected according to the actual region for judgment in step S3.

[0051] When the power market assessment requirements are met, no on-grid power adjustment is performed. When the power market assessment requirements are not met, the optimal power is found by using an optimization algorithm combined with the power and capacity constraints of the energy storage device to meet the assessment requirements or the lowest assessment cost.

[0052] Step S4: issuing a control instruction, the energy storage device stores or releases electric energy, thereby adjusting the grid power.

[0053] Further preferably, the step S4 includes: issuing control instructions according to the optimization result, so that the energy storage device stores or releases electric energy, thereby adjusting the online power to achieve the purpose of no assessment or less assessment.

[0054] Wherein, the optimization algorithm may preferably include a genetic algorithm, an ant colony algorithm or a particle swarm algorithm.

[0055] According to the above method description, a specific embodiment is described in detail below:

[0056] For example, in the Shanxi power market, the medium- and short-term forecast refers to the forecast of renewable energy power generation from 0:00 the next day to the next 168 hours, and the ultra-short-term forecast refers to the forecast of renewable energy power generation from 15 minutes to 4 hours from the time of reporting. The time resolution of both is 15 minutes.

[0057] Medium- and short-term power forecast: Submit medium- and short-term power forecast data and the planned startup capacity from 0:00 to 24:00 the next day to the power grid dispatching agency before 9:00 every day, and the reported startup capacity shall be a 96-point power curve.

[0058] Ultra-short-term power forecast: Ultra-short-term wind power forecast data and startup capacity for 16 time nodes in the next 15 minutes to 4 hours from the time of reporting are automatically submitted to the power grid dispatching agency every 15 minutes.

[0059] This embodiment takes ultra-short-term power prediction as an example:

[0060] For ultra-short-term power, the prediction accuracy is greater than or equal to 90%; when the accuracy is less than 90%, it is assessed according to the following formula (here is the assessment standard for the accuracy of power prediction of new energy power stations in Shanxi Province, which is only an example of the method and is not a limitation of the method of this application. Other regions can select their own assessment standards for judgment):

[0061] Formula 1:

[0062] Formula 2:

[0063] Ultra-short-term accuracy assessment fee = (90% - Acc real-time )×P N ×0.4

[0064] The accuracy of ultra-short-term power prediction is counted on a daily basis and assessed on a monthly basis.

[0065] Among them, Acc real-time is the average accuracy of the ultra-short-term forecast for that day; Acc' real-time,i is the accuracy of the ultra-short-term prediction at time i; Cap is the maximum operating capacity of the new energy power station within the ultra-short-term power prediction period (unit: MW);

[0066] p j is the actual power of the new energy power station at time j (unit: MW), p' j is the predicted power of the new energy power station at time j (unit: MW); n is the predicted points of the assessment on that day; P N It is the installed capacity of new energy power stations (unit: MW).

[0067] Taking a new energy power station as an example, the maximum operating capacity is 49.5MW, the actual power at time i is 27.3MW, and the predicted power before time i is shown in Table 1 below.

[0068] Table 1: Predicted power at simulation time i

[0069] #1 #2 #3 #4 #5 #6 #7 #8 19.569 21.151 19.569 19.569 22.791 20.628 21.8 22.034 #9 #10 #11 #12 #13 #14 #15 #16 21.501 20.672 21.147 22.513 22.238 20.125 21.449 24.745

[0070] According to the above formula 1, the accuracy rate is 87.14%, which does not meet the assessment requirements.

[0071] Through the optimization algorithm, if the energy storage is unlimited, the online power can be adjusted to 25.76MW, which can achieve the power prediction accuracy of 90% and meet the requirements of Shanxi Power Grid. If the energy storage power is only 1MW, the online power can be adjusted to 26.3MW, and the power prediction accuracy is 89.01%, which is 87.14% compared to the original one, and can reduce the assessment costs caused by the ultra-short-term prediction accuracy.

[0072] like Figure 2 As shown, the present invention also provides an energy storage device for improving the accuracy of power prediction of new energy power stations, which adopts the energy storage method for improving the accuracy of power prediction of new energy power stations as described above, and the energy storage device includes: a data acquisition unit 10, a storage unit 20, a power control unit 30 and an energy storage device 40. Among them, the data acquisition unit 10 is used to collect the predicted power of the power prediction system and the real-time power of the new energy power station. The storage unit 20 is used to store the predicted power data collected by the data acquisition unit 10. The power control unit 30 is used to extract the power prediction data matrix and the real-time power of the new energy power station 50 from the data acquisition unit 10, and calculate the power prediction accuracy. The energy storage device 40 is used to receive instructions from the power control unit 30, store or release electric energy, and adjust the online power.

[0073] The data acquisition unit 10 , the storage unit 20 , the power control unit 30 and the energy storage device 40 are connected in sequence, the power prediction system 60 and the new energy power station 50 are connected to the data acquisition unit 10 , and the energy storage device 40 is connected to the new energy power station 50 and the power grid 70 .

[0074] Preferably, the power control unit 30 is also used to determine whether the power prediction accuracy meets the power market assessment requirements. After optimization, the power control unit 30 sends a control instruction to the energy storage device 40, and the energy storage device 40 stores or releases electric energy and adjusts the actual power.

[0075] The power control unit 30 extracts the power prediction data matrix and the real-time power of the new energy power station from the data acquisition unit 10, calculates the power prediction accuracy, and determines whether the accuracy meets the power market assessment requirements, with the purpose of no assessment or less assessment. After optimization, a control instruction is issued to the energy storage device, and the energy storage device stores or releases electric energy, adjusts the actual power, and improves the accuracy of the new energy power prediction.

[0076] According to the above description, the ultra-short-term power prediction accuracy of the embodiment of the present invention can be used for medium- and short-term power prediction accuracy by adjusting the calculation rules according to the power market rules. The embodiment of the present invention collects the actual power first and then optimizes the power; it can also use the power prediction matrix at time i to first optimize the power generation with the highest accuracy, and then adjust the actual power through an auxiliary device with energy storage function.

[0077] In addition, the present invention is not limited to new energy power stations. Power stations with fluctuating characteristics and random power generation can all improve the power prediction accuracy through the present invention. The present invention is not limited to the Shanxi power market. Power markets with power prediction accuracy requirements can still adopt the present invention by adjusting the power prediction accuracy calculation formula in the control system to achieve the function of reducing the assessment.

[0078] In summary, the present invention combines electricity market rules, utilizes a set of energy storage methods and devices to improve the accuracy of power prediction of new energy power stations, actively adjusts the actual power generation power to improve the accuracy of new energy power prediction, and solves the limitations of the prior art of only improving power prediction accuracy or smoothing the power curve.

[0079] The energy storage method and device for improving the power prediction accuracy of new energy power stations of the present invention can improve the accuracy of medium-term, short-term and ultra-short-term power predictions under existing power prediction technology conditions by actively adjusting the control device of the generated power, effectively reduce the assessment of new energy power stations, and do not lose wind energy, which helps to improve the profitability of new energy power stations.

[0080] The present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or multiple times in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0081] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that these are only examples, and the protection scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for storing energy to improve the accuracy of power prediction of new energy power stations, characterized in that: The energy storage method comprises the following steps: S1, the data acquisition unit extracts the power prediction value reported to the power grid at each moment from the power prediction system, constructs a power prediction value matrix, and stores it in the storage unit; S2. When a selected time is reached, the power control unit extracts the real-time power and the power prediction value matrix from the storage unit, and transmits the real-time power and the power prediction value matrix as input parameters to the power control unit; S3. Calculate the power prediction accuracy in real time based on the power prediction value matrix and the real-time power; S4. Issue a control instruction, and the energy storage device stores or releases electric energy, thereby adjusting the online power.

2. The energy storage method for improving the accuracy of power prediction of a new energy power station according to claim 1, characterized in that: The step S1 also includes: the data acquisition unit extracts real-time power from the new energy power station and stores it in the storage unit.

3. The energy storage method for improving the accuracy of power prediction of a new energy power station according to claim 1, characterized in that: After step S3, the following steps are also included: Determine whether the power prediction accuracy meets the power market assessment requirements; when the power market assessment requirements are met, do not adjust the online power; when the power market assessment requirements are not met, use an optimization algorithm, combined with the power and capacity constraints of the energy storage device, to meet the assessment requirements or the lowest assessment cost as the criterion, and find the best power.

4. The energy storage method for improving the accuracy of power prediction of a new energy power station according to claim 3, characterized in that: The step S4 includes: issuing control instructions according to the optimization result, and the energy storage device stores or releases electric energy, thereby adjusting the grid power.

5. The energy storage method for improving the accuracy of power prediction of a new energy power station according to claim 3, characterized in that: The optimization algorithm includes genetic algorithm, ant colony algorithm or particle swarm algorithm.

6. An energy storage device for improving the accuracy of power prediction of a new energy power station, characterized in that: The energy storage device adopts the energy storage method for improving the accuracy of power prediction of a new energy power station as described in any one of claims 1 to 5, and the energy storage device comprises: A data acquisition unit, wherein the data acquisition unit is used to collect the predicted power of the power prediction system and the real-time power of the new energy power station; A storage unit, the storage unit is used to store the predicted power data collected by the data collection unit; A power control unit, which is used to extract the power prediction data matrix and the real-time power of the new energy power station from the data acquisition unit and calculate the power prediction accuracy; An energy storage device, the energy storage device is used to receive instructions from the power control unit, store or release electric energy, and adjust the online power; The data acquisition unit, the storage unit, the power control unit and the energy storage device are connected in sequence, the power prediction system and the new energy power station are connected to the data acquisition unit, and the energy storage device is connected to the new energy power station and the power grid.

7. The energy storage device for improving the accuracy of power prediction of a new energy power station according to claim 6, characterized in that: The power control unit is also used to determine whether the power prediction accuracy meets the power market assessment requirements.

8. The energy storage device for improving the accuracy of power prediction of a new energy power station according to claim 7, characterized in that: The power control unit sends a control instruction to the energy storage device after optimization, and the energy storage device stores or releases electric energy and adjusts the actual power.