Energy storage new energy station power smoothing method and device, electronic equipment and medium

Abstract

The embodiment of the invention relates to an energy storage new energy station power smoothing method and device, electronic equipment and a medium, and the method comprises the steps: obtaining real-time meteorological data of an environment where a target energy storage new energy station is located, and generating a predicted power curve in a future time period; obtaining a time sequence charge state of a target energy storage device, and adjusting the predicted power curve according to the time sequence charge state to generate a target predicted power curve; and smoothing the actual output power of the target energy storage new energy station by controlling the charging and discharging operation of the target energy storage equipment by taking the target predicted power curve as a reference. Therefore, the output power smoothness of the new energy station with high precision, low cost and long service life is realized by matching small-capacity energy storage with ultra-short-term prediction of SOC rolling correction.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of new energy power generation technology, and in particular to a power smoothing method, device, electronic equipment and medium for energy storage new energy power stations. Background Technology

[0002] The power output of new energy power plants (such as wind power and photovoltaic power) is highly dependent on meteorological conditions (such as wind speed, light intensity, temperature, etc.), and its volatility is significantly higher than that of traditional energy sources, which leads to multiple challenges for grid dispatch. First, traditional ultra-short-term forecasting models (15 minutes to 4 hours) suffer from insufficient accuracy, primarily due to their failure to adequately consider the real-time status of energy storage devices (such as State of Charge (SOC) and charging / discharging capacity). This leads to significant discrepancies between predicted and actual output values. Such discrepancies not only reduce the grid's ability to predict power fluctuations at renewable energy plants but may also trigger frequent adjustments to dispatch instructions, increasing grid operational risks. Second, existing energy storage mitigation technologies rely on large-capacity energy storage devices (such as lithium-ion battery packs), which have high design redundancy (typically configured at over 20% of the plant's daily power generation), resulting in high construction costs (e.g., a 50MW photovoltaic power plant with 12MWh of energy storage). Furthermore, the utilization rate of these energy storage systems is low, exhibiting capacity redundancy issues. Additionally, the coordination between fixed forecast values ​​and energy storage is poor. Traditional methods use static forecast values ​​to guide energy storage charging and discharging strategies, failing to dynamically adjust forecast values ​​based on real-time power deviations. This causes energy storage charging and discharging actions to lag behind actual demand, reducing system response efficiency. For example, when renewable energy plant power surges, fixed forecast values ​​cannot be adjusted in time, and the energy storage system may be unable to effectively mitigate fluctuations due to insufficient pre-charging, further exacerbating grid power imbalances. The aforementioned problems collectively result in high power smoothing costs and poor dispatch flexibility for renewable energy power plants, making it difficult to meet the power stability requirements of the power grid under the background of high proportion of renewable energy access.

[0003] The existing technology has the following drawbacks: 1. Insufficient efficiency of energy storage systems Redundancy Design and Cost Issues: Traditional energy storage systems (such as large-capacity lithium battery packs) generally employ redundant designs, with their capacity typically exceeding 20% ​​of the daily power generation of renewable energy plants (e.g., a 50MW photovoltaic power plant equipped with 12MWh of energy storage), resulting in high investment costs. However, this redundant design does not incorporate dynamic prediction to optimize power allocation, leading to a utilization rate of less than 30% for the energy storage system. This results in resource waste and the potential for frequent idling of energy storage devices during low-load periods, increasing operation and maintenance costs.

[0004] Peak-shaving strategies lack real-time response capabilities: Existing energy storage peak-shaving strategies (such as CN117650574A) rely on fixed thresholds and do not dynamically adjust charging and discharging strategies based on real-time power deviations. For example, in scenarios with sudden increases in wind power, fixed thresholds cannot trigger energy storage discharge in a timely manner, causing grid power fluctuations to exceed national standards. Furthermore, traditional strategies do not consider the energy storage SOC state, which may lead to forced discharge of batteries at low SOC levels, accelerating aging.

[0005] 2. Low power prediction accuracy The predictions are not dynamically corrected based on the energy storage status: Wind / PV power prediction models (such as CN119891255A) do not incorporate the energy storage's State of Charge (SOC) status for dynamic correction. For example, when the SOC is greater than 90%, traditional models still use fixed predictions, causing the energy storage to fail to charge in time and instead need to discharge to balance the power, further exacerbating the prediction error. Experiments show that the uncorrected predictions can deviate from the actual output by up to ±15%, while the error can be reduced to within ±5% after dynamic correction (refer to CN115659656A).

[0006] Insufficient error distribution modeling: Traditional prediction models (such as CN115659656A) assume that the error follows a normal distribution, but the actual wind / solar power error exhibits asymmetry. For example, in scenarios of sudden changes in sunlight, the prediction error may deviate from the mean by more than 20%, and traditional models do not use nonparametric kernel density estimation to quantify the error confidence interval, leading to frequent adjustments to dispatch instructions and increasing the risk of grid operation.

[0007] 3. Poor flexibility in control strategy Fixed power allocation strategies limit equipment lifespan: Existing strategies (such as CN117650574A) employ fixed power allocation, failing to dynamically adjust charging and discharging modes based on conditions such as SOC and temperature. For example, forcing discharge when SOC ≤ 10% may lead to deep battery discharge, shortening cycle life. Furthermore, fixed strategies do not differentiate between battery pack performance levels, resulting in some batteries being overloaded while others remain idle, reducing overall system efficiency.

[0008] The hierarchical control system lacks multi-dimensional constraints: Existing hierarchical control systems (such as CN119891255A) only allocate power based on State of Charge (SOC), without considering multi-dimensional constraints such as temperature and efficiency. For example, in low-temperature environments (<0℃), battery charging efficiency decreases by 30%, but existing strategies still allocate power according to nominal efficiency, resulting in actual output power lower than expected. Furthermore, group management does not consider State of Health (SOH), which may subject degraded batteries to excessive loads, accelerating performance degradation.

[0009] Therefore, it is necessary to study efficient and reliable optimization of ultra-short-term power prediction for new energy power plants that combines small-capacity energy storage devices with dynamic power prediction adjustment. Summary of the Invention

[0010] In view of this, in order to solve the above-mentioned technical problems or some of the technical problems, the present invention provides a power smoothing method, device, electronic device and medium for energy storage new energy power stations.

[0011] In a first aspect, embodiments of the present invention provide a power smoothing method for energy storage renewable energy power stations, comprising: Acquire real-time meteorological data of the environment where the target energy storage new energy power station is located, and generate a predicted power curve for the future time period; The time-series state of charge of the target energy storage device is obtained, and the predicted power curve is adjusted according to the time-series state of charge to generate the target predicted power curve. Based on the target predicted power curve, the actual output power of the target energy storage new energy power station is smoothed by controlling the charging and discharging operation of the target energy storage device.

[0012] In one possible implementation, the method further includes: The real-time meteorological data is converted into working meteorological values ​​for the power generation equipment in the target energy storage and new energy power station. The working meteorological values ​​are input into a pre-trained power prediction model, which outputs the predicted power for each minute in the future. A predicted power curve for the future time period is generated based on the predicted power for each minute in the future.

[0013] In one possible implementation, the method further includes: Obtain the state of charge at each moment in the time-series state of charge; When the state of charge is greater than or equal to a first preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding moment will be adjusted upward. When the state of charge is less than or equal to a second preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding time will be reduced. When the state of charge is greater than a second preset percentage of the remaining power of the target energy storage device and less than a first preset percentage of the remaining power of the target energy storage device, a correction coefficient is calculated using a linear function to adjust the predicted power at the corresponding time. The target predicted power curve is generated based on the adjusted predicted power.

[0014] In one possible implementation, the method further includes: When the actual output power is greater than the target predicted power at the corresponding moment in the target predicted power curve, the target energy storage device is controlled to charge. When the actual output power is less than the target predicted power at the corresponding moment in the target predicted power curve, the target energy storage device is controlled to discharge. When the difference between the actual output power and the target predicted power at the corresponding moment in the target predicted power curve is less than or equal to the third preset percentage of the target energy storage device, the target energy storage device is controlled to remain in standby mode.

[0015] In one possible implementation, the method further includes: The difference between the actual output power and the target predicted power is used as the charging power to control the charging of the target energy storage device; The difference between the target predicted power and the actual output power is used as the discharge power to control the discharge of the target energy storage device.

[0016] In one possible implementation, the method further includes: The charging and discharging operation adopts closed-loop control with a control cycle of 1 min to 5 min. After each control, the actual output power is updated in real time and used for the predicted power correction of the next control cycle.

[0017] In one possible implementation, the method further includes: The future time period is 15 min to 4 h, and the predicted power curve is updated every 15 min. The real-time meteorological data includes one or more of the following: wind speed, wind direction, horizontal irradiance, component temperature, and ambient temperature.

[0018] In a second aspect, embodiments of the present invention provide a power smoothing device for energy storage new energy power stations, comprising: The acquisition and generation module is used to acquire real-time meteorological data of the environment where the target energy storage new energy power station is located, and generate a predicted power curve for the future time period. The acquisition and generation module is further configured to acquire the time-series state of charge of the target energy storage device, and adjust the predicted power curve according to the time-series state of charge to generate the target predicted power curve. The smoothing module is used to smooth the actual output power of the target energy storage new energy power station by controlling the charging and discharging operation of the target energy storage device, based on the target predicted power curve. Thirdly, embodiments of the present invention provide a server, including a processor and a memory, wherein the processor is configured to execute a power smoothing program for energy storage and new energy power plants stored in the memory, so as to implement the power smoothing method for energy storage and new energy power plants described in the first aspect above.

[0019] Fourthly, embodiments of the present invention provide a storage medium, comprising: the storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the power smoothing method for energy storage new energy power stations described in the first aspect above.

[0020] This invention provides a method, apparatus, electronic device, and medium for smoothing the power output of a new energy storage power station. It generates a predicted power curve for a future time period by acquiring real-time meteorological data of the environment where the target energy storage power station is located; it acquires the time-series state of charge (SOC) of the target energy storage device and adjusts the predicted power curve based on the SOC to generate a target predicted power curve; and it smooths the actual output power of the target energy storage power station by controlling the charging and discharging operations of the target energy storage device, using the target predicted power curve as a reference. Compared to existing technologies that use large-capacity energy storage for static prediction, which suffers from inaccurate predictions, low energy storage utilization, delayed response, short lifespan, and high costs, this solution uses small-capacity energy storage combined with ultra-short-term prediction using SOC rolling correction to achieve high-precision, low-cost, and long-life output power smoothing for new energy power stations. Attached Figure Description

[0021] The accompanying drawings, which form part of this specification, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 The overall system architecture diagram of the power smoothing method for energy storage new energy power stations provided in the embodiments of the present invention; Figure 2 One of the flowcharts for the power smoothing method of energy storage new energy power stations provided in the embodiments of the present invention; Figure 3 The second flowchart illustrates the power smoothing method for energy storage new energy power stations provided in this embodiment of the invention. Figure 4 This is a curve of SOC-predicted value correction coefficient provided in an embodiment of the present invention; Figure 5 A power deviation-energy storage action logic flowchart provided for embodiments of the present invention; Figure 6 A schematic diagram of the structure of the power smoothing device for energy storage new energy power stations provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0023] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this invention is for describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0024] Figure 1 The overall system architecture diagram of the power smoothing method for energy storage new energy power stations provided in the embodiments of the present invention is as follows: Figure 1 As shown, the system is divided into three layers of information flow and power flow from left to right: The leftmost layer is the environmental sensing layer, which consists of meteorological data acquisition devices (wind speed, irradiance, and temperature sensors) and energy storage body monitoring units, which output real-time meteorological data and the current state of charge (SOC) of the energy storage.

[0025] The core algorithm layer is located in the middle, which includes the "ultra-short-term power prediction module" and the "SOC-linked prediction and correction module". The prediction module first generates the raw power curve for the next 15 minutes to 4 hours based on meteorological data; the correction module then dynamically raises or lowers the raw curve by ±5% to 15% according to the SOC level to form the final target predicted power curve.

[0026] On the right is the execution and grid connection layer. The real-time output power of the target new energy power station (photovoltaic array or wind turbine) and the target predicted power are simultaneously sent to the "smoothing control unit". This unit drives a small-capacity energy storage system (capacity is only 5% to 15% of the rated power of the power station) to perform charging and discharging compensation through the energy storage converter PCS. The compensated combined power is sent to the grid through the step-up transformer to achieve smooth output with a power fluctuation rate of <3% at the grid connection point.

[0027] The entire system architecture is based on the "prediction-correction-closed-loop control" line, forming a complete chain of meteorological data → prediction curve → SOC correction → energy storage compensation → smooth grid connection. In terms of hardware, only a small-capacity energy storage cabinet and a control host are added, which can continuously complete the output power smoothing task of the new energy power station within a 15-minute rolling refresh cycle.

[0028] Figure 2 This is one of the flowcharts illustrating the power smoothing method for energy storage new energy power stations provided in this embodiment of the invention, such as... Figure 2 As shown, the method specifically includes: S21. Obtain real-time meteorological data of the environment where the target energy storage new energy power station is located, and generate a predicted power curve for the future time period.

[0029] Real-time meteorological data is converted into working meteorological values ​​for the power generation equipment in the target energy storage new energy power station; the working meteorological values ​​are input into a pre-trained power prediction model, which outputs the predicted power for each minute in the future; and a predicted power curve for the future time period is generated based on the predicted power for each minute in the future.

[0030] S22. Obtain the time-series state of charge of the target energy storage device, and adjust the predicted power curve according to the time-series state of charge to generate the target predicted power curve.

[0031] like Figure 4 As shown, the state of charge (SOC) at each moment in the time-series SOC is obtained; when the SOC is greater than or equal to a first preset percentage (90%) of the remaining power of the target energy storage device, the predicted power at the corresponding moment is increased; when the SOC is less than or equal to a second preset percentage (10%) of the remaining power of the target energy storage device, the predicted power at the corresponding moment is decreased; when the SOC is greater than the second preset percentage of the remaining power of the target energy storage device and less than the first preset percentage of the remaining power of the target energy storage device, a correction coefficient is calculated using a linear function to adjust the predicted power at the corresponding moment; and a target predicted power curve is generated based on the adjusted predicted power.

[0032] S23. Based on the target predicted power curve, smooth the actual output power of the target energy storage new energy power station by controlling the charging and discharging operation of the target energy storage device.

[0033] like Figure 5 As shown, when the actual output power is greater than the target predicted power at the corresponding moment in the target predicted power curve, the target energy storage device is controlled to charge; the difference between the actual output power and the target predicted power is used as the charging power to control the charging of the target energy storage device.

[0034] When the actual output power is less than the target predicted power at the corresponding moment in the target predicted power curve, the target energy storage device is controlled to discharge; the difference between the target predicted power and the actual output power is used as the discharge power to control the discharge of the target energy storage device.

[0035] When the difference between the actual output power and the target predicted power at the corresponding moment in the target predicted power curve is less than or equal to the third preset percentage of the target energy storage device, the target energy storage device is controlled to remain in standby mode.

[0036] This invention provides a method for smoothing the power output of a new energy storage power station. The method involves acquiring real-time meteorological data of the target energy storage power station's environment to generate a predicted power curve for a future time period; acquiring the time-series state of charge (SOC) of the target energy storage device and adjusting the predicted power curve based on the SOC to generate a target predicted power curve; and using the target predicted power curve as a benchmark, smoothing the actual output power of the target energy storage power station by controlling the charging and discharging operations of the target energy storage device. Compared to existing technologies that use large-capacity energy storage for static prediction, which suffers from inaccurate predictions, low energy storage utilization, delayed response, short lifespan, and high costs, this method uses small-capacity energy storage combined with SOC rolling correction for ultra-short-term prediction, achieving high-precision, low-cost, and long-life output power smoothing for new energy power stations.

[0037] Figure 3 This is the second flowchart illustrating the power smoothing method for energy storage new energy power stations provided in this embodiment of the invention, as shown below. Figure 3 As shown, the method specifically includes: S31. Convert the real-time meteorological data into the working meteorological values ​​of the power generation equipment in the target energy storage new energy station.

[0038] First, the real-time meteorological data is quality checked and anomalies are removed. Then, wind speed, irradiance, temperature, etc., are converted into values ​​that are closest to the height of the solar panels and wind turbine hubs. Next, these converted meteorological values ​​are cut into several small segments in chronological order. Each segment, along with historical data from the same period and the power plant's operating status, is fed into a pre-trained machine learning model. The model has learned the mapping relationship between meteorology and power, and it outputs the expected power for each minute in the future segment. These minute-level power values ​​are connected into a smooth line, and then a trend filter is applied to remove spikes, resulting in a predicted power curve that extends from the current moment to the next fifteen minutes to four hours, updated every fifteen minutes.

[0039] Specifically, the data sources include, but are not limited to, raw signals (10 m wind speed, horizontal irradiance, ambient temperature) from sources such as wind measurement towers, ground weather stations, and temperature sensors on the back of the components. The "sensor height" data is then converted into values ​​that are actually perceived by the power generation equipment.

[0040] Furthermore, the wind speed of 10 m can be extrapolated to the height of the wind turbine hub (e.g., 80 m, 100 m) using the wind shear power law or logarithmic law; if the terrain is complex, turbulence intensity correction can be introduced.

[0041] The horizontal irradiance is decomposed into total irradiance (including direct, scattered, and reflected components) on the tilt surface of the module; at the same time, the actual operating temperature of the solar cell is calculated using the "irradiance-backsheet temperature model" to replace the ambient temperature.

[0042] Output a set of time series of "working meteorological values" that are "at the same height, tilt angle, and temperature" as the power generation equipment, with a sampling interval of ≤5 min, as input features for subsequent models.

[0043] S32. Input the working meteorological values ​​into the pre-trained power prediction model and output the predicted power for each minute in the future.

[0044] Train the power prediction model in advance using historical weather data and corresponding power data. The model type can be gradient boosting tree, lightweight time series network (LSTM / TCN), or physical-data hybrid model.

[0045] Input the "working weather value" and the power performance of the same period in the past 1–4 hours, and the model will output the predicted power of one point every 1 minute in the next 15 min–4 hours.

[0046] Optionally, the process can be repeated every 15 minutes to generate a high-resolution "raw predicted power sequence".

[0047] S33. Generate a predicted power curve for the future time period based on the predicted power for each future minute.

[0048] Low-pass filtering or moving average is applied to the minute-level sequence to eliminate high-frequency glitches, resulting in a smooth original predicted power curve. The time granularity can be maintained at 1 min or downsampled to 5 min; the curve length covers 15 min–4 h, shifting backward as the prediction progresses every 15 min.

[0049] S34. Obtain the state of charge at each moment in the time-series state of charge.

[0050] The state of charge (SOC) of individual cells provided by the energy storage battery management system represents the overall SOC of the entire site using either the average or minimum value. The SOC sequence is interpolated to the same timeline as the original predicted power sequence to ensure that both the predicted power value and the SOC value exist at the same time. The update frequency is synchronized with the power prediction, and the current SOC is reread every 15 minutes as the starting point for correction.

[0051] S35. Adjust the predicted power curve according to the time-series state of charge to generate the target predicted power curve.

[0052] Adjustment logic: SOC≥80% → Increase Praw(t) by 5%–15% to prevent overcharging from continued charging; SOC≤20% → Reduce Praw(t) by 5%–15% to prevent over-discharge caused by continued discharge; 20% < SOC < 80% → The linear coefficient k = 0.95 + 0.2×(SOC – 20) / 60, P'(t) = k·Praw(t).

[0053] The entire curve can be multiplied by the same coefficient. There is no need to use different coefficients for each point, ensuring that the shape remains unchanged and only the amplitude drifts.

[0054] Output the "target predicted power curve P'(t)" corrected by SOC.

[0055] Specifically, when the battery charge is already very high (SOC ≥ 80%), if the energy storage operation is still arranged according to the original predicted value, the battery is very likely to be continuously fully charged, resulting in the risk of overcharging. Therefore, the entire prediction curve of "how much electricity should be generated next" is artificially raised by 5% to 15%, making the system think that "more electricity will be used later", so as to reduce charging in advance or actively discharge, creating space for the battery and preventing overcharging.

[0056] On the contrary, when the battery charge is very low (SOC ≤ 20%), if it still operates according to the original predicted value, the battery may be forced to continue discharging until it runs out. Therefore, the predicted value is reduced by 5% to 15% as a whole, making the system think that "less electricity will be generated later", so as to reduce discharging in advance or actively charge, avoiding draining the battery and preventing over-discharge.

[0057] S36. Based on the target predicted power curve, smooth the actual output power of the target energy storage new energy power station by controlling the charge and discharge operations of the target energy storage device.

[0058] Control period: 1 - 5 min (shorter than the prediction update period of 15 min), continuously compare the measured power Pactual(t) at the grid connection point with P'(t).

[0059] The power difference ΔP(t) = Pactual(t) – P'(t): ΔP > 0 → Energy storage charges, and the charging power = ΔP, limited within the rated power of the energy storage converter; ΔP < 0 → Energy storage discharges, and the discharging power = |ΔP|; |ΔP| ≤ 1% Prated → Standby, avoiding frequent micro charge and discharge.

[0060] After each control, refresh the SOC according to the change in the battery charge, and use it as the initial value for the next round of prediction correction, forming a rolling closed loop of "prediction - correction - control - re - refresh".

[0061] Smoothing effect: Power fluctuation rate at grid connection point is <3%, meeting national standards; the number of energy storage cycles is reduced by about 41% compared to the traditional fixed threshold strategy, and the lifespan is extended.

[0062] This invention provides a power smoothing method for energy storage renewable energy power plants. The method involves acquiring real-time meteorological data of the environment where the target energy storage renewable energy power plant is located to generate a predicted power curve for a future time period; acquiring the time-series state of charge (SOC) of the target energy storage device and adjusting the predicted power curve based on the SOC to generate a target predicted power curve; and smoothing the actual output power of the target energy storage renewable energy power plant by controlling the charging and discharging operations of the target energy storage device, using the target predicted power curve as a benchmark. This method achieves significant cost reduction by using small-capacity energy storage combined with ultra-short-term prediction through SOC rolling correction: the energy storage capacity is only 1 / 5 of the traditional solution, reducing investment costs by more than 60%; improved prediction accuracy: the matching degree between predicted values ​​and actual power increases from 78% to over 92%, optimizing grid dispatch efficiency; extended energy storage lifespan: overcharging / over-discharging is avoided through dynamic SOC correction, reducing cycle times by 41% and extending equipment lifespan to over 10 years; and enhanced adaptability: the closed-loop control strategy can cope with sudden changes in wind speed.

[0063] Figure 6 A schematic diagram of the structure of the energy storage power smoothing device for new energy power stations provided in this embodiment of the invention, specifically including: The acquisition and generation module 601 is used to acquire real-time meteorological data of the environment where the target energy storage new energy power station is located, and generate a predicted power curve for a future time period. The acquisition and generation module 601 is further configured to acquire the time-series state of charge of the target energy storage device, and adjust the predicted power curve according to the time-series state of charge to generate the target predicted power curve. The smoothing module 602 is used to smooth the actual output power of the target energy storage new energy power station by controlling the charging and discharging operation of the target energy storage device, based on the target predicted power curve.

[0064] In one possible implementation, the acquisition and generation module 601 is further configured to convert the real-time meteorological data into working meteorological values ​​for the power generation equipment in the target energy storage new energy power station; input the working meteorological values ​​into a pre-trained power prediction model, and output the predicted power for each minute in the future; and generate a predicted power curve for the future time period based on the predicted power for each minute in the future.

[0065] In one possible implementation, the acquisition and generation module 601 is further configured to acquire the state of charge (SOC) at each moment in the time-series SOC; when the SOC is greater than or equal to a first preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding moment is increased; when the SOC is less than or equal to a second preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding moment is decreased; when the SOC is greater than the second preset percentage of the remaining power of the target energy storage device and less than the first preset percentage of the remaining power of the target energy storage device, a correction coefficient is calculated using a linear function to adjust the predicted power at the corresponding moment; and a target predicted power curve is generated based on the adjusted predicted power.

[0066] In one possible implementation, the smoothing module 602 is further configured to: control the target energy storage device to charge when the actual output power is greater than the target predicted power at the corresponding time in the target predicted power curve; control the target energy storage device to discharge when the actual output power is less than the target predicted power at the corresponding time in the target predicted power curve; and control the target energy storage device to remain in standby mode when the difference between the actual output power and the target predicted power at the corresponding time in the target predicted power curve is less than or equal to a third preset percentage of the target energy storage device.

[0067] In one possible implementation, the smoothing module 602 is further configured to use the difference between the actual output power and the target predicted power as the charging power to control the charging of the target energy storage device; and to use the difference between the target predicted power and the actual output power as the discharging power to control the discharging of the target energy storage device.

[0068] The energy storage power smoothing device for new energy power stations provided in this embodiment can be as follows: Figure 6 The power smoothing device for energy storage and new energy power plants shown can perform the following functions: Figure 2-3 All steps of the power smoothing method for new energy power plants in China's energy storage system, thereby achieving... Figure 2-3 For details on the technical effects of the power smoothing method for energy storage and new energy power plants shown, please refer to [link / reference needed]. Figure 2-3 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0069] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 7The illustrated electronic device 700 includes at least one processor 701, a memory 702, at least one network interface 704, and other user interfaces 703. The various components in the electronic device 700 are coupled together via a bus system 705. It is understood that the bus system 705 is used to implement communication between these components. In addition to a data bus, the bus system 705 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 7 The general labeled all buses as Bus System 705.

[0070] The user interface 703 may include a display, keyboard, or clicking device (e.g., mouse, trackball, touchpad, or touchscreen).

[0071] It is understood that the memory 702 in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 702 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0072] In some implementations, memory 702 stores elements, executable units or data structures, or subsets thereof, or extended sets thereof: operating system 7021 and application program 7022.

[0073] The operating system 7021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 7022 includes various applications, such as a media player and a browser, used to implement various application functions. The program implementing the method of this embodiment can be included in the application program 7022.

[0074] In this embodiment of the invention, by calling the program or instructions stored in the memory 702, specifically the program or instructions stored in the application program 7022, the processor 701 executes the method steps provided in each method embodiment, including, for example: Real-time meteorological data of the environment where the target energy storage new energy power station is located is acquired to generate a predicted power curve for a future time period; the time-series state of charge of the target energy storage device is acquired, and the predicted power curve is adjusted according to the time-series state of charge to generate a target predicted power curve; the actual output power of the target energy storage new energy power station is smoothed by controlling the charging and discharging operation of the target energy storage device based on the target predicted power curve.

[0075] In one possible implementation, the real-time meteorological data is converted into operating meteorological values ​​for the power generation equipment in the target energy storage new energy power station; the operating meteorological values ​​are input into a pre-trained power prediction model, which outputs the predicted power for each minute in the future; and a predicted power curve for the future time period is generated based on the predicted power for each minute in the future.

[0076] In one possible implementation, the state of charge (SOC) at each moment in the time-series SOC is obtained; when the SOC is greater than or equal to a first preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding moment is increased; when the SOC is less than or equal to a second preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding moment is decreased; when the SOC is greater than the second preset percentage of the remaining power of the target energy storage device and less than the first preset percentage of the remaining power of the target energy storage device, a correction coefficient is calculated using a linear function to adjust the predicted power at the corresponding moment; and a target predicted power curve is generated based on the adjusted predicted power.

[0077] In one possible implementation, when the actual output power is greater than the target predicted power at the corresponding time in the target predicted power curve, the target energy storage device is controlled to charge; when the actual output power is less than the target predicted power at the corresponding time in the target predicted power curve, the target energy storage device is controlled to discharge; when the difference between the actual output power and the target predicted power at the corresponding time in the target predicted power curve is less than or equal to a third preset percentage of the target energy storage device, the target energy storage device is controlled to remain in standby mode.

[0078] In one possible implementation, the difference between the actual output power and the target predicted power is used as the charging power to control the charging of the target energy storage device; the difference between the target predicted power and the actual output power is used as the discharging power to control the discharging of the target energy storage device.

[0079] In one possible implementation, the charging and discharging operation employs closed-loop control with a control cycle of 1 min to 5 min, and the actual output power is updated in real time after each control operation and used for the predicted power correction in the next control cycle.

[0080] In one possible implementation, the future time period is 15 min to 4 h, and the predicted power curve is updated every 15 min; the real-time meteorological data includes one or more of wind speed, wind direction, horizontal irradiance, component temperature, and ambient temperature.

[0081] The methods disclosed in the above embodiments of the present invention can be applied to processor 701, or implemented by processor 701. Processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 701 or by instructions in the form of software. The processor 701 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software units in the decoding processor. The software units may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 702. Processor 701 reads the information in memory 702 and, in conjunction with its hardware, completes the steps of the above method.

[0082] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0083] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0084] The electronic device provided in this embodiment may be as follows: Figure 7 The electronic device shown can perform the following: Figure 1-2 All steps of the power smoothing method for new energy power plants in China's energy storage system, thereby achieving... Figure 2-3 For details on the technical effects of the power smoothing method for energy storage and new energy power plants shown, please refer to [link / reference needed]. Figure 1-2 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0085] This invention also provides a storage medium (computer-readable storage medium). This storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; it may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; and it may also include combinations of the above types of memory.

[0086] One or more programs in the storage medium can be executed by one or more processors to implement the above-mentioned power smoothing method for energy storage new energy power stations executed on the electronic device side.

[0087] The processor is used to execute the power smoothing program for energy storage renewable energy power plants stored in the memory, so as to implement the following steps of the power smoothing method for energy storage renewable energy power plants executed on the electronic device side: Real-time meteorological data of the environment where the target energy storage new energy power station is located is acquired to generate a predicted power curve for a future time period; the time-series state of charge of the target energy storage device is acquired, and the predicted power curve is adjusted according to the time-series state of charge to generate a target predicted power curve; the actual output power of the target energy storage new energy power station is smoothed by controlling the charging and discharging operation of the target energy storage device based on the target predicted power curve.

[0088] In one possible implementation, the real-time meteorological data is converted into operating meteorological values ​​for the power generation equipment in the target energy storage new energy power station; the operating meteorological values ​​are input into a pre-trained power prediction model, which outputs the predicted power for each minute in the future; and a predicted power curve for the future time period is generated based on the predicted power for each minute in the future.

[0089] In one possible implementation, the state of charge (SOC) at each moment in the time-series SOC is obtained; when the SOC is greater than or equal to a first preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding moment is increased; when the SOC is less than or equal to a second preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding moment is decreased; when the SOC is greater than the second preset percentage of the remaining power of the target energy storage device and less than the first preset percentage of the remaining power of the target energy storage device, a correction coefficient is calculated using a linear function to adjust the predicted power at the corresponding moment; and a target predicted power curve is generated based on the adjusted predicted power.

[0090] In one possible implementation, when the actual output power is greater than the target predicted power at the corresponding time in the target predicted power curve, the target energy storage device is controlled to charge; when the actual output power is less than the target predicted power at the corresponding time in the target predicted power curve, the target energy storage device is controlled to discharge; when the difference between the actual output power and the target predicted power at the corresponding time in the target predicted power curve is less than or equal to a third preset percentage of the target energy storage device, the target energy storage device is controlled to remain in standby mode.

[0091] In one possible implementation, the difference between the actual output power and the target predicted power is used as the charging power to control the charging of the target energy storage device; the difference between the target predicted power and the actual output power is used as the discharging power to control the discharging of the target energy storage device.

[0092] In one possible implementation, the charging and discharging operation employs closed-loop control with a control cycle of 1 min to 5 min, and the actual output power is updated in real time after each control operation and used for the predicted power correction in the next control cycle.

[0093] In one possible implementation, the future time period is 15 min to 4 h, and the predicted power curve is updated every 15 min; the real-time meteorological data includes one or more of wind speed, wind direction, horizontal irradiance, component temperature, and ambient temperature.

[0094] As is known from common technical knowledge, this invention can be implemented through other embodiments that do not depart from its spirit or essential characteristics. Therefore, the disclosed embodiments described above are merely illustrative in all respects and are not the only ones. All modifications within the scope of this invention or its equivalents are included in this invention.

[0095] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0097] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0098] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A power smoothing method for energy storage renewable energy power stations, characterized in that, include: Acquire real-time meteorological data of the environment where the target energy storage new energy power station is located, and generate a predicted power curve for the future time period; The time-series state of charge of the target energy storage device is obtained, and the predicted power curve is adjusted according to the time-series state of charge to generate the target predicted power curve. Based on the target predicted power curve, the actual output power of the target energy storage new energy power station is smoothed by controlling the charging and discharging operation of the target energy storage device.

2. The method according to claim 1, characterized in that, The process of acquiring real-time meteorological data of the environment where the target energy storage new energy power station is located and generating a predicted power curve for a future time period includes: The real-time meteorological data is converted into working meteorological values ​​for the power generation equipment in the target energy storage and new energy power station. The working meteorological values ​​are input into a pre-trained power prediction model, which outputs the predicted power for each minute in the future. A predicted power curve for the future time period is generated based on the predicted power for each minute in the future.

3. The method according to claim 1 or 2, characterized in that, The step of acquiring the time-series state of charge of the target energy storage device and adjusting the predicted power curve based on the time-series state of charge to generate the target predicted power curve includes: Obtain the state of charge at each moment in the time-series state of charge; When the state of charge is greater than or equal to a first preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding moment will be adjusted upward. When the state of charge is less than or equal to a second preset percentage of the remaining power of the target energy storage device, the predicted power at the corresponding time will be reduced. When the state of charge is greater than a second preset percentage of the remaining power of the target energy storage device and less than a first preset percentage of the remaining power of the target energy storage device, a correction coefficient is calculated using a linear function to adjust the predicted power at the corresponding time. The target predicted power curve is generated based on the adjusted predicted power.

4. The method according to claim 3, characterized in that, The step of smoothing the actual output power of the target energy storage renewable energy power station by controlling the charging and discharging operation of the target energy storage device, based on the target predicted power curve, includes: When the actual output power is greater than the target predicted power at the corresponding moment in the target predicted power curve, the target energy storage device is controlled to charge. When the actual output power is less than the target predicted power at the corresponding moment in the target predicted power curve, the target energy storage device is controlled to discharge. When the difference between the actual output power and the target predicted power at the corresponding moment in the target predicted power curve is less than or equal to the third preset percentage of the target energy storage device, the target energy storage device is controlled to remain in standby mode.

5. The method according to claim 4, characterized in that, The method further includes: The difference between the actual output power and the target predicted power is used as the charging power to control the charging of the target energy storage device; The difference between the target predicted power and the actual output power is used as the discharge power to control the discharge of the target energy storage device.

6. The method according to claim 1, characterized in that, The charging and discharging operation adopts closed-loop control with a control cycle of 1 min to 5 min. After each control, the actual output power is updated in real time and used for the predicted power correction of the next control cycle.

7. The method according to claim 1, characterized in that, The future time period is 15 min to 4 h, and the predicted power curve is updated every 15 min. The real-time meteorological data includes one or more of the following: wind speed, wind direction, horizontal irradiance, component temperature, and ambient temperature.

8. A power smoothing device for energy storage new energy power stations, characterized in that, include: The acquisition and generation module is used to acquire real-time meteorological data of the environment where the target energy storage new energy power station is located, and generate a predicted power curve for the future time period. The acquisition and generation module is further configured to acquire the time-series state of charge of the target energy storage device, and adjust the predicted power curve according to the time-series state of charge to generate the target predicted power curve. The smoothing module is used to smooth the actual output power of the target energy storage new energy power station by controlling the charging and discharging operation of the target energy storage device, based on the target predicted power curve.

9. A computer device, characterized in that, include: A processor and a memory, the processor being configured to execute a monitoring program for services stored in the memory to implement the power smoothing method for energy storage new energy power stations as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the power smoothing method for energy storage new energy power stations as described in any one of claims 1 to 7.

Images