Photovoltaic resource allocation method based on time sequence prediction and related equipment

Abstract

The invention provides a photovoltaic resource allocation method based on time sequence prediction and related equipment. The method comprises the following steps: acquiring meteorological data and power grid resource information, wherein the meteorological data comprises at least one meteorological parameter; predicting the photovoltaic output power at the target time based on the meteorological data; determining an objective function and a corresponding constraint condition based on the photovoltaic output power and the power grid resource information; and determining a photovoltaic resource configuration result based on the objective function and the constraint condition.

Description

Technical Field

[0001] The present disclosure relates to the field of photovoltaics, and in particular, to a photovoltaic resource allocation method based on time series prediction and related devices. Background Art

[0002] The new energy structure is gradually being adjusted. With the gradual grid connection of new energy sources such as photovoltaics, on the premise of ensuring safe and stable operation, an optimization configuration method with good economy and high stability is very important. Due to the characteristics of high intermittency and strong randomness of photovoltaic power generation, traditional optimization configurations mainly focus on economy and only consider economic cost issues. The early prediction of photovoltaic power output is not added to the configuration method, and the issue of energy efficiency is not noticed. This results in a lack of accuracy and reduced flexibility when formulating a scheduling plan. Summary of the Invention

[0003] The present disclosure provides a photovoltaic resource allocation method based on time series prediction and related devices, which solves the above technical problems to at least some extent.

[0004] In a first aspect of the present disclosure, there is provided a photovoltaic resource allocation method based on time series prediction, including:

[0005] Obtaining meteorological data and grid resource information, where the meteorological data includes at least one meteorological parameter;

[0006] Predicting the photovoltaic output power at a target time based on the meteorological data;

[0007] Determining an objective function and corresponding constraint conditions based on the photovoltaic output power and the grid resource information;

[0008] Determining a photovoltaic resource allocation result based on the objective function and the constraint conditions.

[0009] In a second aspect of the present disclosure, there is provided a photovoltaic resource allocation device based on time series prediction, including:

[0010] An obtaining module, configured to obtain meteorological data and grid resource information;

[0011] A prediction module, configured to predict the photovoltaic output power at a target time based on the meteorological data;

[0012] An objective function module, configured to determine an objective function and corresponding constraint conditions based on the photovoltaic output power and the grid resource information;

[0013] A result determination module, configured to determine a photovoltaic resource allocation result based on the objective function and the constraint conditions.

[0014] In a third aspect of the present disclosure, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method described in the first aspect is implemented.

[0015] In a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method described in the first aspect.

[0016] In a fifth aspect of the present disclosure, there is provided a computer program product including computer program instructions which, when run on a computer, cause the computer to execute the method described in the first aspect.

[0017] As can be seen from the above, the photovoltaic resource allocation method and related devices provided by the present disclosure predict the photovoltaic output power at a target time based on meteorological data, determine the objective function and its corresponding constraint conditions by using the predicted photovoltaic output power and grid resource information, and finally determine the photovoltaic resource allocation result according to these objective functions and constraint conditions. It can improve the prediction accuracy of the photovoltaic output power, optimize the photovoltaic resource allocation based on the prediction result and grid resource information, thereby improving the utilization rate of photovoltaic energy and the stability of the power grid. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic diagram of the photovoltaic resource allocation architecture based on time series prediction according to an embodiment of the present disclosure.

[0020] Figure 2 It is a schematic diagram of the hardware structure of an exemplary electronic device according to an embodiment of the present disclosure.

[0021] Figure 3 It is a schematic flowchart of the photovoltaic resource allocation method based on time series prediction according to an embodiment of the present disclosure.

[0022] Figure 4 It is a schematic diagram of the photovoltaic resource allocation method based on time series prediction according to an embodiment of the present disclosure.

[0023] Figure 5 It is a schematic diagram of the photovoltaic resource allocation device based on time series prediction according to an embodiment of the present disclosure. Detailed Implementation Modes

[0024] To make the objectives, technical solutions, and advantages of the present disclosure clearer and more understandable, the following further elaborates on the present disclosure in detail with reference to specific embodiments and the accompanying drawings.

[0025] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the ordinary meanings understood by those of ordinary skill in the field to which the present disclosure pertains. The terms "first", "second", and similar terms used in the embodiments of the present disclosure do not denote any order, quantity, or importance, but are only used to distinguish different components. The terms "comprising", "including", or similar terms mean that the elements or items appearing before the term cover the elements or items listed after the term and their equivalents, without excluding other elements or items. The terms "connected" or "coupled" or similar terms are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0026] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. For example, when responding to an active request from the user, a prompt message is sent to the user to clearly prompt that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application program, server, or storage medium that performs the operations of the technical solutions of the present disclosure based on the prompt message.

[0027] It can be understood that the above processes of notifying and obtaining the user's authorization are only illustrative and do not limit the implementation manners of the present disclosure. Other manners that meet relevant laws and regulations can also be applied to the implementation manners of the present disclosure.

[0028] Figure 1 shows a schematic diagram of the photovoltaic resource allocation architecture based on time series prediction according to an embodiment of the present disclosure. Refer to Figure 1, the photovoltaic resource allocation architecture 100 based on time series prediction may include a server 110, a terminal 120, and a network 130 providing a communication link. The server 110 and the terminal 120 may be connected through the wired or wireless network 130. Among them, the server 110 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, security services, and CDN.

[0029] The terminal 120 may be implemented by hardware or software. For example, when the terminal 120 is implemented by hardware, it may be various electronic devices with a display screen and supporting page display, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, and desktop computers, etc. When the terminal 120 device is implemented by software, it may be installed in the above-listed electronic devices; it may be implemented as multiple software or software modules (such as software or software modules for providing distributed services), or it may be implemented as a single software or software module, which is not specifically limited here.

[0030] It should be noted that the photovoltaic resource allocation method based on time series prediction provided by the embodiments of the present application may be executed by the terminal 120 or by the server 110. It should be understood that Figure 1 the numbers of terminals, networks, and servers in are only for illustration and are not intended to limit them. According to the implementation requirements, there may be any number of terminals, networks, and servers.

[0031] Figure 2 shows a schematic diagram of the hardware structure of the exemplary electronic device 200 provided by the embodiments of the present disclosure. As Figure 2 shown, the electronic device 200 may include: a processor 202, a memory 204, a network module 206, a peripheral interface 208, and a bus 210. Among them, the processor 202, the memory 204, the network module 206, and the peripheral interface 208 are communicatively connected to each other inside the electronic device 200 through the bus 210.

[0032] The processor 202 may be a Central Processing Unit (CPU), a Neural Network Processor (NPU), a Microcontroller Unit (MCU), a programmable logic device, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits. The processor 202 may be used to execute functions related to the technologies described in this disclosure. In some embodiments, the processor 202 may further include multiple processors integrated as a single logic component. For example, as Figure 2 shown, the processor 202 may include multiple processors 202a, 202b, and 202c.

[0033] The memory 204 may be configured to store data (e.g., instructions, computer code, etc.). As Figure 2 shown, the data stored in the memory 204 may include program instructions (e.g., program instructions for implementing the photovoltaic resource allocation method based on time series prediction in the embodiments of this disclosure) and data to be processed (e.g., the memory may store configuration files of other modules, etc.). The processor 202 may also access the program instructions and data stored in the memory 204 and execute the program instructions to operate on the data to be processed. The memory 204 may include a volatile storage device or a non-volatile storage device. In some embodiments, the memory 204 may include a Random Access Memory (RAM), a Read Only Memory (ROM), an optical disc, a magnetic disk, a hard disk, a Solid State Drive (SSD), a flash memory, a memory stick, etc.

[0034] The network module 206 may be configured to provide communication with other external devices to the electronic device 200 via a network. The network may be any wired or wireless network capable of transmitting and receiving data. For example, the network may be a wired network, a local wireless network (e.g., Bluetooth, WiFi, Near Field Communication (NFC), etc.), a cellular network, the Internet, or a combination of the above. It can be understood that the type of the network is not limited to the above specific examples. In some embodiments, the network module 206 may include any combination of any number of Network Interface Controllers (NICs), radio frequency modules, transceivers, modems, routers, gateways, adapters, cellular network chips, etc.

[0035] The peripheral interface 208 may be configured to connect the electronic device 200 to one or more peripheral devices to achieve information input and output. For example, the peripheral devices may include input devices such as a keyboard, a mouse, a touchpad, a touch screen, a microphone, various sensors, etc. and output devices such as a display, a speaker, a vibrator, an indicator light, etc.

[0036] The bus 210 can be configured to transmit information between various components of the electronic device 200 (such as the processor 202, the memory 204, the network module 206, and the peripheral interface 208), such as an internal bus (e.g., a processor-memory bus), an external bus (USB port, PCI-E bus), etc.

[0037] It should be noted that although the architecture of the above-mentioned electronic device 200 only shows the processor 202, the memory 204, the network module 206, the peripheral interface 208, and the bus 210, in the specific implementation process, the architecture of the electronic device 200 may also include other components necessary for normal execution. In addition, those skilled in the art can understand that the architecture of the above-mentioned electronic device 200 may also only include the components necessary to implement the solution of the embodiments of the present disclosure, and do not necessarily include all the components shown in the figure.

[0038] The new energy structure is gradually being adjusted, and new energy such as photovoltaic is gradually connected to the grid. On the premise of ensuring safe and stable operation, an optimization configuration method with good economy and high stability is very important. Due to the characteristics of high intermittency and strong randomness of photovoltaic power generation, in order to reduce the curtailment rate of light and improve the operation and regulation ability of photovoltaic power stations, traditional optimization configurations mainly start from economy, only consider economic cost issues, do not add the preliminary prediction of photovoltaic power output to the configuration method, and do not pay attention to the issue of energy efficiency. This makes the accuracy lacking and the flexibility reduced when formulating the scheduling plan. Therefore, how to improve the accuracy and flexibility of photovoltaic resource configuration has become a technical problem that needs to be solved urgently.

[0039] In view of this, the embodiments of the present disclosure provide a photovoltaic resource configuration method and related devices based on time series prediction. Predict the photovoltaic output power at the target time based on meteorological data, and use the predicted photovoltaic output power and grid resource information to determine the objective function and its corresponding constraint conditions. Finally, determine the photovoltaic resource configuration result according to these objective functions and constraint conditions. It can improve the prediction accuracy of photovoltaic output power, and optimize the photovoltaic resource configuration based on the prediction result and grid resource information, thereby improving the utilization rate of photovoltaic energy and the stability of the power grid.

[0040] See Figure 3 , Figure 3 shows a schematic flowchart of a photovoltaic resource configuration method based on time series prediction according to an embodiment of the present disclosure. The photovoltaic resource configuration method based on time series prediction according to an embodiment of the present disclosure can be deployed on the server side or the terminal. Figure 3 In [the figure], the photovoltaic resource configuration method 300 based on time series prediction may further include the following steps.

[0041] In step S310, meteorological data and power grid resource information are obtained, and the meteorological data includes at least one meteorological parameter.

[0042] Among them, the meteorological data can be data related to the natural environment, such as meteorological parameters like temperature, humidity, wind speed, wind direction, atmospheric pressure, etc. The power grid resource configuration information can refer to the distribution and configuration of power generation stations, substations, and lines in the power grid, and their roles in the operation of the power grid. Specifically, the power grid resource information can include data describing the attributes and states of various electrical equipment, lines, substations, and other resources in the power grid. For example, power grid operation information data such as current, voltage, active power, and reactive power that reflect the operation state of the power grid.

[0043] In some embodiments, the meteorological parameter includes at least one of temperature, humidity, irradiance, wind speed, or rain and snow weather. Among them, temperature can be a physical quantity measuring the thermal motion state of an object, usually in degrees Celsius (°C) or degrees Fahrenheit (°F). In the photovoltaic field, as the temperature rises, the conversion efficiency of photovoltaic cells usually decreases. Humidity can be a physical quantity measuring the water vapor content in the air, usually expressed as relative humidity (%). High humidity may affect the heat dissipation of photovoltaic panels, thereby affecting their working efficiency. In addition, humidity may also affect the insulation performance of power grid equipment. Irradiance can refer to the solar radiation energy received per unit area, usually in watts per square meter (W / m 2 ) as the unit. Irradiance is a direct factor affecting the output power of photovoltaic cells. On sunny days with high irradiance, the output power of photovoltaic cells will be higher. Wind speed can be a physical quantity measuring the air flow speed, usually in meters per second (m / s) or kilometers per hour (km / h). Wind speed has an important impact on the heat dissipation and safety of photovoltaic power stations. On days with higher wind speeds, the heat dissipation effect of photovoltaic panels will be better, but too high wind speeds may also cause damage to the power station equipment. Rain and snow weather can be a binary variable representing the current weather state, where 0 indicates no rain or snow, and 1 indicates rain or snow. Rain and snow will block photovoltaic panels, reducing the solar radiation energy they receive, thereby reducing the output power. At the same time, rain and snow may also cause corrosion and damage to the power station equipment.

[0044] In step S320, the photovoltaic output power at the target time is predicted based on the meteorological data.

[0045] Among them, meteorological parameters such as temperature, humidity, irradiance, wind speed, and rain and snow weather before and after the target time can be obtained from reliable meteorological data sources. Ensure the accuracy and integrity of the data, and reasonably process and fill in missing or abnormal data. Collect historical power generation data of the photovoltaic power station, including the output power under different meteorological conditions. Understand the geographical location of the photovoltaic power station, installation characteristics (such as tilt angle, orientation, etc.), and the type and efficiency of photovoltaic cells. Clean and format the collected meteorological data and photovoltaic power station data to ensure they are suitable for subsequent prediction models. The data can be normalized or standardized to improve the prediction performance of the model. Use historical meteorological data and photovoltaic power station data to train the prediction model. Input the meteorological data of the target time into the trained prediction model. The prediction model calculates the photovoltaic output power of the target time based on the input meteorological data. Output the prediction results, which may include the uncertainty or confidence interval of the prediction. Compare the prediction results with the actual photovoltaic output power to verify the accuracy of the prediction. Make necessary adjustments and optimizations to the prediction model according to the verification results.

[0046] Apply the prediction results to the dispatching and optimization strategies of the power grid to ensure the stable operation of the power grid and the efficient utilization of photovoltaic energy. Adjust the output plans of other power sources according to the predicted photovoltaic output power to meet the load demand of the power grid. Use the prediction results to formulate energy management and planning strategies to improve the energy utilization rate and economic benefits. According to the long-term meteorological prediction data, plan and optimize the layout, capacity, and type of the photovoltaic power station.

[0047] In summary, predicting the photovoltaic output power of the target time based on meteorological data can improve the accuracy and reliability of the prediction through reasonable data preprocessing, selection of appropriate prediction models, optimization of model parameters, and effective result verification and adjustment, providing strong support for power grid dispatching, energy management, and planning.

[0048] In some embodiments, predicting the photovoltaic output power of the target time based on the meteorological data includes:

[0049] Input the meteorological data into the trained prediction model to obtain the photovoltaic output power of the target time; wherein, the trained prediction model is trained based on historical meteorological data and historical photovoltaic data.

[0050] In some embodiments, the trained prediction model is trained based on historical meteorological data and historical photovoltaic data, including:

[0051] Determine the correlation between each meteorological parameter and the photovoltaic output power;

[0052] Generate a correlation matrix based on the correlation;

[0053] The prediction model is trained based on the correlation matrix, the historical meteorological data, and the historical photovoltaic data.

[0054] Specifically, due to the uncertainty and flexibility of photovoltaic output, and problems such as missing or incorrect data, and a long history of data, the present invention uses Informer time series prediction to solve the problems of time dependence and long sequences of input data, greatly improving the prediction efficiency and overcoming the limitations of traditional Transformer models in terms of memory occupancy and slow speed. For example, in the model settings of the Informer time series prediction model, a time granularity of 15 minutes is adopted, and a day is divided into 96 time nodes for continuous prediction.

[0055] The Pearson correlation analysis (PCC) can be used to analyze the correlation between key meteorological factors and time factors. The range of the Pearson correlation coefficient is [-1, 1]. 1 and -1 indicate strong correlation, and the closer to 0, the weaker the correlation. The relevant expression is:

[0056]

[0057] where: x i is the i-th meteorological factor, y i is the i-th photovoltaic output power, are the sample means of the meteorological factor and the photovoltaic output power, respectively.

[0058] Among the key meteorological factors, temperature, humidity, irradiance, wind speed, rain and snow weather, etc. are extracted, and correlation statistical analysis is carried out for different influencing conditions.

[0059] In the Informer time series prediction model, the problem of long sequence time series can be solved. Through the sparse self-attention mechanism and the information aggregation mechanism, Informer can more accurately capture the important patterns in the time series, thereby improving the prediction accuracy. A new attention mechanism is adopted in the Informer time series prediction model to reduce the computational amount, replacing self-attention with ProbSparse Self-attention; the Self-attention Distilling module reduces the data dimension and the number of network parameters; the Layer stacking replicas module improves the robustness of the model; the Decoder is a very important part in the Informer model, and the long sequence input can be obtained through this module; the Generative style is used for the prediction of the target, and the prediction result can be directly generated without the process of dynamic decoding.

[0060] First, set the training input set of the model. In the training input data, the training input set can be a×b×c, where a represents the number of input samples, b is the number of time points, and c is the data dimension. For example, for historical data with a 15-minute granularity and considering key meteorological factors for prediction, so b = 96, c = 5, and the value of a is determined by the number of input samples.

[0061] Then, calculate the single-layer time complexity. Assume that the sequence length of each input sample is L, and the feature dimension of each element in the sample is D. Then an L×D matrix and a D×L matrix can be obtained. After (L×D)×(D×L) calculation, a group of L×L matrices are generated to represent the correlation degree between each element and other elements in the sample sequence, and the time complexity is O(L 2 ). Then multiply the obtained L×L matrix and the L×D matrix to get a new L×D matrix. At this time, the space complexity is still O(L 2 ). If multiple layers are stacked, the memory space becomes O(J*L 2 ), where J refers to the number of layers of the encoder / decoder in the informer model.

[0062] Add the meteorological influence factors to the dimension of the input data and complete the prediction of the photovoltaic output through the operation of the model.

[0063] In step S330, determine the objective function and the corresponding constraint conditions based on the photovoltaic output power and the grid resource information.

[0064] Among them, based on the photovoltaic power plant power prediction results and the grid resource allocation information, with the objectives of minimizing the voltage deviation, system power loss, and photovoltaic curtailment and maximizing the economy, and adding constraint conditions for constraint. Finally, solve the objective function through the particle swarm algorithm. Among them, the voltage deviation can refer to the absolute value of the voltage difference between two nodes on the line. The system power loss can refer to the line loss between two nodes i and j in the line P and Q are the active power and reactive power, and R is the resistance of the line. The photovoltaic curtailment can refer to the difference between the photovoltaic power generation capacity and the accommodation capacity.

[0065] In some embodiments, the objective function F = F1 + F2; where,

[0066]

[0067] Among them, T is the scheduling period; U i is the output voltage of the i-th photovoltaic power plant, U0 is the reference output voltage; μ1, μ2, μ3 are the weights of the objective function; P ij , Q ij are the active power and reactive power between two nodes of the line; R ijis the resistance value between lines; P PV 、P P ′ V are the photovoltaic power generation capacity and the accommodation capacity; C buy 、C sell are the electricity purchase cost and the electricity sale cost; P buy 、P sell are the electricity purchase quantity and the electricity sale quantity; C cut 、P cut are the penalty coefficient for load shedding and the load shedding quantity; C PV,cut is the penalty coefficient for curtailment of PV power; C loss is the operation and maintenance loss coefficient of the PV power station; P t is the dispatching power within the dispatching period; n is the number of nodes, i.e., the number of PV power stations.

[0068] In some embodiments, the constraint conditions include power flow constraint conditions and node voltage constraints; among them,

[0069] The power flow constraint conditions include:

[0070]

[0071] The node voltage constraint conditions include:

[0072] U min <U i <U max ,

[0073] Among them, P i 、P j are the active powers between two nodes of the line; Q i 、Q j are the reactive powers between two nodes of the line; X ij is the inductance between two nodes of the line; U max 、U min are the upper and lower limits of the voltage.

[0074] In step S340, determine the photovoltaic resource allocation result based on the objective function and the constraint conditions.

[0075] Among them, according to the objective function and the constraint conditions set by the model, use the particle swarm optimization algorithm to perform the operation of the optimal solution and output the optimal dispatching result.

[0076] Among them, the optimal scheduling result can refer to the power generation plan of a photovoltaic power station calculated by an optimization algorithm (such as the particle swarm optimization algorithm) under the objective function and constraint conditions. The optimal scheduling result can be for a single photovoltaic power station or for the coordinated scheduling of multiple photovoltaic power stations, specifically depending on the scale of the problem and the optimization objective. For example, the optimal scheduling result can include the power generation output curve of the photovoltaic power station, that is, the variation of the power generation power of the photovoltaic power station over time within a future period (such as one day, one week, or one month). Specific power generation instructions can be issued to the photovoltaic power station based on this power generation output curve to ensure that the power generation amount matches the grid demand. That is, a dynamic adjustment strategy for photovoltaic power generation can be realized, and the power generation plan can be dynamically adjusted according to real-time meteorological data, grid load changes, etc., to achieve efficient configuration and stable operation.

[0077] Specifically, historical power generation data can be collected first. For example, collect the power generation data of a photovoltaic power station in the past few years, including power generation power, meteorological conditions (such as light intensity, temperature, humidity, etc.). Obtain grid demand data. For example, collect the historical load data of the grid to understand the variation law of power demand. Obtain meteorological prediction data. For example, obtain the meteorological forecast data for a future period to predict the power generation potential of the photovoltaic power station. Then, a time series prediction model (such as the Informer model) can be used to predict the future power generation of the photovoltaic power station. For example, predict the power generation power per hour within the next 24 hours. For example, at 10:00: the power generation power is 500 kW; at 12:00: the power generation power is 800 kW; at 15:00: the power generation power is 600 kW. Use the particle swarm optimization algorithm (PSO) to optimize the objective function and solve for the optimal power generation plan. For example, at 10:00: the planned power generation power is 480 kW; at 12:00: the planned power generation power is 820 kW; at 15:00: the planned power generation power is 610 kW. The power generation plan can be dynamically adjusted according to real-time meteorological data and grid load changes. For example, if the light intensity suddenly increases at noon, the power generation power can be appropriately increased. Assume that the installed capacity of a certain photovoltaic power station is 1 MW, and the power generation prediction results for the next 24 hours are as follows:

[0078]

[0079] The optimization objective can be to maximize the economic benefits of the photovoltaic power station while meeting the grid demand. The optimization results can include: At 10:00, the power generation is adjusted to 450 kW (meeting the grid demand and avoiding waste). At 12:00, the power generation is adjusted to 700 kW (meeting the grid demand and avoiding over-generation). At 15:00, the power generation is adjusted to 550 kW (meeting the grid demand and avoiding waste). Dynamic adjustment can be further carried out: If at 12:00, the weather forecast shows that the light intensity increases and the actual power generation may reach 850 kW. At this time, the dispatching system can dynamically adjust the power generation plan, increase the power generation to 700 kW, and store the extra 150 kW in the energy storage system for subsequent use.

[0080] It can be seen that the optimal dispatching result of the embodiment of the present disclosure is obtained through the analysis of historical data, the prediction of future power generation, and the calculation of the optimization algorithm. It can ensure that the photovoltaic power station maximizes its economic benefits while meeting the grid demand. And through dynamic adjustment, the dispatching scheme can adapt to the real-time changing meteorological conditions and grid load, thereby improving the operation efficiency and stability of the photovoltaic power station.

[0081] See Figure 4 , Figure 4 shows a schematic diagram of a photovoltaic resource allocation method based on time series prediction according to an embodiment of the present disclosure. Figure 4Among them, the Informer time series prediction model is first adopted to predict the photovoltaic output. This model has a unique self-attention mechanism different from the traditional Transformer prediction model and the ability to process text in parallel, and can solve the problem of data dependence on long time series. Then, adjustment strategies and optimization configuration schemes are formulated according to the prediction results, with the economic optimum, minimum network loss, minimum voltage offset, etc. as the objective functions to solve the power supply and demand problems of the power grid. Finally, the particle swarm algorithm is used to solve the objective function to obtain the optimal scheduling scheme that meets the requirements of the objective function. The particle swarm algorithm first initializes the particle swarm; then evaluates the fitness of each particle and calculates the fitness value, which is the value of the objective function at the position where the particle is located; then updates the velocity and position; then judges the quality of the particle and randomly selects a non-dominated solution as the global optimal position; then repeats the above steps within the number of iterations; finally, outputs the solution under the objective function. The optimal solution obtained under the setting of the constraint conditions and the objective function needs to satisfy the Pareto optimal index of multi-objective optimization, and the solution set found becomes the Pareto optimal solution set. For a single photovoltaic power station, under the influence of specific meteorological factors, by analyzing the historical power generation data of the photovoltaic power station and the power demand on the demand side of the power grid, the photovoltaic output for a period of time in the future is predicted to obtain the corresponding power generation information. According to the set objective function and constraint conditions, the particle swarm algorithm is used to calculate the optimal scheduling scheme. This scheme is obtained through optimization calculation based on the collection of historical data and the time series prediction results of the Informer model, and is dynamically adjusted according to the actual situation, so as to ensure the efficient configuration and stable operation in aspects such as power generation, load and grid connection.

[0082] It can be seen that according to the method of the embodiments of the present disclosure, the method based on the Informer time series is used to predict the photovoltaic output, which can solve the prediction of long time series, and according to the prediction results, optimize the configuration of the scheduling of the photovoltaic power station, so that the photovoltaic power station has good economy and ensures the stable operation of the power grid, and consumes the photovoltaic power generation as much as possible.

[0083] It should be noted that the method of the embodiments of the present disclosure can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario and completed by the cooperation of multiple devices. In this case of a distributed scenario, one of these multiple devices can only execute one or more steps of the method of the embodiments of the present disclosure, and these multiple devices will perform photovoltaic resource allocation based on time series prediction with each other to complete the described method.

[0084] It should be noted that some embodiments of the present disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the above embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] Based on the same inventive concept, corresponding to any of the above-described embodiment methods, the present disclosure also provides a photovoltaic resource allocation device based on time series prediction. Refer to Figure 5 , the photovoltaic resource allocation device based on time series prediction, the device includes:

[0086] An acquisition module, configured to acquire meteorological data and grid resource information;

[0087] A prediction module, configured to predict the photovoltaic output power at a target time based on the meteorological data;

[0088] A target function module, configured to determine a target function and corresponding constraint conditions based on the photovoltaic output power and the grid resource information;

[0089] A result determination module, configured to determine a photovoltaic resource allocation result based on the target function and the constraint conditions.

[0090] For the convenience of description, when describing the above device, various modules are described separately according to their functions. Of course, when implementing the present disclosure, the functions of each module can be implemented in one or more software and / or hardware.

[0091] The device of the above embodiment is used to implement the corresponding photovoltaic resource allocation method based on time series prediction in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0092] Based on the same inventive concept, corresponding to any of the above-described embodiment methods, the present disclosure also provides a non-transitory computer-readable storage medium, and the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the photovoltaic resource allocation method based on time series prediction as described in any of the foregoing embodiments.

[0093] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0094] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the photovoltaic resource allocation method based on time series prediction as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0095] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary, and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the concept of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of brevity.

[0096] In addition, for the sake of simplicity of description and discussion, and in order not to make the embodiments of the present disclosure difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. In addition, the devices may be shown in block diagram form in order to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure are to be implemented (i.e., these details should be fully within the understanding of those skilled in the art). In the case where specific details (such as circuits) are set forth to describe the exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that the embodiments of the present disclosure can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0097] Although the present disclosure has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0098] Embodiments of the present disclosure are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Accordingly, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the embodiments of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A photovoltaic resource allocation method based on time series prediction, comprising: Obtaining meteorological data and grid resource information, where the meteorological data includes at least one meteorological parameter; Predicting the photovoltaic output power at the target time based on the meteorological data; Determining an objective function and corresponding constraint conditions based on the photovoltaic output power and the grid resource information; Determining the photovoltaic resource allocation result based on the objective function and the constraint conditions.

2. The method according to claim 1, wherein Predicting the photovoltaic output power at the target time based on the meteorological data, comprising: Inputting the meteorological data into a trained prediction model to obtain the photovoltaic output power at the target time; wherein, the trained prediction model is trained based on historical meteorological data and historical photovoltaic data.

3. The method according to claim 1, wherein The trained prediction model is trained based on historical meteorological data and historical photovoltaic data, comprising: Determining the correlation between each meteorological parameter and the photovoltaic output power; Generating a correlation matrix based on the correlation; Training the prediction model based on the correlation matrix, the historical meteorological data, and the historical photovoltaic data.

4. The method according to claim 1, wherein The objective function F = F1 + F2; Wherein, Among them, T is the scheduling period; μ1, μ2, μ3 are the weights of the objective function; P ij , Q ij are the active power and reactive power between two nodes of the line; R ij is the resistance value between lines; P PV , P P ′ V are the photovoltaic power generation capacity and the absorption capacity; C buy , C sell are the power purchase cost and the power sale cost; P buy , P sell are the power purchase quantity and the power sale quantity; C cut , P cut are the penalty coefficient and the amount of load shed; C PV,cut is the penalty coefficient for light curtailment; C loss is the operation and maintenance loss coefficient of the photovoltaic power station; P t is the scheduling power within the scheduling period.

5. The method according to claim 4, wherein, The constraint conditions include a power flow constraint condition and a node voltage constraint; wherein, The power flow constraint condition includes: The node voltage constraint condition includes: U min <U i <U max , Among them, P i , P j are the active powers between two nodes of the line; Q i , Q j are the reactive powers between two nodes of the line; X ij is the inductance between two nodes of the line; U max , U min are the upper and lower limits of the voltage.

6. The method according to claim 1, wherein Determining the photovoltaic resource allocation result based on the objective function and the constraint conditions, comprising: Using a particle swarm algorithm to perform an optimal solution operation on the objective function and the constraint conditions to obtain the optimal scheduling result as the photovoltaic resource allocation result.

7. The method according to claim 1, wherein The meteorological parameter includes at least one of temperature, humidity, irradiance, wind speed, or rain and snow weather.

8. A photovoltaic resource allocation device based on time series prediction, comprising: An acquisition module for acquiring meteorological data and grid resource information; A prediction module for predicting the photovoltaic output power at the target time based on the meteorological data; An objective function module for determining an objective function and corresponding constraint conditions based on the photovoltaic output power and the grid resource information; A result determination module for determining the photovoltaic resource allocation result based on the objective function and the constraint conditions.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the photovoltaic resource allocation method based on time series prediction according to any one of claims 1 to 7 when executing the program.

10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the photovoltaic resource allocation method based on time series prediction according to any one of claims 1 to 7.

Images