A multi-energy coordinated power management system

Abstract

The present invention discloses a multi-energy collaborative power management system, which specifically relates to the field of power management technology. By obtaining the scheduling response information when the backup power management system schedules the energy equipment, and obtaining the equipment scheduling response delay rising coefficient, obtaining the data communication loss information when the backup power management system communicates data with the energy equipment, and obtaining the data communication loss abnormality coefficient, a coupling decline trend hidden danger analysis model is generated, a coupling decline trend hidden danger index is generated, and the decline trend hidden danger of the coupling between the backup power management system and the energy equipment is intelligently perceived, the coupling problem is identified early, and the correlation coefficient between the decline trend hidden danger signal generation ratio and the importance of the energy equipment is obtained. From an overall perspective, the decline trend hidden danger of the coupling between the backup power management system and the energy equipment is classified into different degrees of early warning, the response capability and post-disaster recovery efficiency are improved, and the efficient and reliable operation of the multi-energy collaborative system is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of power management, and more specifically, to a multi-energy coordinated power management system. Background Art

[0002] A multi-energy synergistic power management system typically integrates and optimizes multiple energy sources (such as wind, solar, and energy storage) to achieve efficient and reliable energy management and supply. The goal of this system is to improve energy efficiency, reduce operating costs, and enhance system flexibility and reliability through multi-energy complementarity and coordinated control.

[0003] While the existing multi-energy collaborative power management system is becoming increasingly technologically mature, it faces numerous challenges in remote areas, particularly due to the lag in infrastructure funding compared to developed urban areas, which results in incomplete coverage of power and communication networks. This lack of coverage directly impacts the system's ability to respond to and recover from natural disasters, particularly due to the potential for a declining coupling between the backup power management system and basic energy equipment. In this case, the system may not be able to effectively coordinate the operation of different energy devices, reducing overall recovery efficiency. Furthermore, existing monitoring methods lack the ability to capture and analyze subtle manifestations of declining trends, resulting in potential risks not being identified in a timely manner, exacerbating delays in post-disaster reconstruction and even leading to the risk of secondary damage. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a multi-energy coordinated power management system to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A multi-energy collaborative power management system, including an equipment dispatch response module, a data communication loss module, a model building module, a trend hidden danger generation module, and an early warning classification module;

[0007] The equipment dispatch response module is used to obtain the dispatch response information when the backup power management system dispatches the energy equipment, and obtain the equipment dispatch response delay rise coefficient based on the dispatch response information;

[0008] A data communication loss module is used to obtain data communication loss information when the backup power management system communicates with the energy equipment, and obtain a data communication loss abnormality coefficient based on the data communication loss information;

[0009] A model building module is used to construct a coupling decline trend hidden danger analysis model based on the equipment scheduling response delay increase coefficient and the data communication loss abnormality coefficient, conduct a comprehensive analysis of the coupling decline trend hidden danger between the backup power management system and energy equipment, and generate a coupling decline trend hidden danger index;

[0010] A trend hidden danger generating module is used to compare the coupling decreasing trend hidden danger index with a preset coupling decreasing trend hidden danger index threshold to determine whether there is a decreasing trend hidden danger in the coupling between the backup power management system and the current energy equipment;

[0011] The early warning classification module is used to classify the hidden dangers of the downward trend in the coupling between the backup power management system and the current energy equipment, combined with the importance information of the energy equipment, when there is a hidden danger of the downward trend in the coupling between the backup power management system and the current energy equipment.

[0012] In a preferred embodiment, by obtaining the dispatch response information when the backup power management system dispatches the energy equipment, analyzing the dispatch response between the backup power management system and the energy equipment, and obtaining the equipment dispatch response delay increase coefficient, the degree of increase in the dispatch response delay between the backup power management system and the energy equipment is measured;

[0013] The logic for obtaining the device scheduling response delay increase coefficient is as follows:

[0014] Each time the backup power management system dispatches the energy equipment, the time tc when the backup power management system sends the dispatch instruction and the time ts when the energy equipment executes the dispatch instruction are obtained, and the dispatch response value dxy is calculated. The expression is as follows: dxy = ts - tc; a dispatch response value data analysis set is constructed and marked as DXY = {dxy i}={dxy1,dxy2,...,dxy I}, where dxy i represents the dispatch response value calculated by the backup power management system when dispatching the energy equipment for the i-th time, i={1,2,...,I}, where I is a positive integer;

[0015] Calculating average dispatch response time The expression is as follows

[0016] Calculate the standard deviation dxyσ of the scheduling response time, as follows

[0017] Calculate the scheduling response time deviation coefficient cv, the expression is as follows

[0018] Calculate the scheduling response time abnormality coefficient Zdxy i , the expression is as follows

[0019] Calculate the trend coefficient qs, the expression is as follows where tc i Indicates the time when the backup power management system sends the scheduling instruction for the i-th time, is the average value of the time when the backup power management system sends the scheduling instruction, and the expression is as follows

[0020] Calculate the device scheduling response delay rise coefficient Sbxy, which is expressed as follows Wherein max(0,qs) is the maximum value acquisition function. If qs≤0, max(0,qs) takes the value of 0. If qs>0, max(0,qs) takes the value of qs. a1, a2, and a3 represent preset proportional coefficients, and a1, a2, and a3 are all greater than 0.

[0021] In a preferred embodiment, by acquiring data communication loss information when the backup power management system communicates with the energy device, analyzing the data communication loss between the backup power management system and the energy device, and obtaining a data communication loss abnormality coefficient, the degree of abnormality of the data communication loss between the backup power management system and the energy device is measured;

[0022] The logic for obtaining the data communication loss anomaly coefficient is as follows:

[0023] When the backup power management system communicates data with the energy equipment, multiple monitoring cycles are preset and the data packet loss rate in different monitoring cycles is calculated. The calculation expression is as follows Among them dsl t represents the packet loss rate in the t-th monitoring period, s1 represents the number of data packets lost when the backup power management system communicates with the energy equipment in the t-th monitoring period, s2 represents the total number of data packets when the backup power management system communicates with the energy equipment in the t-th monitoring period, t={1,2,...,T}, T is a positive integer;

[0024] Calculate the exponentially weighted moving average of the packet loss rate. The calculation expression is as follows: t+1 =α*dsl t+1 +(1-α)*Eds t , of which Eds t represents the exponentially weighted moving average of the packet loss rate in the tth monitoring period, α represents the preset smoothing factor, dsl t+1 represents the packet loss rate of the t+1th monitoring period, Eds t+1represents the exponentially weighted moving average of the packet loss rate in the t+1th monitoring period;

[0025] The packet loss rate and the exponentially weighted moving average of the packet loss rate in different monitoring periods are used as a set of feature data. The Euclidean distance between the feature data in the t-th monitoring period and the feature data in the remaining j-th monitoring periods is calculated. The calculation expression is as follows: where d t,j It represents the Euclidean distance between the feature data of the t-th monitoring period and the remaining j-th monitoring period, dsl t represents the packet loss rate in the tth monitoring period, Eds t represents the exponentially weighted moving average of the packet loss rate in the tth monitoring period, dsl j represents the packet loss rate in the remaining j-th monitoring period, Eds j represents the exponentially weighted moving average of the packet loss rate in the remaining j-th monitoring period, j = {1, 2, ..., T-1};

[0026] Compare the Euclidean distance between the feature data of the t-th monitoring period and the remaining j-th monitoring period with the preset distance threshold. When the Euclidean distance between the feature data of the t-th monitoring period and the remaining j-th monitoring period is less than the distance threshold, add the corresponding j-th monitoring period to the neighbor set of the t-th monitoring period. Calculate the local density, the expression is as follows where ld t represents the local density of the t-th monitoring period, ZS t represents the cumulative Euclidean distance within the neighbor set corresponding to the t-th monitoring period;

[0027] Calculate the packet loss outlier value LOF of the tth monitoring cycle t , the expression is as follows where ld k represents the local density of the kth monitoring period in the neighbor set corresponding to the tth monitoring period, k = {1, 2, ..., K}, K is a positive integer;

[0028] The data packet loss anomaly values ​​of T monitoring cycles are compared with the preset anomaly threshold respectively, and the data packet loss anomaly values ​​greater than the anomaly threshold are accumulated and calculated to obtain the data communication loss anomaly coefficient Sjtc.

[0029] In a preferred embodiment, a coupling downtrend hidden danger analysis model is constructed based on the device scheduling response delay increase coefficient and the data communication loss abnormality coefficient to generate a coupling downtrend hidden danger index Ohxz. The model is based on the following formula: Where b1 and b2 represent the preset proportional coefficients of the device scheduling response delay increase coefficient and the data communication loss abnormality coefficient, respectively, and both b1 and b2 are greater than 0.

[0030] In a preferred embodiment, if the coupling downtrend hidden danger index is greater than the coupling downtrend hidden danger index threshold, a coupling downtrend hidden danger signal is generated;

[0031] If the coupling downward trend hidden danger index is less than or equal to the coupling downward trend hidden danger index threshold, there is no need to generate a coupling downward trend hidden danger signal.

[0032] In a preferred embodiment, the number of times V1 of coupling downward trend hidden danger signal generation is obtained, and the downward trend hidden danger signal generation ratio Yhbl is calculated, which is expressed as follows: Where V2 represents the total number of energy devices.

[0033] In a preferred embodiment, the energy equipment importance information includes an energy equipment importance correlation coefficient;

[0034] The logic for obtaining the correlation coefficient of energy equipment importance is as follows:

[0035] Obtain relevant assessment data of energy equipment including operating status data, environmental data, load data, energy consumption data, and fault data;

[0036] Calculate the energy equipment correlation coefficient xgx between the target energy equipment and the remaining energy equipment. The expression is as follows where X n represents the nth correlation evaluation data of the target energy device, X represents the average value of the correlation evaluation data of the target energy device, and Y m,n represents the nth correlation evaluation data of the remaining mth energy device, represents the average value of the correlation evaluation data of the remaining m-th energy equipment, n={1,2,...,N}, N is a positive integer;

[0037] Calculate the correlation coefficient Nysb of the importance of energy equipment, the expression is as follows where xgx h,m represents the energy equipment correlation coefficient between the h-th target energy equipment and the remaining m-th energy equipment, represents the preset energy equipment correlation coefficient threshold, h={1,2,...,H}, H is a positive integer, and m={1,2,...,H-1}.

[0038] In a preferred embodiment, a coupled downward trend hidden danger warning classification model is constructed based on the downward trend hidden danger signal generation ratio and the energy equipment importance correlation coefficient, and a coupled downward trend hidden danger warning classification index Oyzf is generated. The model is based on the following formula Oyzf=ln(r1*Yhbl+r2*Nysb+1), where r1 and r2 represent the preset proportional coefficients of the downward trend hidden danger signal generation ratio and the energy equipment importance correlation coefficient, respectively, and r1 and r2 are both greater than 0.

[0039] In a preferred embodiment, the coupling downward trend hidden danger warning classification index is compared with a preset coupling downward trend hidden danger warning classification index threshold. If the coupling downward trend hidden danger warning classification index is greater than the coupling downward trend hidden danger warning classification index threshold, a first-level warning signal is generated; if the coupling downward trend hidden danger warning classification index is less than or equal to the coupling downward trend hidden danger warning classification index threshold, a second-level warning signal is generated.

[0040] Technical effects and advantages of the present invention:

[0041] 1. The present invention obtains the dispatch response information of the backup power management system when dispatching the energy equipment, obtains the equipment dispatch response delay rising coefficient, obtains the data communication loss information when the backup power management system communicates data with the energy equipment, and obtains the data communication loss abnormality coefficient, constructs a coupling decline trend hidden danger analysis model, generates a coupling decline trend hidden danger index, intelligently perceives the coupling decline trend hidden danger between the backup power management system and the energy equipment, identifies and solves the coupling problem early, reduces the equipment failure rate, reduces the maintenance and repair costs, and improves the energy utilization efficiency and post-disaster recovery capabilities as well as the energy management level in remote areas.

[0042] 2. The present invention obtains the correlation coefficient between the generation ratio of the downward trend hidden danger signal and the importance of the energy equipment from an overall perspective, constructs a coupling downward trend hidden danger warning classification model, generates a coupling downward trend hidden danger warning classification index, and classifies the coupling downward trend hidden dangers between the backup power management system and the energy equipment into different degrees of warning, thereby improving the response capability and post-disaster recovery efficiency, and promoting the efficient and reliable operation of the multi-energy collaborative system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0044] Figure 1 Schematic diagram of the structure of the system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0046] Embodiment: The present invention provides Figure 1 A multi-energy collaborative power management system shown includes an equipment scheduling response module, a data communication loss module, a model building module, a trend hidden danger generation module, and an early warning classification module;

[0047] The equipment dispatch response module is used to obtain the dispatch response information when the backup power management system dispatches the energy equipment, and obtain the equipment dispatch response delay rise coefficient based on the dispatch response information;

[0048] A data communication loss module is used to obtain data communication loss information when the backup power management system communicates with the energy equipment, and obtain a data communication loss abnormality coefficient based on the data communication loss information;

[0049] A model building module is used to construct a coupling decline trend hidden danger analysis model based on the equipment scheduling response delay increase coefficient and the data communication loss abnormality coefficient, conduct a comprehensive analysis of the coupling decline trend hidden danger between the backup power management system and energy equipment, and generate a coupling decline trend hidden danger index;

[0050] A trend hidden danger generating module is used to compare the coupling decreasing trend hidden danger index with a preset coupling decreasing trend hidden danger index threshold to determine whether there is a decreasing trend hidden danger in the coupling between the backup power management system and the current energy equipment;

[0051] An early warning classification module is used to classify the potential danger of a decreasing trend in the coupling between the backup power management system and the current energy equipment based on the importance information of the energy equipment when the potential danger of a decreasing trend in the coupling between the backup power management system and the current energy equipment exists;

[0052] The equipment dispatch response module is used to obtain the dispatch response information when the backup power management system dispatches the energy equipment, and obtain the equipment dispatch response delay rise coefficient based on the dispatch response information;

[0053] When the backup power management system dispatches energy equipment, if its dispatch response is delayed, it may cause the following effects:

[0054] Untimely response of energy equipment: Backup power systems are usually activated in emergency situations (such as after a disaster or equipment failure). If the dispatch response is delayed, energy equipment may not be able to start or adjust its operating status in time, resulting in the failure to supply emergency energy as expected, affecting the normal operation of key areas.

[0055] Reduced system reliability: Delayed dispatch responses may indicate problems with the system's communication or control links. This delay can affect the overall coordination and reliability of the system, especially in multi-energy scenarios where various energy devices must respond quickly and work together to ensure continuous and stable power supply.

[0056] Reduced energy efficiency: Delayed scheduling may prevent energy equipment from adjusting its operating mode to meet real-time demand, resulting in inefficient operation of energy equipment. For example, intermittent energy sources such as wind or solar power may experience significant reductions in energy efficiency after missing optimal timing.

[0057] Reduced coupling between the backup power system and equipment: Delayed dispatch responses indicate problems with the coordination between the backup power system and energy equipment, which can affect the system's ability to accurately monitor the status of energy equipment. In the long term, reduced coupling can lead to reduced operating efficiency and safety of the overall system.

[0058] Therefore, by obtaining the dispatch response information when the backup power management system dispatches the energy equipment, analyzing the dispatch response between the backup power management system and the energy equipment, and obtaining the equipment dispatch response delay increase coefficient, the degree of increase in the dispatch response delay between the backup power management system and the energy equipment is measured;

[0059] The logic for obtaining the device scheduling response delay increase coefficient is as follows:

[0060] Each time the backup power management system dispatches the energy equipment, the time tc when the backup power management system sends the dispatch instruction and the time ts when the energy equipment executes the dispatch instruction are obtained, and the dispatch response value dxy is calculated. The expression is as follows: dxy = ts - tc; a dispatch response value data analysis set is constructed and marked as DXY = {dxy i}={dxy1,dxy2,...,dxy I}, where dxy i represents the dispatch response value calculated by the backup power management system when dispatching the energy equipment for the i-th time, i={1,2,...,I}, where I is a positive integer;

[0061] Calculating average dispatch response time The expression is as follows

[0062] Calculate the standard deviation dxyσ of the scheduling response time, as follows

[0063] Calculate the scheduling response time deviation coefficient cv, the expression is as follows

[0064] The dispatch response time deviation coefficient is used to measure the relative volatility of the dispatch response time;

[0065] Calculate the scheduling response time abnormality coefficient Zdxy i , the expression is as follows

[0066] The scheduling response time anomaly coefficient is used to measure the impact of scheduling response time anomalies on the overall scheduling response;

[0067] Calculate the trend coefficient qs, the expression is as follows where tc i It represents the time when the backup power management system sends the scheduling instruction for the i-th time, and tc1 is the average time when the backup power management system sends the scheduling instruction. The expression is as follows

[0068] The trend coefficient is used to measure the changing trend of the energy equipment dispatch response time over time, and can be used to help identify the dispatch response delay when the backup power management system dispatches energy equipment;

[0069] Calculate the device scheduling response delay increase coefficient Sbxy, which is expressed as follows: Sbxy = a1*cv+a2* Where max(0,qs) is the maximum value acquisition function. If qs≤0, max(0,qs) takes the value of 0. If qs>0, max(0,qs) takes the value of qs. a1, a2, and a3 represent the preset proportional coefficients, and a1, a2, and a3 are all greater than 0.

[0070] It should be noted that a1, a2, and a3 are set according to actual conditions. For example, the expert empowerment method is adopted, that is, experts in relevant fields are invited to determine the preset proportional coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0071] The equipment dispatch response delay increase coefficient is used to measure the degree of increase in the dispatch response delay between the backup power management system and the energy equipment. When the equipment dispatch response delay increase coefficient is larger, it indicates that the degree of increase in the dispatch response delay between the backup power management system and the energy equipment is more serious, and the probability of the potential risk of a downward trend in the coupling between the backup power management system and the energy equipment is greater; conversely, when the equipment dispatch response delay increase coefficient is smaller, it indicates that the coupling between the backup power management system and the energy equipment is stronger, the dispatch response is more timely, the potential risk is lower, and the probability of the potential risk of a downward trend in the coupling between the backup power management system and the energy equipment is smaller;

[0072] A data communication loss module is used to obtain data communication loss information when the backup power management system communicates with the energy equipment, and obtain a data communication loss abnormality coefficient based on the data communication loss information;

[0073] When data is lost during communication between the backup power management system and energy equipment, the following effects may occur:

[0074] Lack of energy equipment status monitoring: Due to communication interruptions or data loss, the backup power management system cannot monitor the real-time status of energy equipment in a timely manner. This may result in energy equipment operating anomalies not being discovered in time, increasing the risk of system failure.

[0075] Reduced energy efficiency: When the system cannot obtain real-time load information or energy consumption data of energy equipment, it may lead to inaccurate or untimely backup power scheduling, resulting in unreasonable energy distribution, thereby reducing the energy utilization efficiency of the backup power system;

[0076] Increased system safety risks: Under high load or emergency conditions, if the backup power dispatch system cannot obtain real-time data from energy equipment, it may lead to unbalanced power load distribution, resulting in safety risks such as overload and power outage;

[0077] Reduced data consistency and control accuracy: Lost data may contain control instructions or energy device status information. This information loss will affect the system's precise control of energy devices, potentially leading to erroneous operation or status deviations, and thus affecting the coordination and accuracy of the entire system.

[0078] Therefore, by obtaining the data communication loss information when the backup power management system and the energy equipment communicate with each other, the data communication loss situation between the backup power management system and the energy equipment is analyzed, and the data communication loss abnormality coefficient is obtained to measure the abnormality degree of the data communication loss between the backup power management system and the energy equipment;

[0079] The logic for obtaining the data communication loss anomaly coefficient is as follows:

[0080] When the backup power management system communicates data with the energy equipment, multiple monitoring cycles are preset and the data packet loss rate in different monitoring cycles is calculated. The calculation expression is as follows where dsl t represents the packet loss rate in the t-th monitoring period, s1 represents the number of data packets lost when the backup power management system communicates with the energy equipment in the t-th monitoring period, s2 represents the total number of data packets when the backup power management system communicates with the energy equipment in the t-th monitoring period, t={1,2,...,T}, T is a positive integer;

[0081] Calculate the exponentially weighted moving average of the packet loss rate. The calculation expression is as follows: t+1 =α*dsl t+1 +(1-α)*Eds t , of which Eds t represents the exponentially weighted moving average of the packet loss rate in the tth monitoring period, α represents the preset smoothing factor, dsl t+1 represents the packet loss rate of the t+1th monitoring period, Eds t+1 represents the exponentially weighted moving average of the packet loss rate in the t+1th monitoring period;

[0082] It should be noted that the initial value of the exponentially weighted moving average of the packet loss rate is the packet loss rate of the first monitoring period, that is, when t=1, Eds1=dsl1, α represents a preset smoothing factor, and a reference value can be given by those skilled in the art with reference to the number of data packets for data communication between the backup power management system and the energy equipment;

[0083] The packet loss rate and the exponentially weighted moving average of the packet loss rate in different monitoring periods are used as a set of feature data. The Euclidean distance between the feature data in the t-th monitoring period and the feature data in the remaining j-th monitoring periods is calculated. The calculation expression is as follows: where d t,j It represents the Euclidean distance between the feature data of the t-th monitoring period and the remaining j-th monitoring period, dsl t represents the packet loss rate in the tth monitoring period, Eds t represents the exponentially weighted moving average of the packet loss rate in the tth monitoring period, dsl j represents the packet loss rate in the remaining j-th monitoring period, Eds j represents the exponentially weighted moving average of the packet loss rate in the remaining j-th monitoring period, j = {1, 2, ..., T-1};

[0084] Compare the Euclidean distance between the feature data of the t-th monitoring period and the remaining j-th monitoring period with the preset distance threshold. When the Euclidean distance between the feature data of the t-th monitoring period and the remaining j-th monitoring period is less than the distance threshold, add the corresponding j-th monitoring period to the neighbor set of the t-th monitoring period. Calculate the local density, the expression is as follows where ld t represents the local density of the t-th monitoring period, ZS t represents the cumulative Euclidean distance within the neighbor set corresponding to the t-th monitoring period;

[0085] Calculate the packet loss outlier value LOF of the tth monitoring cycle t , the expression is as follows where ld k represents the local density of the kth monitoring period in the neighbor set corresponding to the tth monitoring period, k = {1, 2, ..., K}, K is a positive integer;

[0086] The data packet loss anomaly values ​​of T monitoring cycles are compared with the preset anomaly threshold respectively, and the data packet loss anomaly values ​​greater than the anomaly threshold are accumulated and calculated to obtain the data communication loss anomaly coefficient Sjtc;

[0087] The data communication loss anomaly coefficient is used to measure the degree of data communication loss anomaly between the backup power management system and the energy equipment. When the data communication loss anomaly coefficient is larger, it indicates that the degree of data communication loss anomaly between the backup power management system and the energy equipment is more serious, and the probability of the potential risk of a downward trend in the coupling between the backup power management system and the energy equipment is greater; conversely, when the data communication loss anomaly coefficient is smaller, it indicates that the degree of data communication loss anomaly between the backup power management system and the energy equipment is smaller, indicating that the coupling between the backup power management system and the energy equipment is stronger, the data communication is more stable, the potential risk is lower, and the probability of the potential risk of a downward trend in the coupling between the backup power management system and the energy equipment is smaller;

[0088] A model building module is used to construct a coupling decline trend hidden danger analysis model based on the equipment scheduling response delay increase coefficient and the data communication loss abnormality coefficient, conduct a comprehensive analysis of the coupling decline trend hidden danger between the backup power management system and energy equipment, and generate a coupling decline trend hidden danger index;

[0089] Based on the equipment scheduling response delay increase coefficient and data communication loss anomaly coefficient, a coupling decline trend hidden danger analysis model is constructed to generate the coupling decline trend hidden danger index Ohxz. The model is based on the following formula: Where b1 and b2 represent the preset proportional coefficients of the device scheduling response delay increase coefficient and the data communication loss abnormality coefficient, respectively, and both b1 and b2 are greater than 0;

[0090] It should be noted that before building a coupling decline trend hazard analysis model, it is necessary to ensure that the equipment scheduling response delay increase coefficient and the data communication loss anomaly coefficient are normalized. Common normalization methods include Min-Max normalization and Z-Score standardization. b1 and b2 are set according to actual conditions. For example, the expert empowerment method can be adopted, that is, experts in related fields are invited to determine the preset proportional coefficients of various indicators through professional opinion surveys and comprehensive evaluations.

[0091] From the above calculation expression, it can be seen that the larger the equipment scheduling response delay increase coefficient and the larger the data communication loss anomaly coefficient, the larger the coupling downward trend hidden danger index, indicating that the probability of the coupling downward trend hidden danger between the backup power management system and the energy equipment is greater. Conversely, the smaller the equipment scheduling response delay increase coefficient and the smaller the data communication loss anomaly coefficient, the smaller the coupling downward trend hidden danger index, indicating that the coupling between the backup power management system and the energy equipment is strong, the potential risk is low, and the probability of the coupling downward trend hidden danger between the backup power management system and the energy equipment is smaller.

[0092] A trend hidden danger generating module is used to compare the coupling decreasing trend hidden danger index with a preset coupling decreasing trend hidden danger index threshold to determine whether there is a decreasing trend hidden danger in the coupling between the backup power management system and the current energy equipment;

[0093] If the coupling downtrend hidden danger index is greater than the coupling downtrend hidden danger index threshold, a coupling downtrend hidden danger signal is generated to indicate the coupling downtrend hidden danger between the backup power management system and the current energy equipment, so that operators can quickly identify it;

[0094] If the coupling downward trend hidden danger index is less than or equal to the coupling downward trend hidden danger index threshold, there is no need to generate a coupling downward trend hidden danger signal and no special intervention is required;

[0095] An early warning classification module is used to classify the potential danger of a decreasing trend in the coupling between the backup power management system and the current energy equipment based on the importance information of the energy equipment when the potential danger of a decreasing trend in the coupling between the backup power management system and the current energy equipment exists;

[0096] Get the number of times V1 of coupling downward trend hidden danger signal is generated, and calculate the generation ratio of downward trend hidden danger signal Yhbl. The expression is as follows Where V2 represents the total number of energy devices;

[0097] The proportion of downward trend hidden danger signals generated is used to measure the proportion of energy devices that generate coupling downward trend hidden danger signals to the total number of energy devices. The greater the proportion of downward trend hidden danger signals generated, the deeper the warning level of the downward trend hidden danger of coupling between the backup power management system and energy devices.

[0098] The energy equipment importance information includes the energy equipment importance correlation coefficient;

[0099] The energy equipment importance correlation coefficient is used to measure the correlation between the energy equipment that generates the coupling decline trend hidden danger signal and other energy equipment. For example, the output power reduction of the power generation equipment may cause the load energy equipment that relies on this power to not operate normally; the maintenance of a certain transformer may affect the operation of the generator connected to it. The larger the energy equipment importance correlation coefficient, the more important the energy equipment is. The greater the impact of the coupling decline trend between it and the backup power management system, the more serious the warning level.

[0100] The logic for obtaining the correlation coefficient of energy equipment importance is as follows:

[0101] Obtain relevant assessment data of energy equipment including operating status data, environmental data, load data, energy consumption data, and fault data;

[0102] It should be noted that the operating status data of energy equipment includes operating time, downtime, etc., environmental data includes temperature, humidity, air pressure, vibration, etc., load data includes load power, equipment utilization rate, etc., energy consumption data includes energy consumption, energy consumption cost, etc., and fault data includes fault frequency, repair time, etc.;

[0103] Calculate the energy equipment correlation coefficient xgx between the target energy equipment and the remaining energy equipment. The expression is as follows where X n represents the nth correlation evaluation data of the target energy equipment, represents the average value of the correlation evaluation data of the target energy equipment, Y m,n represents the nth correlation evaluation data of the remaining mth energy device, represents the average value of the correlation evaluation data of the remaining m-th energy equipment, n={1,2,...,N}, N is a positive integer;

[0104] It should be noted that the target energy device refers to any energy device among all energy devices, and the remaining energy devices refer to other energy devices except the target energy device. Before calculating the energy device correlation coefficient, it is necessary to ensure that the correlation evaluation data are normalized;

[0105] Calculate the correlation coefficient Nysb of the importance of energy equipment, the expression is as follows where xgx h,m represents the energy equipment correlation coefficient between the h-th target energy equipment and the remaining m-th energy equipment, represents the preset energy equipment correlation coefficient threshold, h={1,2,...,H}, H is a positive integer, m={1,2,...,H-1};

[0106] A coupled downward trend hidden danger warning classification model is constructed based on the generation ratio of downward trend hidden danger signals and the correlation coefficient of the importance of energy equipment, and a coupled downward trend hidden danger warning classification index Oyzf is generated. The model is based on the following formula: Oyzf = ln(r1*Yhbl+r2*Nysb+1), where r1 and r2 represent the preset proportional coefficients of the generation ratio of downward trend hidden danger signals and the correlation coefficient of the importance of energy equipment, respectively, and both r1 and r2 are greater than 0.

[0107] It should be noted that before constructing the coupled downward trend hidden danger early warning classification model, it is necessary to ensure that the downward trend hidden danger signal generation ratio and the energy equipment importance correlation coefficient are normalized. Common normalization methods include Min-Max normalization and Z-Score standardization. b1 and b2 are set according to actual conditions. For example, the expert empowerment method can be adopted, that is, experts in related fields are invited to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations.

[0108] From the above calculation expression, it can be seen that the greater the proportion of downward trend hidden danger signal generation and the greater the correlation coefficient of energy equipment importance, the greater the coupling downward trend hidden danger warning classification index, indicating that the overall downward trend hidden danger of the coupling between the backup power management system and the energy equipment is more serious and the degree of early warning intervention is deeper. Conversely, the smaller the proportion of downward trend hidden danger signal generation and the smaller the correlation coefficient of energy equipment importance, the smaller the coupling downward trend hidden danger warning classification index, indicating that the overall downward trend hidden danger of the coupling between the backup power management system and the energy equipment is relatively gentle and the degree of early warning intervention can be appropriately reduced.

[0109] Compare the coupling downward trend hidden danger warning classification index with the preset coupling downward trend hidden danger warning classification index threshold. If the coupling downward trend hidden danger warning classification index is greater than the coupling downward trend hidden danger warning classification index threshold, a first-level warning signal is generated, indicating that many energy devices have potential coupling problems, and the situation is relatively serious and requires urgent treatment; if the coupling downward trend hidden danger warning classification index is less than or equal to the coupling downward trend hidden danger warning classification index threshold, a second-level warning signal is generated, indicating that the current coupling problem is still within an acceptable range, but vigilance and strengthened monitoring are still required;

[0110] It should be noted that the level of early warning intervention for a Level 1 early warning signal is deeper than that for a Level 2 early warning signal;

[0111] The present invention obtains the dispatch response information of the backup power management system when dispatching the energy equipment, obtains the equipment dispatch response delay rising coefficient, obtains the data communication loss information when the backup power management system communicates data with the energy equipment, and obtains the data communication loss abnormality coefficient, constructs a coupling decline trend hidden danger analysis model, generates a coupling decline trend hidden danger index, intelligently perceives the coupling decline trend hidden danger between the backup power management system and the energy equipment, identifies and solves the coupling problem early, reduces the equipment failure rate, reduces the maintenance and repair costs, and improves the energy utilization efficiency and post-disaster recovery capabilities as well as the energy management level in remote areas.

[0112] The present invention obtains the correlation coefficient between the generation ratio of downward trend hidden danger signals and the importance of energy equipment from an overall perspective, constructs a coupling downward trend hidden danger warning classification model, generates a coupling downward trend hidden danger warning classification index, and classifies the coupling downward trend hidden dangers between the backup power management system and energy equipment into different degrees of warning, thereby improving the response capability and post-disaster recovery efficiency, and promoting the efficient and reliable operation of the multi-energy collaborative system.

[0113] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0114] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0115] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0116] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0117] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A multi-energy coordinated power management system, characterized by: It includes equipment dispatch response module, data communication loss module, model building module, trend hidden danger generation module, and early warning classification module; The equipment dispatch response module is used to obtain the dispatch response information when the backup power management system dispatches the energy equipment, analyze the dispatch response between the backup power management system and the energy equipment, and obtain the equipment dispatch response delay increase coefficient to measure the degree of increase in the dispatch response delay between the backup power management system and the energy equipment; The data communication loss module is used to obtain data communication loss information when the backup power management system communicates with the energy equipment, analyze the data communication loss between the backup power management system and the energy equipment, and obtain the data communication loss abnormality coefficient to measure the degree of abnormality of the data communication loss between the backup power management system and the energy equipment; A model building module is used to construct a coupling decline trend hidden danger analysis model based on the equipment scheduling response delay increase coefficient and the data communication loss abnormality coefficient, conduct a comprehensive analysis of the coupling decline trend hidden danger between the backup power management system and energy equipment, and generate a coupling decline trend hidden danger index; A trend hidden danger generating module is used to compare the coupling decreasing trend hidden danger index with a preset coupling decreasing trend hidden danger index threshold to determine whether there is a decreasing trend hidden danger in the coupling between the backup power management system and the current energy equipment; An early warning classification module is used to classify the potential danger of a decreasing trend in the coupling between the backup power management system and the current energy equipment based on the importance information of the energy equipment when the potential danger of a decreasing trend in the coupling between the backup power management system and the current energy equipment exists; According to the equipment scheduling response delay increase coefficient and data communication loss anomaly coefficient, a coupling decline trend hidden danger analysis model is constructed to generate a coupling decline trend hidden danger index. The model is based on the following formula , where is the device scheduling response delay rise coefficient, is the data communication loss anomaly coefficient, They represent the preset proportional coefficients of the equipment scheduling response delay increase coefficient and the data communication loss abnormality coefficient, respectively, and Both are greater than 0.

2. The multi-energy coordinated power management system according to claim 1, characterized in that: By obtaining the dispatch response information of the backup power management system when dispatching energy equipment; The logic for obtaining the device scheduling response delay increase coefficient is as follows: Each time the backup power management system dispatches energy equipment, obtain the time when the backup power management system sends the dispatch instruction and the time when energy equipment executes scheduling instructions , calculate the dispatch response value , the expression is as follows ; Construct a scheduling response value data analysis set and mark the scheduling response value data analysis set as ,in It represents the dispatch response value calculated by the backup power management system when dispatching the energy equipment for the i-th time, i={1,2,..., }, is a positive integer; Calculating average dispatch response time , the expression is as follows ; Calculate the standard deviation of dispatch response time , the expression is as follows ; Calculate the scheduling response time deviation coefficient , the expression is as follows ; Calculate the abnormal coefficient of scheduling response time , the expression is as follows ; Calculating the trend coefficient , the expression is as follows ,in Indicates the time when the backup power management system sends the scheduling instruction for the i-th time, is the average value of the time when the backup power management system sends the scheduling instruction, and the expression is as follows ; Computing device scheduling response delay increase coefficient , the expression is as follows ,in is the maximum value obtaining function, if ,but The value is 0, if ,but The value is , represents the preset scaling factor, and Both are greater than 0.

3. The multi-energy coordinated power management system according to claim 1, characterized in that: By obtaining data communication loss information when the backup power management system communicates with the energy equipment; The logic for obtaining the data communication loss anomaly coefficient is as follows: When the backup power management system communicates data with the energy equipment, multiple monitoring cycles are preset and the data packet loss rate in different monitoring cycles is calculated. The calculation expression is as follows ,in represents the packet loss rate in the tth monitoring period, It represents the number of data packets lost during data communication between the backup power management system and the energy equipment in the tth monitoring cycle. represents the total number of data packets during data communication between the backup power management system and the energy equipment in the t-th monitoring period, t={1,2,...,T}, where T is a positive integer; Calculate the exponentially weighted moving average of the packet loss rate. The calculation expression is as follows ,in represents the exponentially weighted moving average of the packet loss rate in the tth monitoring period, represents the preset smoothing factor, represents the packet loss rate of the t+1th monitoring period, represents the exponentially weighted moving average of the packet loss rate in the t+1th monitoring period; The packet loss rate and the exponentially weighted moving average of the packet loss rate in different monitoring periods are used as a set of feature data. The Euclidean distance between the feature data in the t-th monitoring period and the feature data in the remaining j-th monitoring periods is calculated. The calculation expression is as follows: ,in represents the Euclidean distance between the feature data of the t-th monitoring period and the remaining j-th monitoring periods, represents the packet loss rate in the tth monitoring period, represents the exponentially weighted moving average of the packet loss rate in the tth monitoring period, represents the packet loss rate in the remaining j-th monitoring period, represents the exponentially weighted moving average of the packet loss rate in the remaining j-th monitoring period, j={1,2,...,T-1}; Compare the Euclidean distance between the feature data of the t-th monitoring period and the remaining j-th monitoring period with a preset distance threshold. When the Euclidean distance between the feature data of the t-th monitoring period and the remaining j-th monitoring period is less than the distance threshold, add the corresponding j-th monitoring period to the neighbor set of the t-th monitoring period. Calculate the local density, the expression is as follows ,in represents the local density of the t-th monitoring period, represents the cumulative Euclidean distance within the neighbor set corresponding to the t-th monitoring period; Calculate the packet loss anomaly value of the tth monitoring period , the expression is as follows ,in represents the local density of the kth monitoring period in the neighbor set corresponding to the tth monitoring period, k={1,2,...,K}, K is a positive integer; Compare the data packet loss anomaly values ​​of T monitoring cycles with the preset anomaly threshold, and accumulate the data packet loss anomaly values ​​greater than the anomaly threshold to obtain the data communication loss anomaly coefficient .

4. The multi-energy coordinated power management system according to claim 1, characterized in that: If the coupling downward trend hidden danger index is greater than the coupling downward trend hidden danger index threshold, a coupling downward trend hidden danger signal is generated; If the coupling downward trend hidden danger index is less than or equal to the coupling downward trend hidden danger index threshold, there is no need to generate a coupling downward trend hidden danger signal.

5. The multi-energy coordinated power management system according to claim 4, characterized in that: Get the number of times the coupling downtrend hidden danger signal is generated , calculate the proportion of downward trend hidden danger signal generation , the expression is as follows ,in Indicates the total number of energy devices.

6. The multi-energy coordinated power management system according to claim 1, characterized in that: The energy equipment importance information includes the energy equipment importance correlation coefficient; The logic for obtaining the correlation coefficient of energy equipment importance is as follows: Obtain relevant assessment data of energy equipment including operating status data, environmental data, load data, energy consumption data, and fault data; Calculate the energy equipment correlation coefficient between the target energy equipment and the remaining energy equipment , the expression is as follows ,in represents the nth correlation evaluation data of the target energy equipment, Indicates the average value of the correlation evaluation data of the target energy equipment, represents the nth correlation evaluation data of the remaining mth energy device, represents the average value of the correlation evaluation data of the remaining m-th energy equipment, n={1,2,...,N}, N is a positive integer; Calculate the correlation coefficient of energy equipment importance , the expression is as follows ,in represents the energy equipment correlation coefficient between the h-th target energy equipment and the remaining m-th energy equipment, Represents the preset energy equipment correlation coefficient threshold, h={1,2,...,H}, H is a positive integer, and m={1,2,...,H-1}.

7. The multi-energy coordinated power management system according to claim 6, characterized in that: According to the generation ratio of downward trend hidden danger signals and the correlation coefficient of energy equipment importance, a coupling downward trend hidden danger warning classification model is constructed to generate a coupling downward trend hidden danger warning classification index. The model is based on the following formula , where The preset proportional coefficients respectively represent the generation ratio of downward trend hidden danger signals and the correlation coefficient of the importance of energy equipment, and Both are greater than 0.

8. The multi-energy coordinated power management system according to claim 7, characterized in that: Comparing the coupling downward trend hidden danger warning classification index with a preset coupling downward trend hidden danger warning classification index threshold, if the coupling downward trend hidden danger warning classification index is greater than the coupling downward trend hidden danger warning classification index threshold, generating a first-level warning signal; If the coupling downward trend hidden danger warning classification index is less than or equal to the coupling downward trend hidden danger warning classification index threshold, a secondary warning signal is generated.

Images