Photovoltaic station energy storage equipment scheduling method, device, equipment and medium

Abstract

The invention relates to new energy, and discloses a photovoltaic station energy storage equipment scheduling method and device, equipment and a medium, and the photovoltaic station energy storage equipment scheduling method comprises the steps: obtaining a day-ahead power generation plan of a target photovoltaic station, a first historical load of a power grid side, and a historical scheduling plan; performing load prediction based on the time sequence change characteristics of the first historical load to obtain predicted load data of a first time scale; when the day-ahead power generation plan is not matched with the predicted load data, determining a first charging event based on the day-ahead power generation plan and the predicted load data; correcting the first charging event based on at least one historical charging event to obtain a day-ahead scheduling plan; and scheduling the energy storage equipment based on the day-ahead scheduling plan. According to the method, the influence of the inherent intermittency, volatility and randomness of photovoltaic power generation or the uncertainty of the user load can be considered, and the day-ahead scheduling plan of the energy storage equipment can be more accurately formulated.

Description

Technical Field

[0001] The present invention relates to the field of new energy technologies, and in particular to a method, device, equipment and medium for scheduling energy storage equipment in a photovoltaic station. Background Art

[0002] Affected by the inherent intermittent, volatile and random nature of photovoltaic power generation, as well as the uncertainty of photovoltaic output, user load and electricity price, photovoltaic power generation is not as stable and controllable as traditional thermal power generation, resulting in high abandonment rate and low economic benefits. In addition, after photovoltaic power generation is connected to the grid, the active loss cost and voltage deviation cost of the power generation network are too large. Therefore, additional equipment is needed to maintain the stability of its power generation. Energy storage can flexibly and stably dispatch power supply and power consumption, and can achieve stable and controllable balanced dispatch control.

[0003] In the related art, the scheduling method for energy storage equipment is usually determined by the photovoltaic power generation power, the load on the grid side and the current energy storage capacity of the energy storage equipment; when the photovoltaic power generation power is greater than the load on the grid side and the energy storage capacity of the energy storage equipment is sufficient, the energy storage equipment is usually used to store redundant electric energy; when the photovoltaic power generation power is less than the load on the grid side and the energy storage equipment has stored electric energy, the energy storage equipment is usually used to release the stored electric energy to meet the load demand on the grid side; further, the scheduling plan of the energy storage equipment can be determined according to the photovoltaic power generation plan, the predicted user load and the charge range of the energy storage equipment.

[0004] However, photovoltaic power generation is affected by weather, power generation plans, etc., and the power generation capacity is extremely unstable. In addition, the load on the user side is also affected by weather, seasons, etc. and is also changing. As a result, there is a technical problem of inaccurate scheduling when determining the scheduling plan of energy storage equipment based on photovoltaic power generation plans, predicted user loads and the charge range of energy storage equipment. Summary of the invention

[0005] In view of this, the present invention provides a method, apparatus, device and medium for scheduling energy storage equipment in a photovoltaic station to solve the technical problem of inaccurate scheduling in the scheduling plan of the energy storage equipment.

[0006] In a first aspect, the present invention provides a method for scheduling energy storage equipment in a photovoltaic station, the method comprising: obtaining a day-ahead power generation plan of a target photovoltaic station, a first historical load on a power grid side, and a historical scheduling plan; performing load forecasting based on a time series variation characteristic of the first historical load to obtain forecast load data of a first time scale; when the day-ahead power generation plan does not match the forecast load data, determining a first power generation and charging event based on the day-ahead power generation plan and the forecast load data; correcting the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan; and scheduling the energy storage device based on the day-ahead scheduling plan.

[0007] As an exemplary embodiment, the method of correcting the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan includes: obtaining a historical scheduling plan of the target station containing historical power generation and charging events and a second historical load corresponding to the timing of the historical scheduling plan; clustering the historical scheduling plan and the second historical load based on the first timing change characteristics of the day-ahead power generation plan and the second timing change characteristics of the first historical load, respectively, to obtain a clustering result; based on the clustering result, selecting historical power generation and charging events in the historical scheduling plan with a clustering degree greater than a preset degree; and correcting the first power generation and charging event based on the timestamp of the historical power generation and charging event to obtain the day-ahead scheduling plan.

[0008] As an exemplary embodiment, the method of correcting the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan also includes: inputting the day-ahead power generation plan and the predicted load data into a pre-trained day-ahead scheduling plan correction model, extracting a first time series change trend of the day-ahead power generation plan and a second time series change trend of the predicted load data based on the day-ahead scheduling plan correction model, and determining the first power generation and charging event according to the first time series change trend and the second time series change trend; the day-ahead scheduling plan correction model is trained according to the time series corresponding historical photovoltaic power generation power, the first historical load, the historical power prediction data and the historical day-ahead power generation plan, and during the model training process, the historical power generation and charging event is determined based on the historical photovoltaic power generation power and the first historical load; the model is trained with the historical day-ahead power generation plan and the historical power prediction data as input features and the historical power generation and charging events as labels.

[0009] As an exemplary embodiment, after the first power generation and charging event is corrected based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan, the photovoltaic station energy storage equipment scheduling method also includes: obtaining the historical photovoltaic power generation power of the target photovoltaic station; performing power forecasting based on the time series variation characteristics of the historical photovoltaic power generation power to obtain intraday forecasted power data at a second time scale; wherein the second time scale is smaller than the first time scale; obtaining a second power generation and charging event at a second time scale based on the intraday forecasted power data and the forecasted load data; and correcting the day-ahead scheduling plan at a second time scale based on the second power generation and charging event.

[0010] As an exemplary embodiment, the photovoltaic station energy storage equipment scheduling method also includes: obtaining a historical second charging event at a second time scale of the target photovoltaic station; extracting the historical photovoltaic power generation power, the first historical load and the predicted load data with the second charging event as the central time node and the second time scale as a preset duration to obtain sub-historical photovoltaic power generation power, sub-first historical load data and first predicted load data; clustering the sub-historical photovoltaic power generation power and sub-historical load data based on the intraday predicted power data and the first predicted load data to obtain a clustering result; based on the clustering result, selecting the historical second charging event with a clustering degree greater than a preset degree; and revising the day-ahead scheduling plan based on the historical second charging event.

[0011] As an exemplary embodiment, after the first power generation and charging event is corrected based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan, the photovoltaic station energy storage equipment scheduling method also includes: acquiring the real-time photovoltaic power generation power of the target photovoltaic station and the real-time load data on the grid side; determining a third power generation and charging event based on the real-time photovoltaic power generation power and the real-time load data; and correcting the day-ahead scheduling plan based on the third power generation and charging event.

[0012] As an exemplary embodiment, the energy storage device includes a plurality of sub-energy storage devices with different energy storage durations and energy storage capacities, and the scheduling of the energy storage device based on the day-ahead scheduling plan includes: obtaining a rated energy storage duration and a rated energy storage capacity of each of the sub-energy storage devices; matching each of the rated energy storage durations and the rated energy storage capacity based on the generation and charging power values ​​and generation and charging power fluctuation values ​​of each of the first generation and charging events included in the day-ahead scheduling plan to obtain a matching result; and determining a day-ahead scheduling plan for the energy storage device corresponding to each of the generation and charging events based on the matching result and the timestamp of each of the first generation and charging events.

[0013] In a second aspect, the present invention provides a photovoltaic station energy storage equipment scheduling device, which includes: an acquisition module, used to acquire the day-ahead power generation plan of the target photovoltaic station, the first historical load on the grid side and the historical scheduling plan; a load prediction module, used to perform load prediction based on the time series variation characteristics of the first historical load to obtain predicted load data of a first time scale; a first power generation and charging event determination module, used to determine the first power generation and charging event based on the day-ahead power generation plan and the predicted load data when the day-ahead power generation plan does not match the predicted load data; a day-ahead scheduling plan determination module, used to correct the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan; an energy storage equipment scheduling module, used to schedule the energy storage equipment based on the day-ahead scheduling plan.

[0014] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the photovoltaic station energy storage equipment scheduling method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the photovoltaic station energy storage equipment scheduling method of the first aspect or any corresponding embodiment thereof.

[0016] The present invention provides a photovoltaic station energy storage equipment scheduling method, which includes: obtaining a day-ahead power generation plan of a target photovoltaic station, a first historical load on a power grid side, and a historical scheduling plan; performing load forecasting based on the time series variation characteristics of the first historical load to obtain forecast load data of a first time scale; when the day-ahead power generation plan does not match the forecast load data, determining a first power generation and charging event based on the day-ahead power generation plan and the forecast load data; correcting the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan; scheduling the energy storage device based on the day-ahead scheduling plan; being able to consider the intermittent, volatility, and randomness inherent in photovoltaic power generation or the influence of uncertainty in user load, and being able to more accurately formulate a day-ahead scheduling plan for energy storage equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 is a flow chart of a photovoltaic station energy storage device scheduling method according to an embodiment of the present invention;

[0019] Figure 2 is a structural block diagram of a photovoltaic station energy storage device scheduling device according to an embodiment of the present invention;

[0020] Figure 3 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] According to an embodiment of the present invention, an embodiment of a method for scheduling energy storage equipment in a photovoltaic station is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0023] In this embodiment, a method for scheduling energy storage equipment in a photovoltaic station is provided. Figure 1 is a flow chart of a photovoltaic station energy storage device scheduling method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0024] Step S101, obtaining the day-ahead power generation plan of the target photovoltaic station, the first historical load on the grid side, and the historical dispatch plan.

[0025] A photovoltaic station generally has a predetermined power generation plan requirement, under which the photovoltaic station should output the corresponding planned power generation power on an expected date.

[0026] For example, the time scale of the day-ahead power generation plan is 24 hours, which is used to represent the photovoltaic power generation power that the target photovoltaic station should output at each time point in the next 24 hours.

[0027] Exemplarily, the first historical load is the load data of the load end supplied by the target photovoltaic station, and its time scale is the same as the time scale of the day-ahead power generation plan, which is 24 hours; the first historical load can be obtained by collecting historical data of the target photovoltaic station; in one embodiment, the first historical load can be used for load forecasting to obtain predicted load data of the target photovoltaic station within the next 24 hours corresponding to the timestamp of the day-ahead power generation plan.

[0028] Among them, the historical dispatch plan is obtained by the target photovoltaic station in accordance with the historical power generation plan and the historical load data on the grid side within the historical time period.

[0029] Step S102: performing load forecasting based on the time series variation characteristics of the first historical load to obtain forecast load data of a first time scale.

[0030] After obtaining the first historical load, in order to determine the load condition of the target photovoltaic station in the next 24 hours, load prediction is performed based on the time series variation characteristics of the historical load data to obtain predicted load data of the first time scale.

[0031] As a possible implementation method, a pre-trained load data prediction model can be used to realize load prediction based on the time series variation characteristics of historical load data; specifically, the historical load data of the target photovoltaic station is obtained, and the historical load data is intercepted based on a 24-hour time scale to obtain multiple 24-hour first historical loads as a data set; further, the first historical load is used as input data, and the load data 24 hours after the first historical load is used as a label, and the first historical load is input into a pre-built first preset model for model training until the model converges.

[0032] Step S103: when the day-ahead power generation plan does not match the predicted load data, determining a first charging event based on the day-ahead power generation plan and the predicted load data.

[0033] When photovoltaic power generation is connected to the power grid, the stability of its power generation is usually maintained through energy storage equipment; in this embodiment, the degree of matching between the day-ahead power generation plan and the predicted load data determines whether the energy storage equipment needs to be scheduled so that it can meet the needs of the power grid side.

[0034] Specifically, when the day-ahead power generation plan does not match the predicted load data, the power generated by the photovoltaic station cannot meet the load demand of the load end. There are situations where the power generation power of the photovoltaic station is too high and the load end cannot absorb it, and the power generation power of the photovoltaic station is too low and cannot meet the supply demand of the load end. At this time, it is necessary to schedule the energy storage device to charge to absorb the redundant electric energy of the photovoltaic station or to schedule the energy storage device to discharge to supply electric energy to the load end. In the present invention, scheduling the energy storage device to charge and scheduling the energy storage device to discharge are recorded as the first charging event.

[0035] It should be understood that since the time scale of the day-ahead power generation plan and the predicted load data is 24 hours, multiple first generation and charging events within the planned 24 hours can be determined based on the day-ahead power generation plan and the predicted load data.

[0036] In one embodiment, a power difference between the day-ahead power generation plan and the first historical load is calculated, and a plurality of first power generation and charging events are determined based on the non-zero power difference and the duration.

[0037] Specifically, when the power difference is not zero, the moment when the power difference is not zero is recorded as the start time of the first charging event until the power difference is zero; when the power difference is zero, the moment when the power difference is zero is recorded as the end time of the first charging event, and the start time of the first charging event to the end time of the first charging event is recorded as one first charging event, the sum of the power difference values ​​from the start time of the first charging event to the end time of the first charging event is recorded as the charging power value, and the power difference is recorded as the charging power fluctuation value

[0038] Step S104: modifying the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan.

[0039] When determining the first power generation and charging event based on the day-ahead power generation plan and the predicted load data, due to the inherent intermittent, volatile and random nature of photovoltaic power generation, as well as the uncertainty of photovoltaic output and user load, and the error in power prediction using the first historical load, there is a technical problem of inaccuracy in determining the first power generation and charging event. Therefore, it is necessary to correct the first power generation and charging event based on at least one historical power generation and charging event in the historical scheduling plan.

[0040] In one embodiment, in order to take into account the impact of the inherent intermittent, volatile and random characteristics of photovoltaic power generation, the first power generation and charging event can be corrected according to at least one historical power generation and charging event in the historical scheduling plan that matches the day-ahead power generation plan; specifically, for multiple historical scheduling plans containing historical power generation and charging events, the historical power generation plans corresponding to the historical scheduling plans can be clustered based on the time series variation characteristics of the day-ahead power generation plan, and a matching power generation plan close to the day-ahead power generation plan is obtained according to the clustering results, and the first power generation and charging event is further corrected according to the historical power generation and charging event corresponding to the matching power generation plan.

[0041] In order to take into account the uncertainty of user load, the first charging event can be corrected according to at least one historical charging event in the historical scheduling plan that matches the first historical load; specifically, for multiple historical scheduling plans containing historical charging events, the historical loads corresponding to the historical scheduling plans can be clustered based on the temporal change characteristics of the first historical load to obtain matching historical loads close to the first historical load, and the first charging event can be further corrected according to the historical charging event corresponding to the matching historical load.

[0042] In one embodiment, the intermittent, volatility and randomness inherent in photovoltaic power generation and the uncertainty of user load can be considered simultaneously, and the historical scheduling plan and historical load are clustered according to the first time series change characteristics of the day-ahead power generation plan and the second time series change characteristics of the first historical load, respectively, to obtain a matching power generation plan similar to the day-ahead power generation plan and a matching historical load similar to the first historical load, and further the first power generation and charging event is corrected according to the historical power generation and charging events corresponding to the matching power generation plan and the matching historical load.

[0043] The above method of correcting the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan can take into account the impact of the inherent intermittent, volatility and randomness of photovoltaic power generation or the uncertainty of user load, and can more accurately formulate a day-ahead scheduling plan for energy storage equipment.

[0044] Step S105: scheduling the energy storage device based on the day-ahead scheduling plan.

[0045] Exemplarily, after obtaining the day-ahead scheduling plan, the energy storage device is scheduled based on the day-ahead scheduling plan; when the actual time reaches the start time of at least one first charging event included in the day-ahead scheduling plan, a corresponding charging instruction or discharging instruction is sent to the corresponding energy storage device based on the first charging event, so that the energy storage device is in an enabled state.

[0046] The photovoltaic station energy storage equipment scheduling method of the present invention obtains the day-ahead power generation plan of the target photovoltaic station, the first historical load on the grid side, and the historical scheduling plan; performs load forecasting based on the time series variation characteristics of the first historical load to obtain forecast load data of a first time scale; when the day-ahead power generation plan does not match the forecast load data, determines a first power generation and charging event based on the day-ahead power generation plan and the forecast load data; corrects the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan; schedules the energy storage equipment based on the day-ahead scheduling plan; can take into account the effects of the intermittent, volatility, and randomness inherent in photovoltaic power generation or the uncertainty of user load, and can more accurately formulate a day-ahead scheduling plan for energy storage equipment.

[0047] As an exemplary embodiment, the method of correcting the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan includes: obtaining a historical scheduling plan of the target station containing historical power generation and charging events and a second historical load corresponding to the timing of the historical scheduling plan; clustering the historical scheduling plan and the second historical load based on the first timing change characteristics of the day-ahead power generation plan and the second timing change characteristics of the first historical load, respectively, to obtain a clustering result; based on the clustering result, selecting historical power generation and charging events in the historical scheduling plan with a clustering degree greater than a preset degree; and correcting the first power generation and charging event based on the timestamp of the historical power generation and charging event to obtain the day-ahead scheduling plan.

[0048] In this embodiment, the intermittent, volatility and randomness inherent in photovoltaic power generation and the influence of the uncertainty of user load are taken into consideration, and the first charging event is corrected.

[0049] Exemplarily, after the clustering results are obtained, for historical power generation and charging events and the first power generation and charging event whose similarity is greater than a preset degree, the first power generation and charging event is directly replaced by the historical power generation and charging event, and the first power generation and charging event is deleted in the day-ahead scheduling plan.

[0050] In one embodiment, a K-means algorithm may be used to cluster the historical scheduling plan and the second historical load based on the first time series variation characteristics of the day-ahead power generation plan and the second time series variation characteristics of the first historical load.

[0051] Exemplarily, the clustering result may be reflected in the form of a similarity percentage; when the actual similarity percentage is greater than a preset similarity percentage, it is confirmed that the clustering degree is greater than the preset degree; wherein the preset similarity percentage may be 90%.

[0052] As an exemplary embodiment, the method of correcting the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan also includes: inputting the day-ahead power generation plan and the predicted load data into a pre-trained day-ahead scheduling plan correction model, extracting a first time series change trend of the day-ahead power generation plan and a second time series change trend of the predicted load data based on the day-ahead scheduling plan correction model, and determining the first power generation and charging event according to the first time series change trend and the second time series change trend; the day-ahead scheduling plan correction model is trained according to the time series corresponding historical photovoltaic power generation power, the first historical load, the historical power prediction data and the historical day-ahead power generation plan, and during the model training process, the historical power generation and charging event is determined based on the historical photovoltaic power generation power and the first historical load; the model is trained with the historical day-ahead power generation plan and the historical power prediction data as input features and the historical power generation and charging events as labels.

[0053] In order to further consider the differences in photovoltaic power generation and user load, in this embodiment, the impact of actual photovoltaic power generation and user load on the day-ahead scheduling plan is considered by model training; wherein, the day-ahead scheduling plan correction model is trained according to the historical photovoltaic power generation, the first historical load, the historical power forecast data and the historical day-ahead power generation plan corresponding to the time series; specifically, the historical photovoltaic power generation, the first historical load, the historical power forecast data and the historical day-ahead power generation plan corresponding to the time series are obtained, and the historical power generation and charging events are determined based on the historical photovoltaic power generation and the first historical load; further, the day-ahead scheduling plan correction model is trained with the day-ahead power generation plan and the first historical load as input data and the historical power generation and charging events as labels until the model converges.

[0054] In one embodiment, the day-ahead scheduling plan correction model may be a random forest machine learning model.

[0055] In the above implementation mode, during the model training process, according to the training method of the historical photovoltaic power generation power, the first historical load, the historical power prediction data and the historical day-ahead power generation plan corresponding to the time series, the day-ahead power generation plan and the first historical load can be considered, and the day-ahead power generation plan and the first historical load are input into the pre-trained day-ahead scheduling plan correction model, and the first charging event can be corrected by considering the deviation between the day-ahead power generation plan and the actual power generation power of the photovoltaic station, and the deviation between the predicted load and the actual load at the load end.

[0056] As an exemplary embodiment, after the first power generation and charging event is corrected based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan, the photovoltaic station energy storage equipment scheduling method also includes: obtaining the historical photovoltaic power generation power of the target photovoltaic station; performing power forecasting based on the time series variation characteristics of the historical photovoltaic power generation power to obtain intraday forecasted power data at a second time scale; wherein the second time scale is smaller than the first time scale; obtaining a second power generation and charging event at a second time scale based on the intraday forecasted power data and the forecasted load data; and correcting the day-ahead scheduling plan at a second time scale based on the second power generation and charging event.

[0057] When scheduling energy storage equipment for photovoltaic stations, 4-hour daytime scheduling is usually further performed on the basis of the 24-hour day-ahead scheduling plan; based on this, in this embodiment, the second time scale is smaller than the first time scale; specifically, the second time scale is not greater than 4 hours; illustratively, the technical solution of this embodiment is described with the second time scale being 4 hours.

[0058] In this embodiment, the historical photovoltaic power generation power of the target photovoltaic station is obtained, and power prediction is further performed based on the time series variation characteristics of the historical photovoltaic power generation power to obtain the day-ahead predicted power data for the next 4 hours; further, a second charging event of a second time scale is obtained based on the intraday predicted power data and the predicted load data; compared with the day-ahead scheduling plan determined by the day-ahead power generation plan and the predicted load data, the use of more accurate intraday predicted power data can further consider the effects of the inherent intermittent, volatility and randomness of photovoltaic power generation, and can obtain more accurate prediction results.

[0059] Exemplarily, the specific implementation method of obtaining the second charging event of the second time scale based on the intra-day predicted power data and the predicted load data refers to the content in step S103, which will not be repeated here.

[0060] Exemplarily, after obtaining the second charging event of the second time scale, when the day-ahead scheduling plan is corrected to the second time scale based on the second charging event, the second charging event is used as the first charging event in the time period in the day-ahead scheduling plan that matches the start time of the intraday predicted power data.

[0061] As a possible implementation manner, the day-ahead scheduling plan is revised in a rolling manner using the intraday predicted power data obtained by using the historical photovoltaic power generation power prediction of the second time scale with different starting times.

[0062] As an exemplary embodiment, the photovoltaic station energy storage equipment scheduling method also includes: obtaining a historical second charging event at a second time scale of the target photovoltaic station; extracting the historical photovoltaic power generation power, the first historical load and the predicted load data with the second charging event as the central time node and the second time scale as a preset duration to obtain sub-historical photovoltaic power generation power, sub-first historical load data and first predicted load data; clustering the sub-historical photovoltaic power generation power and sub-historical load data based on the intraday predicted power data and the first predicted load data to obtain a clustering result; based on the clustering result, selecting the historical second charging event with a clustering degree greater than a preset degree; and revising the day-ahead scheduling plan based on the historical second charging event.

[0063] In this embodiment, the day-ahead scheduling plan is modified by taking into account the inherent intermittency, volatility and randomness of photovoltaic power generation and the uncertainty of user load.

[0064] In one embodiment, a K-means algorithm may be used to implement clustering of the sub-historical photovoltaic power generation data and the sub-historical load data based on the intra-day predicted power data and the first predicted load data.

[0065] Exemplarily, the clustering result may be reflected in the form of a similarity percentage; when the actual similarity percentage is greater than a preset similarity percentage, it is confirmed that the clustering degree is greater than the preset degree; wherein the preset similarity percentage may be 90%.

[0066] When scheduling energy storage equipment for photovoltaic stations, in order to make the scheduling more accurate, on the basis of 24h intraday scheduling or 4h daytime scheduling, the day-ahead scheduling plan is usually further corrected in real time according to the real-time photovoltaic power generation power and real-time load data; based on this, as an exemplary embodiment, the first generation and charging event is corrected based on at least one historical generation and charging event to obtain the day-ahead scheduling plan, and the photovoltaic station energy storage equipment scheduling method also includes: obtaining the real-time photovoltaic power generation power of the target photovoltaic station and the real-time load data on the grid side; determining a third generation and charging event based on the real-time photovoltaic power generation power and the real-time load data; and correcting the day-ahead scheduling plan based on the third generation and charging event.

[0067] In this embodiment, the real-time photovoltaic power generation power of the target photovoltaic station and the real-time load data on the grid side are obtained; a third charging event is determined based on the real-time photovoltaic power generation power and the real-time load data; the day-ahead scheduling plan is corrected based on the third charging event; wherein, the method for determining the third charging event based on the real-time photovoltaic power generation power and the real-time load data can be found in the content of step S103, which will not be repeated here.

[0068] Exemplarily, when the day-ahead scheduling plan is modified based on the third charging event, the third charging event is used as the first charging event at a time in the day-ahead scheduling plan that matches the timestamp of the third charging event.

[0069] As an exemplary embodiment, the scheduling of the energy storage device based on the day-ahead scheduling plan includes: obtaining the rated energy storage duration and the rated energy storage capacity of each of the sub-energy storage devices; matching the rated energy storage duration and the rated energy storage capacity based on the generation and charging power values ​​and the generation and charging power fluctuation values ​​of each of the first generation and charging events included in the day-ahead scheduling plan to obtain a matching result; and determining the day-ahead scheduling plan of the energy storage device corresponding to each of the generation and charging events based on the matching result and the timestamp of each of the first generation and charging events.

[0070] After determining the day-ahead scheduling plan, when the actual time reaches the start time of at least one first charging event included in the day-ahead scheduling plan, a corresponding charging instruction or discharging instruction is sent to the corresponding energy storage device based on the first charging event to enable the energy storage device.

[0071] Specifically, if the first charging event corresponds to input power, the energy storage device needs to complete the charging process; if the first charging event is output power, the energy storage device needs to complete the discharging process.

[0072] In this embodiment, the energy storage device includes multiple sub-energy storage devices with different energy storage durations and energy storage capacities. The corresponding sub-energy storage devices are called according to the size and fluctuation of the input and output power according to the autonomous characteristics of the sub-energy storage devices to ensure that the power supply and demand reaches the optimal balance.

[0073] Exemplarily, the sub-energy storage devices may include hydrogen energy storage devices, battery energy storage devices, supercapacitor energy storage devices and compressed air energy storage devices; among the above sub-energy storage devices, hydrogen energy storage devices are suitable for high-power slow discharge, battery energy storage devices are suitable for low-power fast discharge, supercapacitor energy storage devices are suitable for short-time high discharge, and compressed air energy storage devices are suitable for continuous high discharge; therefore, when the energy storage devices are scheduled based on the day-ahead scheduling plan, the rated energy storage duration and rated energy storage capacity of each sub-energy storage device are obtained; based on the day-ahead scheduling plan containing the power generation and charging power values ​​and power generation and charging power fluctuation values ​​of each of the first power generation and charging events, the rated energy storage duration and the rated energy storage capacity are matched to obtain a matching result; based on the matching result and the timestamp of each of the first power generation and charging events, the day-ahead scheduling plan of the energy storage device corresponding to each of the power generation and charging events is determined.

[0074] Exemplarily, for a first charging event in which the charging power value is greater than a first preset power value and the charging power fluctuation value is not greater than the first preset fluctuation value, the hydrogen energy storage device is called based on the timestamp of the first charging event.

[0075] Exemplarily, for a first charging event in which the charging power value is less than a first preset power value and the charging power fluctuation value is greater than the first preset fluctuation value, the battery energy storage device is called based on the timestamp of the first charging event.

[0076] Exemplarily, for a first charging event in which the charging power value is greater than a first preset power value and the charging power fluctuation value is greater than the first preset fluctuation value, the supercapacitor energy storage device and / or the compressed air energy storage device is called based on the timestamp of the first charging event.

[0077] Since supercapacitor energy storage devices are suitable for short-term high discharge, and compressed air energy storage devices are suitable for long-term high discharge, the duration of the first charging event can be further considered to further schedule the supercapacitor energy storage devices and compressed air energy storage devices.

[0078] Based on this, as an exemplary embodiment, the scheduling of the energy storage device based on the day-ahead scheduling plan also includes: obtaining the starting time of the first charging event; determining the actual duration of the first charging event based on the starting time; when the actual duration is greater than the preset duration, scheduling the compressed air energy storage device based on the first charging event; when the actual duration is not greater than the preset duration, scheduling the supercapacitor energy storage device based on the first charging event.

[0079] This embodiment provides a photovoltaic station energy storage equipment scheduling device, such as Figure 2 As shown, including:

[0080] An acquisition module 501 is used to acquire a day-ahead power generation plan of a target photovoltaic station, a first historical load on the grid side, and a historical dispatching plan;

[0081] A load forecasting module 502, configured to perform load forecasting based on the time series variation characteristics of the first historical load to obtain forecast load data at a first time scale;

[0082] A first charging event determination module 503, configured to determine a first charging event based on the day-ahead power generation plan and the forecast load data when the day-ahead power generation plan does not match the forecast load data;

[0083] A day-ahead scheduling plan determination module 504, configured to modify the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan;

[0084] The energy storage device scheduling module 505 is used to schedule the energy storage device based on the day-ahead scheduling plan.

[0085] It should be noted here that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments.

[0086] It should be noted that the above modules as part of the device can be implemented by software or hardware, wherein the hardware environment includes a network environment.

[0087] An embodiment of the present invention also provides a computer device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, the memory is used to store a computer program; the processor is used to execute a method in any of the above embodiments by running the computer program stored in the memory.

[0088] Figure 3 is a structural block diagram of an optional computer device according to an embodiment of the present application, such as Figure 3 As shown, it includes a processor 10, a communication interface 20, a memory 30 and a communication bus 40, wherein the processor 10, the communication interface 20 and the memory 30 communicate with each other through the communication bus 40, wherein:

[0089] A memory 30, for storing computer programs;

[0090] The processor 10 is used to implement the photovoltaic station energy storage equipment scheduling method as described in any of the above embodiments when executing the computer program stored in the memory 30.

[0091] Optionally, in this embodiment, the communication bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0092] The communication interface is used for communication between the above-mentioned computer device and other devices.

[0093] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0094] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0095] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0096] It can be understood by those skilled in the art that Figure 3 The structure shown is for illustration only. The device for implementing any one of the methods in the above embodiments may be a terminal device, which may be a smart phone (such as an Android phone, an IOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 3 It does not limit the structure of the above electronic device. For example, the terminal device may also include Figure 3 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 3 Different configurations shown.

[0097] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which can include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0098] As an exemplary embodiment, the present application also provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute any one of the method steps of the present embodiment when running.

[0099] Optionally, in this embodiment, the above-mentioned storage medium can be used to execute the program code of the method steps of the embodiment of the present application.

[0100] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0101] Optionally, in this embodiment, the storage medium is configured to store data for executing the method in the above embodiment.

[0102] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0103] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a ROM, a RAM, a mobile hard disk, a magnetic disk, or an optical disk.

[0104] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0105] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers or network devices, etc.) to execute all or part of the steps of the method in the above embodiments.

[0106] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0108] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0109] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0110] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for dispatching energy storage equipment in a photovoltaic station, characterized in that: The photovoltaic station energy storage equipment scheduling method comprises: Obtain the day-ahead power generation plan of the target PV station, the first historical load on the grid side, and the historical dispatch plan; Perform load forecasting based on the time series variation characteristics of the first historical load to obtain forecast load data at a first time scale; When the day-ahead power generation plan does not match the predicted load data, determining a first charging event based on the day-ahead power generation plan and the predicted load data; Based on at least one historical power generation and charging event, the first power generation and charging event is modified to obtain a day-ahead scheduling plan; The energy storage device is scheduled based on the day-ahead scheduling plan.

2. The photovoltaic station energy storage equipment scheduling method according to claim 1, characterized in that: The step of correcting the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan includes: Obtain a historical scheduling plan of the target station including historical power generation and charging events and a second historical load corresponding to the time sequence of the historical scheduling plan; Based on the first time series variation characteristic of the day-ahead power generation plan and the second time series variation characteristic of the first historical load, respectively clustering the historical scheduling plan and the second historical load to obtain a clustering result; Based on the clustering result, selecting the historical power generation and charging events in the historical scheduling plan whose clustering degree is greater than a preset degree; The first charging event is corrected based on the timestamp of the historical charging event to obtain the day-ahead scheduling plan.

3. The photovoltaic station energy storage equipment scheduling method according to claim 1, characterized in that: The step of correcting the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan further includes: The day-ahead power generation plan and the predicted load data are input into a pre-trained day-ahead scheduling plan correction model, and a first time series change trend of the day-ahead power generation plan and a second time series change trend of the predicted load data are extracted based on the day-ahead scheduling plan correction model, and the first power generation and charging event is determined according to the first time series change trend and the second time series change trend; the day-ahead scheduling plan correction model is trained according to the time series corresponding historical photovoltaic power generation power, the first historical load, the historical power prediction data and the historical day-ahead power generation plan, and during the model training process, the historical power generation and charging event is determined based on the historical photovoltaic power generation power and the first historical load; the historical day-ahead power generation plan and the historical power prediction data are used as input features, and the historical power generation and charging events are used as labels for model training.

4. The photovoltaic station energy storage equipment scheduling method according to claim 1, characterized in that: After the first power generation and charging event is corrected based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan, the photovoltaic station energy storage device scheduling method further includes: Obtaining the historical photovoltaic power generation power of the target photovoltaic station; Power prediction is performed based on the time series variation characteristics of the historical photovoltaic power generation to obtain intraday predicted power data at a second time scale; wherein the second time scale is smaller than the first time scale; Obtaining a second charging event at a second time scale based on the intra-day predicted power data and the predicted load data; The day-ahead scheduling plan is corrected at a second time scale based on the second charging event.

5. The photovoltaic station energy storage equipment scheduling method according to claim 4, characterized in that: The photovoltaic station energy storage equipment scheduling method further includes: Obtaining a historical second charging event of the target photovoltaic station at a second time scale; Taking the second charging event as the central time node and the second time scale as the preset duration, the historical photovoltaic power generation power, the first historical load and the predicted load data are extracted to obtain sub-historical photovoltaic power generation power, sub-first historical load data and first predicted load data; Clustering the sub-historical photovoltaic power generation data and the sub-historical load data based on the intra-day predicted power data and the first predicted load data to obtain a clustering result; Based on the clustering result, selecting the historical second charging event with a clustering degree greater than a preset degree; The day-ahead scheduling plan is modified based on the historical second charging event.

6. The photovoltaic station energy storage equipment scheduling method according to claim 1, characterized in that: After the first power generation and charging event is corrected based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan, the photovoltaic station energy storage device scheduling method further includes: Acquire the real-time photovoltaic power generation data of the target photovoltaic station and the real-time load data of the power grid side; Determine a third charging event based on the real-time photovoltaic power generation power and the real-time load data; The day-ahead scheduling plan is modified based on the third charging event.

7. The photovoltaic station energy storage equipment scheduling method according to claim 1, characterized in that: The energy storage device includes a plurality of sub-energy storage devices with different energy storage durations and energy storage capacities, and the scheduling of the energy storage devices based on the day-ahead scheduling plan includes: Obtaining the rated energy storage duration and rated energy storage capacity of each of the sub-energy storage devices; Matching each of the rated energy storage durations and the rated energy storage capacity based on the power generation and charging power values ​​and power generation and charging power fluctuation values ​​of each of the first power generation and charging events included in the day-ahead scheduling plan to obtain a matching result; A day-ahead scheduling plan of the energy storage device corresponding to each of the power generation and charging events is determined based on the matching result and the timestamp of each of the first power generation and charging events.

8. A photovoltaic station energy storage equipment scheduling device, characterized in that: The photovoltaic station energy storage equipment scheduling device comprises: An acquisition module is used to acquire the day-ahead power generation plan of the target photovoltaic station, the first historical load and historical dispatch plan of the grid side; A load forecasting module, configured to perform load forecasting based on the time series variation characteristics of the first historical load to obtain forecast load data at a first time scale; A first charging event determination module, configured to determine a first charging event based on the day-ahead power generation plan and the forecast load data when the day-ahead power generation plan does not match the forecast load data; a day-ahead scheduling plan determination module, configured to modify the first power generation and charging event based on at least one historical power generation and charging event to obtain a day-ahead scheduling plan; An energy storage device scheduling module is used to schedule the energy storage device based on the day-ahead scheduling plan.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the photovoltaic station energy storage equipment scheduling method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the photovoltaic station energy storage equipment scheduling method according to any one of claims 1 to 7.

Images