New energy station multi-stage collaborative energy distribution method, device and equipment and storage medium

Abstract

The invention discloses a new energy station multi-stage cooperative energy distribution method, device and equipment and a storage medium. The method comprises the following steps: firstly, obtaining new energy station data of a to-be-tested new energy station at a historical moment and new energy station data of the to-be-tested new energy station at a current moment; according to the new energy station data at the historical moment and the new energy station data at the current moment, constructing an energy demand prediction model; according to the new energy station data at the current moment and an energy demand prediction model, calculating to obtain an energy demand prediction value at the current moment; comparing the energy demand prediction value with each preset energy distribution threshold value, and determining an energy distribution level function corresponding to the energy demand prediction value; and finally, according to the energy distribution level function and the energy demand prediction value, calculating to obtain an energy distribution value. By implementing the method, the energy demand can be predicted according to continuously changing real-time data, and efficient energy distribution is realized.

Description

Technical Field

[0001] The present invention relates to the field of energy distribution technology, and in particular to a multi-level collaborative energy distribution method, device, equipment and storage medium for a new energy station. Background Art

[0002] In the field of operation and management of new energy stations, the development of intelligent control systems has become a research hotspot in recent years, especially in the efficient use of renewable energy and energy distribution optimization, and various technologies have emerged. These technologies mainly rely on traditional data processing and control strategies, such as rule-based control algorithms and basic data analysis methods. With the rise of machine learning and deep learning technologies, their applications in energy forecasting and demand response have begun to gradually unfold.

[0003] Since the data from new energy stations is constantly changing, it is difficult for existing technologies to accurately predict energy demand based on the ever-changing data and achieve efficient energy distribution. Summary of the invention

[0004] The present invention provides a multi-level collaborative energy distribution method, device, terminal equipment and storage medium for a new energy station, which can predict energy demand based on constantly changing real-time data and achieve efficient energy distribution.

[0005] An embodiment of the present invention provides a multi-level collaborative energy distribution method for a new energy station, comprising:

[0006] Obtaining the new energy station data of the new energy station to be tested at the historical moment and the new energy station data at the current moment; wherein the new energy station data includes: energy production data, energy consumption data, environmental weather data, equipment performance data and energy demand data;

[0007] Based on the new energy station data at the above historical moments, an energy demand prediction model is constructed;

[0008] According to the energy demand prediction model and the new energy station data at the current moment, the energy demand prediction value at the current moment is calculated;

[0009] Compare the energy demand forecast value with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand forecast value;

[0010] The energy allocation value is calculated based on the energy allocation level function and the energy demand forecast value.

[0011] Furthermore, the above energy demand prediction model is:

[0012]

[0013] In the formula, x irepresents the data of the new energy station of type i, f i (x i ) represents the mixed Gaussian model function of the i-th type of new energy station data, m represents the total number of different Gaussian distributions of the i-th type of new energy station data, j represents the j-th Gaussian distribution of the i-th type of new energy station data, a ij represents the relative importance of the jth Gaussian distribution in the i-th type of new energy station data in the model, μ ij represents the mean of the jth Gaussian distribution in the i-th type of new energy station data, σ ij represents the standard deviation of the jth Gaussian distribution in the i-th type of new energy station data, g(x) represents the normalization function, σ g represents the standard deviation of the normalized function, x represents the data value input into the above energy demand prediction model, P(x) represents the energy demand prediction value, n represents the number of data types of the new energy station data, and w i Represents the weight parameter of the i-th type of new energy station data.

[0014] Furthermore, the energy demand forecast value is compared with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand forecast value, including:

[0015] Comparing the above energy demand forecast value with each preset energy allocation threshold;

[0016] According to the comparison results, the energy allocation level function corresponding to the above energy demand forecast value is determined by the following formula:

[0017]

[0018]

[0019] In the formula, h q (P) represents the allocation strategy function of the qth level, A q represents the maximum amplitude parameter of the control allocation strategy function at the qth level, k q represents the adjustment parameter of the qth level, B q represents the parameter for determining the baseline energy allocation of the qth level, P represents the predicted energy demand, and λ q represents the energy allocation threshold of the qth level, and H(P,λ) represents the energy allocation level function.

[0020] Furthermore, the energy allocation value is calculated according to the following formula:

[0021]

[0022] Where S(P) represents the energy allocation value, σ represents the standard deviation of the energy demand forecast value, and μ represents the mean of the energy demand forecast value.

[0023] Furthermore, it also includes:

[0024] Get the actual energy distribution data at the current moment;

[0025] The prediction deviation is calculated according to the absolute value of the difference between the actual energy allocation data and the energy allocation value;

[0026] The above-mentioned prediction deviation is compared with each preset deviation threshold to obtain the fault degree of the current new energy station.

[0027] Furthermore, it also includes:

[0028] According to the above prediction deviation and the preset deviation threshold, the fault assessment function value at the current moment is calculated;

[0029] According to the above energy demand data at the current moment and the above energy consumption data at the current moment, the energy demand and consumption evaluation relationship function value at the current moment is calculated;

[0030] According to the energy demand and consumption evaluation relationship function value and the fault evaluation function value, the environmental impact evaluation function value at the current moment is calculated.

[0031] Furthermore, it also includes:

[0032] Compare the above environmental impact assessment function value with each preset environmental impact threshold value to determine the environmental impact level under the current energy allocation value;

[0033] According to the above environmental impact level, the parameters in the above energy allocation level function are adjusted.

[0034] Based on the above method embodiment, the present invention provides a corresponding device embodiment;

[0035] The present invention provides a multi-level coordinated energy distribution device for a new energy station, comprising:

[0036] New energy station data acquisition module, prediction model building module, demand prediction calculation module, energy allocation level function determination module and energy allocation calculation module;

[0037] The new energy station data acquisition module is used to acquire the new energy station data of the new energy station to be tested at the historical moment and the new energy station data at the current moment; wherein the new energy station data includes: energy production data, energy consumption data, environmental weather data, equipment performance data and energy demand data;

[0038] The above-mentioned prediction model building module is used to build an energy demand prediction model based on the new energy station data at the above-mentioned historical moment;

[0039] The demand forecasting calculation module is used to calculate the energy demand forecast value at the current moment according to the energy demand forecasting model and the new energy station data at the current moment;

[0040] The energy allocation level function determination module is used to compare the energy demand prediction value with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand prediction value;

[0041] The energy allocation calculation module is used to calculate the energy allocation value according to the energy allocation level function and the energy demand forecast value.

[0042] Based on the above method embodiment, the present invention provides a terminal device embodiment;

[0043] The present invention provides a terminal device, including a processor, a memory, and a computer program stored in the above-mentioned memory and configured to be executed by the above-mentioned processor. When the above-mentioned processor executes the above-mentioned computer program, the multi-level collaborative energy distribution method for new energy stations described in any embodiment of the present invention is implemented.

[0044] Based on the above method embodiment, the present invention provides a storage medium embodiment;

[0045] The present invention provides a storage medium, including a processor, a memory, and a computer program stored in the above-mentioned memory and configured to be executed by the above-mentioned processor. When the above-mentioned processor executes the above-mentioned computer program, the multi-level collaborative energy distribution method for new energy stations described in any embodiment of the present invention is implemented.

[0046] The embodiments of the present invention have the following beneficial effects:

[0047] The present invention provides a multi-level collaborative energy allocation method, device, terminal device and storage medium for new energy stations. The above method first obtains the new energy station data of the new energy station to be tested at the historical moment and the new energy station data at the current moment; wherein the new energy station data includes: energy production data, energy consumption data, environmental weather data, equipment performance data and energy demand data; then, according to the new energy station data at the historical moment, an energy demand prediction model is constructed; according to the new energy station data at the current moment and the above energy demand prediction model, the energy demand prediction value at the current moment is calculated; then the energy demand prediction value is compared with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand prediction value; finally, according to the above energy allocation level function and the above energy demand prediction value, the energy allocation value is calculated. Therefore, the present invention first constructs an energy demand prediction model using historical new energy station data, then obtains the energy demand prediction value at the current moment based on the calculation between real-time data and the energy demand prediction model, and finally determines the final energy allocation value based on the energy demand prediction value. Therefore, the present invention can realize the prediction of energy demand according to the constantly changing real-time data, and then realize more efficient energy allocation according to the prediction result of real-time energy demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of a multi-level collaborative energy allocation method for a new energy station provided by an embodiment of the present invention.

[0049] Figure 2 It is a schematic diagram of comparing evaluation indicators provided by an embodiment of the present invention.

[0050] Figure 3 It is a schematic diagram of the structure of a multi-level collaborative energy distribution device for a new energy station provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] like Figure 1 As shown, a multi-level collaborative energy allocation method for a new energy station provided by an embodiment of the present invention includes:

[0053] Step S101: Acquire the new energy station data of the new energy station to be tested at the historical moment and the new energy station data at the current moment; wherein the new energy station data includes: energy production data, energy consumption data, environmental weather data, equipment performance data and energy demand data;

[0054] Specifically, the above-mentioned energy production data include production data of various types of renewable energy (such as solar energy and wind energy) and non-renewable energy, which can be directly obtained from the monitoring system of the energy station; the above-mentioned energy consumption data include recording the energy consumption of various equipment and operations in the new energy station, as well as the amount of energy supplied to users; the above-mentioned environmental weather data include temperature, humidity, wind speed, sunshine intensity, etc., which have a direct impact on the production of renewable energy such as solar energy and wind energy; the above-mentioned equipment performance data are performance data of various types of equipment (such as solar panels, wind turbines) in the energy station, including efficiency, power, maintenance records, etc.; the above-mentioned energy demand data include peak demand time, grid load, energy storage equipment status, etc. These energy demand data are crucial for balancing supply and demand and optimizing resource allocation.

[0055] Preferably, after obtaining the new energy station data, the data are cleaned and standardized.

[0056] Step S102: constructing an energy demand prediction model based on the new energy station data at the above historical moments;

[0057] In a preferred embodiment, the energy demand prediction model is:

[0058]

[0059] In the formula, x i represents the data of the new energy station of type i, f i (x i ) represents the mixed Gaussian model function of the i-th type of new energy station data, m represents the total number of different Gaussian distributions of the i-th type of new energy station data, j represents the j-th Gaussian distribution of the i-th type of new energy station data, a ij represents the relative importance of the jth Gaussian distribution in the i-th type of new energy station data in the model, μ ij represents the mean of the jth Gaussian distribution in the i-th type of new energy station data, σ ij represents the standard deviation of the jth Gaussian distribution in the i-th type of new energy station data, g(x) represents the normalization function, σ g represents the standard deviation of the normalized function, x represents the data value input into the above energy demand prediction model, P(x) represents the energy demand prediction value, n represents the number of data types of the new energy station data, and w i Represents the weight parameter of the i-th type of new energy station data.

[0060] In this preferred embodiment, an energy demand prediction model is constructed through the new energy station data at the above historical moments, and various parameters in the energy demand prediction model are determined.

[0061] Step S103: Calculate the energy demand forecast value at the current moment according to the energy demand forecast model and the new energy station data at the current moment;

[0062] Specifically, in the previous step, an energy demand forecasting model was constructed through the new energy station data at historical moments and various parameters in the energy demand forecasting model were determined. In the current step, the new energy station data at the current moment is substituted into the above energy demand forecasting model to obtain the energy demand forecast value of the new energy station data at the current moment.

[0063] Step S104: comparing the energy demand prediction value with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand prediction value;

[0064] In a preferred embodiment, the energy demand forecast value is compared with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand forecast value, including:

[0065] Comparing the above energy demand forecast value with each preset energy allocation threshold;

[0066] According to the comparison results, the energy allocation level function corresponding to the above energy demand forecast value is determined by the following formula:

[0067]

[0068] In the formula, h q (P) represents the allocation strategy function of the qth level, A q represents the maximum amplitude parameter of the control allocation strategy function at the qth level, k q represents the adjustment parameter of the qth level, B q represents the parameter for determining the baseline energy allocation of the qth level, P represents the predicted energy demand, and λ q represents the energy allocation threshold of the qth level, and H(P,λ) represents the energy allocation level function.

[0069] Specifically, the above adjustment parameter k q Allows adjustment of the sensitivity of energy allocation value to changes in energy demand, so that when the energy demand forecast value P is close to a certain energy allocation threshold, the energy allocation value can change more sensitively or more smoothly; determines the parameter B of the baseline energy allocation q Ensure that even at low energy demand, there is a basic energy supply level to meet basic operating needs; amplitude parameter A q Used to control the maximum intensity of energy distribution values ​​at different levels to adapt to peak and trough periods.

[0070] Preferably, different new energy stations may have different energy output capabilities, storage capacities, and consumption patterns, so each new energy station can select an appropriate maximum amplitude parameter A according to its own characteristics. q , adjustment parameter k q and the parameter B that determines the baseline energy allocation q , to optimize the energy allocation value.

[0071] Indicatively, if the energy demand forecast value P is greater than λ 1 and not greater than λ 2 , then the level corresponding to the current energy demand forecast value is the second level, that is, q = 2. Substituting it into the formula, we can calculate the current second-level allocation strategy function h 2 (P).

[0072] In this preferred embodiment, by comparing the energy demand forecast value with each preset energy allocation threshold, the level interval of the energy demand forecast value is determined, and then the energy allocation level function corresponding to the energy demand forecast value is calculated.

[0073] Step S105: Calculate the energy allocation value according to the energy allocation level function and the energy demand forecast value.

[0074] In a preferred embodiment, the energy allocation value is calculated according to the following formula:

[0075]

[0076] Where S(P) represents the energy allocation value, σ represents the standard deviation of the energy demand forecast value, and μ represents the mean of the energy demand forecast value.

[0077] Preferably, different energy demand levels require the new energy station to implement energy allocation values ​​of different intensities, and the exponential function allows for rapid or gradual adjustments at different energy demand levels.

[0078] In this preferred embodiment, the energy allocation value is calculated by using the above formula, the energy demand forecast value and the energy allocation level function.

[0079] In another preferred embodiment, it also includes:

[0080] Get the actual energy distribution data at the current moment;

[0081] The prediction deviation is calculated according to the absolute value of the difference between the actual energy allocation data and the energy allocation value;

[0082] The above-mentioned prediction deviation is compared with each preset deviation threshold to obtain the fault degree of the current new energy station.

[0083] Specifically, the above prediction deviation is calculated by the following formula:

[0084] δ = |DS(P)|;

[0085] Where δ represents the prediction deviation, and D represents the actual energy allocation data, which is the real-time energy allocation value or the average energy allocation value in the time period to be evaluated.

[0086] Specifically, set the first-order deviation threshold Δ 1 and the second deviation threshold Δ 2 , if the prediction deviation δ is less than the first-order deviation threshold Δ 1 , it is a minor fault, and it is necessary to analyze the energy production and energy consumption data, check whether there are abnormal fluctuations in these data, and slightly adjust the energy allocation value according to the environmental weather data to increase the proportion of solar panels used; if the prediction deviation δ is greater than the first-class deviation threshold Δ 1 And less than the second deviation threshold Δ 2 , it is a medium fault, and a comprehensive equipment performance check of the new energy station is required, including a thorough check of key equipment using advanced diagnostic tools. Based on the diagnostic results, the energy allocation value is deeply optimized according to the current energy demand data and historical new energy station data; if the prediction deviation δ is greater than the second-class deviation threshold Δ 2 , it is a serious fault and adjustment measures need to be implemented immediately to optimize the energy allocation value or slightly adjust the equipment settings, start the inspection procedure, including recalibrating the equipment and temporarily adjusting the energy output, perform fault diagnosis and repair, isolate the fault area to prevent the problem from further spreading, and then re-forecast the energy demand and recalculate the energy allocation.

[0087] In this preferred embodiment, the prediction deviation is obtained by calculating the absolute value of the difference between the actual energy distribution data and the energy distribution value, and the prediction deviation is then compared with the preset deviation threshold to obtain the current fault degree of the new energy station.

[0088] In another preferred embodiment, it also includes:

[0089] According to the above prediction deviation and the preset deviation threshold, the fault assessment function value at the current moment is calculated;

[0090] According to the above energy demand data at the current moment and the above energy consumption data at the current moment, the energy demand and consumption evaluation relationship function value at the current moment is calculated;

[0091] According to the energy demand and consumption evaluation relationship function value and the fault evaluation function value, the environmental impact evaluation function value at the current moment is calculated.

[0092] Specifically, the fault assessment function value is calculated by the following formula:

[0093]

[0094] Where f(t) represents the fault assessment function value at time t, A represents the adjustment factor for adjusting the environmental impact assessment under the minor fault level, δ(t) represents the prediction deviation at time t, represents the standard deviation parameter, which affects the sensitivity of the fault level to the environmental impact assessment, and B represents the adjustment factor used to adjust the environmental impact assessment under medium faults.

[0095] Specifically, adjustment factor A is used to adjust the exponential impact assessment of minor faults, and adjustment factor B is used to adjust the linear impact assessment of medium faults.

[0096] Specifically, the energy demand and consumption evaluation relationship function value is calculated by the following formula:

[0097]

[0098] Where, γ(D(t), C(t)) represents the energy demand and consumption evaluation relationship function value, ω i represents the weight parameter of the i-th type of new energy station data. This weight parameter is used to adjust the difference between energy demand and consumption. D(t) represents the energy demand data at time t, C(t) represents the energy consumption data at time t, and δ i Represents the offset parameter of the i-th type of new energy station data, σ i Represents the distribution width parameter of the i-th type of new energy station data.

[0099] Preferably, since there may be multiple energy types in the new energy station at the same time, such as solar energy, wind energy, energy storage equipment, etc., as well as energy demand at different time periods, the importance of each energy type and time period may be different, so the weight parameter ω is used i To reflect these differences, for example, solar power may have a higher weight during the day, while wind power may have a higher weight at night or under certain weather conditions.

[0100] Preferably, the offset parameter δ i It is used to represent the difference between the expected energy consumption and the actual demand for a specific energy type or time period. In principle, if the energy output of the solar panels is lower than expected over a period of time, this deviation can be offset by the offset parameter δ i To quantify.

[0101] Preferably, the distribution width parameter σ i The difference between energy demand and consumption may fluctuate to different degrees in different energy types or time periods. By adjusting the distribution width parameter σi , the width of the distribution of this fluctuation can be controlled. A smaller distribution width parameter means a more sensitive response to differences, which is suitable for situations where precise control of energy demand is critical.

[0102] Specifically, the environmental impact assessment function value is calculated by the following formula:

[0103]

[0104] Where E represents the environmental impact assessment function value, T represents the assessment time range, and α and β represent adjustment parameters used to balance the impact of fault assessment and energy use.

[0105] In this preferred embodiment, the environmental impact assessment function value is calculated by predicting the deviation, the preset deviation threshold, the energy demand data and the energy consumption data.

[0106] In another preferred embodiment, it also includes:

[0107] Compare the above environmental impact assessment function value with each preset environmental impact threshold value to determine the environmental impact level under the current energy allocation value;

[0108] According to the above environmental impact level, the parameters in the above energy allocation level function are adjusted.

[0109] Specifically, set the first-level environmental impact threshold and the second-level environmental impact threshold. If the environmental impact assessment function value E is less than the first-level environmental impact threshold, it is assessed as a first-level environmental impact. It is necessary to increase the monitoring frequency, closely track the environmental impact, and slightly adjust the energy allocation threshold and the maximum amplitude parameter A. q , adjustment parameter k q and the parameter B that determines the baseline energy allocation q , to optimize energy efficiency; if E is greater than the primary environmental impact threshold and less than the secondary environmental impact threshold, it is assessed as a secondary environmental impact, requiring an in-depth performance review, including efficiency analysis of energy conversion equipment and energy transmission loss assessment. Based on the review results, the energy allocation strategy is replanned, the energy flow during peak and valley periods is adjusted, and the energy allocation threshold and maximum amplitude parameter A are adjusted. q , adjustment parameter k q , Determine the parameters of baseline energy allocation B q, the standard deviation σ of the energy demand forecast value, the mean μ of the energy demand forecast value and the various parameters in the energy demand forecast model. According to the environmental impact analysis, measures are implemented to reduce the negative impact of specific environmental parameters, including reducing specific emissions and optimizing resource utilization. If E is greater than the secondary environmental impact threshold, it is assessed as a tertiary environmental impact. When serious environmental impacts are identified, high-energy-consuming operations and inefficient energy use are immediately suspended. Based on the analysis of serious environmental impacts, long-term energy management and environmental protection strategies are formulated, including restructuring the energy infrastructure and resetting the energy allocation strategy.

[0110] In this preferred embodiment, the environmental impact level under the current energy allocation value is determined by comparing the environmental impact assessment function value with each preset environmental impact threshold, and then the parameters in the energy allocation level function are adjusted accordingly based on the environmental impact level.

[0111] In another preferred embodiment, an existing new energy station is selected as an experimental object, and the evaluation indicators such as "accuracy of predicted energy demand", "energy allocation efficiency", "minor fault recognition rate", "medium fault recognition rate", "serious fault recognition rate", "environmental impact assessment accuracy", "stability" and "fault response time" are calculated respectively by using the traditional scheme and the scheme of the present invention. Schematically, the comparison diagram of the evaluation indicators of the traditional method and the method of the present invention is shown in FIG. Figure 2 As shown, it can be clearly seen that the scheme of the present invention has advantages in many aspects. First, the accuracy of predicting energy demand has been improved by 17%, which means that energy allocation can meet actual needs more accurately, thereby reducing waste and improving efficiency. Secondly, the efficiency of energy allocation has been improved by 25%, which is the result of the combined effect of more accurate demand forecasting and efficient allocation strategies. In terms of fault identification, the recognition rates of minor, moderate and major faults have increased by 15%, 20% and 35% respectively. This significant improvement shows that the scheme can more effectively identify and classify faults, so as to take more appropriate countermeasures, reduce system downtime and improve overall operating efficiency. Finally, the accuracy of environmental impact assessment has been improved by 25%. This means that energy use strategies can be adjusted more accurately to reduce negative impacts on the environment and achieve sustainable development goals. The stability is improved by 10% compared with traditional methods, and the fault response time is reduced by 15 minutes compared with traditional methods.

[0112] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0113] like Figure 3As shown, an embodiment of the present invention provides a multi-level collaborative energy distribution device for a new energy station, including: a new energy station data acquisition module, a prediction model construction module, a demand prediction calculation module, an energy distribution level function determination module and an energy distribution calculation module;

[0114] The new energy station data acquisition module is used to acquire the new energy station data of the new energy station to be tested at the historical moment and the new energy station data at the current moment; wherein the new energy station data includes: energy production data, energy consumption data, environmental weather data, equipment performance data and energy demand data;

[0115] The above-mentioned prediction model building module is used to build an energy demand prediction model based on the new energy station data at the above-mentioned historical moment;

[0116] The demand forecasting calculation module is used to calculate the energy demand forecast value at the current moment according to the energy demand forecasting model and the new energy station data at the current moment;

[0117] The energy allocation level function determination module is used to compare the energy demand prediction value with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand prediction value;

[0118] The energy allocation calculation module is used to calculate the energy allocation value according to the energy allocation level function and the energy demand forecast value.

[0119] It should be noted that the device embodiments described above are merely schematic, wherein the modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. Ordinary technicians in this field can understand and implement it without creative work. The above schematic diagram is only an example of a device for multi-level collaborative energy distribution in a new energy station, and does not constitute a limitation on the device for multi-level collaborative energy distribution in a new energy station, and may include more or fewer components than shown in the figure, or a combination of certain components, or different components.

[0120] Based on the above method item embodiments, the present invention provides corresponding terminal device item embodiments.

[0121] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the multi-level collaborative energy distribution method for new energy stations described in any embodiment of the present invention is implemented.

[0122] Exemplarily, in this embodiment, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more module elements may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the device;

[0123] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The device may include, but is not limited to, a processor, a memory;

[0124] The processor referred to herein may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The above-mentioned processor is the control center of the above-mentioned device, and uses various interfaces and lines to connect various parts of the entire device;

[0125] The above-mentioned memory can be used to store the above-mentioned computer programs and / or modules. The above-mentioned processor realizes various functions of the above-mentioned device by running or executing the computer programs and / or modules stored in the above-mentioned memory, and calling the data stored in the memory. The above-mentioned memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; in addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0126] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.

[0127] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the multi-level collaborative energy distribution method for new energy stations described in any embodiment of the present invention.

[0128] In this embodiment, the storage medium is a computer-readable storage medium, the computer program includes computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0129] Compared with the prior art, by implementing the above-mentioned embodiments of the present invention, energy demand can be predicted according to the constantly changing real-time data, thereby achieving efficient energy distribution.

[0130] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A multi-level collaborative energy distribution method for a new energy station, characterized in that: include: Acquire the new energy station data of the new energy station to be tested at the historical moment and the new energy station data at the current moment; wherein the new energy station data includes: energy production data, energy consumption data, environmental weather data, equipment performance data and energy demand data; Constructing an energy demand prediction model based on the new energy station data at the historical moment; Calculate the energy demand forecast value at the current moment according to the energy demand forecast model and the new energy station data at the current moment; Comparing the energy demand prediction value with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand prediction value; An energy allocation value is calculated based on the energy allocation level function and the energy demand forecast value.

2. The multi-level collaborative energy distribution method for a new energy station according to claim 1, characterized in that: The energy demand prediction model is: In the formula, x i represents the data of the new energy station of type i, f i (x i ) represents the mixed Gaussian model function of the i-th type of new energy station data, m represents the total number of different Gaussian distributions of the i-th type of new energy station data, j represents the j-th Gaussian distribution of the i-th type of new energy station data, a ij represents the relative importance of the jth Gaussian distribution in the i-th type of new energy station data in the model, μ ij represents the mean of the jth Gaussian distribution in the i-th type of new energy station data, σ ij represents the standard deviation of the jth Gaussian distribution in the i-th type of new energy station data, g(x) represents the normalization function, σ g represents the standard deviation of the normalized function, x represents the data value input into the energy demand prediction model, P(x) represents the energy demand prediction value, n represents the number of data types of the new energy station data, and w i Represents the weight parameter of the i-th type of new energy station data.

3. The multi-level collaborative energy distribution method for a new energy station according to claim 2 is characterized in that: The comparing the energy demand prediction value with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand prediction value includes: Comparing the energy demand forecast value with each preset energy allocation threshold; According to the comparison results, the energy allocation level function corresponding to the energy demand forecast value is determined by the following formula: In the formula, h q (P) represents the allocation strategy function of the qth level, A q represents the maximum amplitude parameter of the control allocation strategy function at the qth level, k q represents the adjustment parameter of the qth level, B q represents the parameter for determining the baseline energy allocation of the qth level, P represents the predicted energy demand, and λ q represents the energy allocation threshold of the qth level, and H(P, λ) represents the energy allocation level function.

4. The multi-level collaborative energy distribution method for a new energy station according to claim 3 is characterized in that: The energy allocation value is calculated according to the following formula: Where S(P) represents the energy allocation value, σ represents the standard deviation of the energy demand forecast value, and μ represents the mean of the energy demand forecast value.

5. The multi-level collaborative energy distribution method for a new energy station according to claim 4 is characterized in that: Also includes: Get the actual energy distribution data at the current moment; Calculating a prediction deviation according to an absolute value of a difference between the actual energy allocation data and the energy allocation value; The predicted deviation is compared with each preset deviation threshold to obtain the fault degree of the current new energy station.

6. The multi-level collaborative energy distribution method for a new energy station according to claim 5, characterized in that: Also includes: According to the predicted deviation and the preset deviation threshold, the fault assessment function value at the current moment is calculated; Calculate the energy demand and consumption evaluation relationship function value at the current moment according to the energy demand data at the current moment and the energy consumption data at the current moment; The environmental impact assessment function value at the current moment is calculated based on the energy demand and consumption assessment relationship function value and the fault assessment function value.

7. The multi-level collaborative energy distribution method for a new energy station according to claim 6, characterized in that: Also includes: Comparing the environmental impact assessment function value with each preset environmental impact threshold value to determine the environmental impact level under the current energy allocation value; According to the environmental impact level, the parameters in the energy allocation level function are adjusted.

8. A multi-level collaborative energy distribution device for a new energy station, characterized in that: include: New energy station data acquisition module, prediction model building module, demand prediction calculation module, energy allocation level function determination module and energy allocation calculation module; The new energy station data acquisition module is used to acquire the new energy station data of the new energy station to be tested at the historical moment and the new energy station data at the current moment; wherein the new energy station data includes: energy production data, energy consumption data, environmental weather data, equipment performance data and energy demand data; The prediction model building module is used to build an energy demand prediction model based on the new energy station data at the historical moment; The demand forecasting calculation module is used to calculate the energy demand forecast value at the current moment according to the energy demand forecasting model and the new energy station data at the current moment; The energy allocation level function determination module is used to compare the energy demand prediction value with each preset energy allocation threshold value to determine the energy allocation level function corresponding to the energy demand prediction value; The energy allocation calculation module is used to calculate the energy allocation value according to the energy allocation level function and the energy demand forecast value.

9. A terminal device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the multi-level collaborative energy distribution method for a new energy station as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the multi-level collaborative energy distribution method for a new energy station as described in any one of claims 1 to 7.

Images