Method, system and equipment for predicting generating capacity based on corrected power and storage medium

Abstract

The invention relates to the technical field of photovoltaic power generation, in particular to a method, a system and equipment for predicting generating capacity based on corrected power and a storage medium. The total deviation accumulated in a plurality of time steps can be effectively reduced; the method is not only suitable for a photovoltaic-based system, but also suitable for a wind power-based system or a photovoltaic and wind power coexistence system, especially under the condition that the proportion of renewable energy sources is relatively high; the accurate power generation capacity prediction is beneficial to better resource scheduling of the power grid and is also beneficial to full utilization of limited power generation and energy storage resources; and expandability: the prediction precision can be further improved according to requirements in combination with seasonal effects, equipment degradation and large-scale climate phenomena, and the method is suitable for wide scenes from a short period to a long period.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and particularly to a method, system, device and storage medium for predicting power generation based on corrected power. Background Art

[0002] With the rapid development of renewable energy, photovoltaic power generation has become an important form of energy supplement. However, the volatility and intermittency of photovoltaic power generation pose challenges to the stability and scheduling of the power grid. Therefore, accurately predicting the photovoltaic power generation is of great significance for ensuring the safe and stable operation of the power grid.

[0003] Existing renewable energy prediction methods often focus on minimizing the power prediction error (such as RMSE, MAE) at each time step. However, the small-scale systematic biases existing in these power predictions may accumulate into large power generation biases within a daily, weekly or monthly range. For power systems with a high penetration rate of renewable energy (including photovoltaic, wind power, etc.), especially when the installed capacity margin of power generation and energy storage in the system is small, the requirement for the prediction accuracy of power generation is even more stringent. If the prediction is inaccurate, it is easy to cause power supply-demand imbalance and a decline in operating efficiency.

[0004] Although there are currently various power generation prediction models for photovoltaic or wind power, they usually ignore the total bias accumulated over time and do not focus on the prediction accuracy of power generation. The present invention aims to compare the historical differences between the predicted values and the actual measured values, and correct the prediction through a dynamically updated bias correction factor, thereby improving the prediction accuracy of the total power generation of renewable energy (photovoltaic or wind power). Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies of the prior art and provide a prediction method and system that can effectively reduce the cumulative error of the prediction results for photovoltaic or wind power within a preset prediction period.

[0006] To achieve the above object, the present invention provides a method for predicting power generation based on corrected power, and the specific steps are as follows:

[0007] S1. For the current system, predict the initial power within a given time interval;

[0008] S2. Collect the historical predicted power and actual power, and conduct comparison and systematic bias analysis;

[0009] S3. Determine at least one bias correction factor according to the analysis data in step S2;

[0010] S4. Correct the initial predicted power according to the bias correction factor;

[0011] S5. Calculate the power generation amount predicted by the corrected power in step S4.

[0012] Preferably, step S1 includes step S11, and step S11 is specifically as follows:

[0013] S11. Deploy a sensor network on-site in the photovoltaic system or wind power system to collect meteorological parameters and electrical parameters in real time.

[0014] Preferably, step S1 includes step S12, and step S12 is specifically as follows:

[0015] S12. Input the collected real-time parameters into the LSTM model and obtain the initial predicted power generation power within a given time interval.

[0016] Preferably, step S2 is specifically to perform statistical analysis within the selected time period range to determine whether there is a deviation or a persistent deviation in the initial predicted power generation power.

[0017] Preferably, the deviation correction factor in step S3 is given for a specific time period and can only be applied to the correction of the initial predicted power for the corresponding time period.

[0018] Preferably, step S4 includes step S41, and step S41 is specifically as follows:

[0019] S41. Input the deviation correction factor into the LSTM model, obtain the corrected power generation power, and compare the corrected power generation power with the real-time power generation power to determine whether the prediction within the current time period is accurate.

[0020] Preferably, step S5 is specifically to calculate the power generation amount within the current time period according to the corrected power, and sum up the power generation amount prediction data for different time periods to obtain the power generation amount prediction value for one day.

[0021] The present invention also provides a power generation amount prediction system, which adopts the above method for predicting power generation amount based on corrected power, and includes:

[0022] A data collection and input module, which is used to receive the predicted power value generated by the LSTM model, as well as the corresponding measured power and meteorological data;

[0023] An error analysis module, which is used to compare the historical predicted power with the measured power and calculate the deviation index;

[0024] A deviation correction module, which updates the deviation correction factor according to the prediction duration and the characteristics of photovoltaic or wind power generation;

[0025] A power prediction adjustment module, which applies a deviation correction factor to subsequent power predictions;

[0026] An electricity generation calculation module, which accumulates or integrates the corrected power prediction within a given time range to obtain the final electricity generation prediction value.

[0027] The present invention also provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. The feature is that when the processor executes the program, the steps of the above method are implemented.

[0028] The present invention also provides a computer-readable storage medium, on which a computer program is stored. The feature is that when the program is executed by a processor, the steps of the above method are implemented.

[0029] Compared with the prior art, the technical solution proposed by the present application has the following beneficial effects:

[0030] Reducing cumulative error: By correcting systematic deviations, the total deviation accumulated over multiple time steps can be effectively reduced;

[0031] Strong compatibility: This method is applicable to both photovoltaic-based systems and wind power-based or photovoltaic-wind power coexisting systems, especially in the case of a relatively high proportion of renewable energy;

[0032] Improving grid reliability: Accurate electricity generation prediction helps the grid better schedule resources and also helps to make full use of limited power generation and energy storage resources;

[0033] Scalability: According to requirements, the prediction accuracy can be further improved by combining seasonal effects, equipment degradation, and large-scale climate phenomena, and it is applicable to a wide range of scenarios from short-term to long-term. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, purposes, and advantages of the present invention will become more obvious:

[0035] Figure 1 It is a schematic diagram of the method steps of the present invention;

[0036] Figure 2 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] In the following, the technical solutions in the embodiments of the present invention will be clearly and completely described and discussed in conjunction with the accompanying drawings of the present invention. Obviously, what is described here is only a part of the examples of the present invention, not all of the examples. All other examples obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the protection scope of the present invention.

[0038] It should be noted that when a component is referred to as being "fixed to" another component, it can be directly on the other component or there can also be an intermediate component. When a component is considered to be "connected to" another component, it can be directly connected to the other component or there may be an intermediate component at the same time. When a component is considered to be "disposed on" another component, it can be directly disposed on the other component or there may be an intermediate component at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0040] Embodiment 1

[0041] This embodiment provides a method for predicting power generation based on corrected power, and the specific steps are as follows:

[0042] (1) Initial power prediction

[0043] Adopt a method combining physics and statistics to predict the power generation of a photovoltaic or wind power system within a given time interval (such as every hour).

[0044] For photovoltaics, the core meteorological input is irradiance, and temperature, humidity, cloud cover, cloud height, etc. can also be included; for wind power, the core meteorological inputs are wind speed and wind direction, and additional weather factors such as temperature and humidity can also be included.

[0045] Deploy a sensor network at the site of the photovoltaic system or wind power system to collect meteorological parameters and electrical parameters in real time, input the collected real-time parameters into the LSTM model, and obtain the initial predicted power generation within a given time interval.

[0046] (2) Historical error analysis

[0047] Compare the past predicted power with the actual measured power, and count the deviation or error accumulation between them within a time window.

[0048] Determine whether there is persistent overestimation or underestimation (systematic bias) in the prediction.

[0049] (3) Determination of the bias correction factor

[0050] Generate one or more bias correction factors based on the above historical errors.

[0051] Different correction factors can be used for different scenarios such as different time periods, weather types, or seasons.

[0052] (4) Corrected power prediction

[0053] Apply the bias correction factor to the new round of power prediction results to obtain the corrected prediction value. This can minimize systematic bias in subsequent time periods. Input the bias correction factor into the LSTM model, and obtain the corrected power generation. Compare the corrected power generation with the real-time power generation to determine whether the prediction in the current time period is accurate.

[0054] (5) Calculation of power generation

[0055] Integrate or sum up the corrected power prediction within the corresponding time range (e.g., daily, weekly) to obtain the required predicted power generation value.

[0056] (6) Scope of application

[0057] Applicable to predictions of 4 hours (ultra-short term), 72 hours (short term), 240 hours (medium term), 24 hours (one day), 168 hours (one week). More factors can also be incorporated into the model to extend to long-term predictions of several months or even years.

[0058] For medium-term, long-term, and ultra-long-term predictions, additional factors such as seasonal changes, equipment degradation, and large-scale climate phenomena need to be considered. For long-term predictions (exceeding several months), model the equipment degradation (photovoltaic module attenuation or wind turbine wear) to adjust the prediction value. When the system includes both photovoltaic and wind power, the power generation calculation module can calculate the cumulative power generation predictions of the two separately and can output them combined.

[0059] The LSTM (Long Short-Term Memory) used in this embodiment is a special type of recurrent neural network (RNN) for processing and predicting time series data. By introducing a gating mechanism, LSTM can solve the problem of gradient disappearance encountered by traditional RNNs when processing long sequence data, thus better capturing time dependence.

[0060] The LSTM model is applied to the power system field for power prediction tasks. The specific steps include: First, an LSTM model is constructed based on historical monitoring data to obtain preliminary power prediction results. Then, the real-time monitoring data is compared with the predicted values, the differences are calculated, and the model parameters are adjusted accordingly to improve the prediction accuracy.

[0061] The application of the LSTM model in the power system field has the following advantages:

[0062] High precision: The LSTM model can capture the complex laws and trends of power load changes more accurately, improving the accuracy and precision of prediction.

[0063] Self-adaptability: The LSTM model can automatically learn and adapt to the changes in the power system load, with strong self-adaptive capabilities.

[0064] Parallel processing: Due to its distributed computing structure, the LSTM model can achieve parallel processing, thereby accelerating the speed of load prediction and meeting the real-time requirements. And the LSTM model is already a relatively mature technology in this field, so no more details will be elaborated here.

[0065] Example 2

[0066] A renewable energy power generation prediction system for photovoltaic or wind power includes:

[0067] a) A data collection and input module for receiving the predicted power values generated based on photovoltaic or wind power models, as well as the corresponding measured power and meteorological data;

[0068] b) An error analysis module for comparing the historical predicted power with the measured power and calculating the deviation index;

[0069] c) A deviation correction module for updating the deviation correction factor according to the prediction duration and the characteristics of photovoltaic or wind power generation;

[0070] d) A power prediction adjustment module for applying the deviation correction factor to subsequent power predictions;

[0071] e) A power generation calculation module for accumulating or integrating the corrected power prediction within a given time range to obtain the final power generation prediction value.

[0072] Example 3

[0073] This embodiment provides a computer device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of multiple servers) that can execute programs. The computer device of this embodiment at least includes, but is not limited to, a memory and a processor that can communicate with each other through a system bus.

[0074] In this embodiment, the memory (i.e., the readable storage medium) includes flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory may be an internal storage unit of the computer device, such as the hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the computer device. Of course, the memory may also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the memory is generally used to store the operating system and various application software installed on the computer device. In addition, the memory can also be used to temporarily store various data that have been output or will be output.

[0075] In some embodiments, the processor may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 22 is generally used to control the overall operation of the computer device. In this embodiment, the processor is used to run the program code stored in the memory or process data.

[0076] This embodiment also provides a computer-readable storage medium, such as flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, and when the program is executed by the processor, corresponding functions are implemented.

[0077] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the above specific embodiments, and for the combination embodiments of one or more of the above embodiments, those skilled in the art can make various changes, modifications or combinations within the scope of the claims, which does not affect the essence of the present invention. Without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A method for predicting power generation based on corrected power, characterized in that: The specific steps are as follows: S1. For the current system, predict the initial power within a given time interval; S2. Collect historical predicted power and actual power, and conduct comparison and systematic deviation analysis; S3. Determine at least one bias correction factor based on the analysis data in step S2; S4. Correcting the initial predicted power according to the deviation correction factor; S5. The power forecasted power generation amount corrected in step S4.

2. A method for predicting power generation based on corrected power according to claim 1, characterized in that: The step S1 includes step S11, and the step S11 is specifically as follows: S11. Deploy a sensor network at the photovoltaic system or wind power system site to collect meteorological parameters and electrical parameters in real time.

3. A method for predicting power generation based on corrected power according to claim 2, characterized in that: The step S1 includes step S12, and the step S12 is specifically as follows: S12. Input the collected real-time parameters into the LSTM model and obtain the initial predicted power generation within a given time interval.

4. The method for predicting power generation based on corrected power according to claim 1, characterized in that: The step S2 specifically involves performing statistical analysis within the selected time period to determine whether there is a deviation or a persistent deviation in the initial predicted power generation.

5. The method for predicting power generation based on corrected power according to claim 1, characterized in that: The deviation correction factor in step S3 is given for a specific time period and can only be applied to the correction of the initial predicted power in the corresponding time period.

6. A method for predicting power generation based on corrected power according to claim 1, characterized in that: The step S4 includes step S41, and the step S41 is specifically as follows: S41. Input the deviation correction factor into the LSTM model, and obtain the corrected power generation, and compare the corrected power generation with the real-time power generation to determine whether the prediction in the current time period is accurate.

7. The method for predicting power generation based on corrected power according to claim 1, characterized in that: The step S5 specifically includes calculating the power generation in the current time period according to the corrected power, and summing up the power generation prediction data in different time periods to obtain the power generation prediction value for one day.

8. A power generation prediction system, using a method for predicting power generation based on corrected power as claimed in any one of claims 1 to 7, characterized in that: include: A data acquisition and input module, which is used to receive the predicted power value generated by the LSTM model, as well as the corresponding measured power and meteorological data; An error analysis module, which is used to compare the historical predicted power with the measured power and calculate the deviation index; A deviation correction module, wherein the deviation correction module updates the deviation correction factor according to the prediction duration and photovoltaic or wind power generation characteristics; a power prediction adjustment module, the power prediction adjustment module applying the deviation correction factor to subsequent power predictions; The power generation calculation module accumulates or integrates the corrected power forecast within a given time range to obtain a final power generation forecast value.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images