A method and system for power grid security risk management based on data analysis

Abstract

The present invention discloses a method and system for controlling power grid security risks based on data analysis, and relates to the technical field of power grid risk prediction. The system uses sensors to monitor water quality, temperature, dissolved oxygen and flow rate indicators in real time through an environmental monitoring module to establish an environmental impact data set. If the environmental condition index Pn is lower than the first condition threshold, a first control instruction is sent to the outside; through the introduction of the real-time index Dwfh of the power grid load and the sub-region comprehensive load coefficient Zhfz, effective early warning and management of power security risks are achieved. When the sub-region comprehensive load coefficient Zhfz exceeds the preset load threshold, the system will issue an alarm and trigger the corresponding emergency plan, and trigger a multi-level evaluation strategy. Through the power grid risk prediction model, it can quickly respond and evaluate the energy fluctuation of key equipment such as water pumps, oxygenation equipment and heaters, and promptly detect abnormalities and take corresponding measures, such as optimizing the start-stop sequence, adjusting operating parameters, etc., to reduce equipment loss and improve efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid risk prediction, and in particular to a power grid security risk management and control method and system based on data analysis. Background Art

[0002] Traditional technologies face many challenges and shortcomings in the management of power networks in fish ponds. As a complex ecosystem, fish ponds rely on a stable and reliable power supply to maintain water quality, control water temperature and provide sufficient oxygen. However, traditional management methods often fail to effectively address the following key issues:

[0003] First, traditional fish pond management often lacks refined regional division and power grid design. Traditional practices often regard the entire fish pond as a whole, without detailed regional division and precise layout of power equipment. In addition, traditional load forecasting and risk assessment methods lack scientificity and accuracy. In traditional practices, load forecasting for key power equipment such as water pumps, heaters and aeration equipment mainly relies on empirical judgment or simple statistical methods. This method cannot fully consider the impact of different environmental conditions and seasonal changes on equipment load, resulting in low prediction accuracy and unstable results. The response to equipment abnormalities, load overloads or environmental abnormalities is often passive and delayed, and there is a lack of timely early warning mechanisms and emergency response plans, which brings potential risks to the stable operation of power and biological health of fish ponds. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a power grid security risk management method and system based on data analysis to solve the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a power grid security risk management method based on data analysis, comprising:

[0006] S1. Divide several fish ponds into several sub-areas, install isolation devices between sub-areas and adjacent sub-areas, build a sub-grid for each sub-area, and install corresponding power equipment;

[0007] S2. Setting monitoring points in each sub-area and deploying sensors at the monitoring points to monitor the fish pond operating environment in the sub-area in real time and establish an environmental impact data set; and extracting features from the relevant data information in the environmental impact data set to construct an environmental condition index Pn. If the environmental condition index Pn is lower than the first condition threshold, a first control instruction is sent to the outside.

[0008] S3. After receiving the first control instruction, start the power equipment in the sub-grid in the current sub-region; and collect and monitor the drop and surge mutation data, pressure change data and flow fluctuation data of each sub-grid power equipment before and after startup in real time to establish a load data set;

[0009] S4. Using the power grid risk prediction model trained by the time series model ARIMA or the deep learning model Transformer, the load data set is preprocessed and analyzed and calculated to obtain: the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy, the heater energy fluctuation index Njy and the power grid load real-time index Dwfh; and the environmental condition index Pn and the power grid load real-time index Dwfh are associated to obtain the sub-area comprehensive load coefficient Zhfz. When the sub-area comprehensive load coefficient Zhfz exceeds the preset load threshold, a second warning instruction is sent;

[0010] S5. After receiving the second warning instruction, the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy and the heater energy fluctuation index Njy are evaluated respectively, and after obtaining the corresponding evaluation results, the corresponding control strategy is generated.

[0011] Preferably, S1 comprises:

[0012] S11, dividing the fish ponds into several sub-areas at equal intervals according to their areas and shapes, and locating the sub-area boundaries using GPS technology or measurement tools;

[0013] S12. Use AutoCAD drawing software to draw a sub-area map and mark each sub-area on the sub-area map, specifically marking as: Zq1, Zq2, Zq3, ..., Zq n , n represents the number of sub-regions, and the fish pond area is marked in each sub-region;

[0014] S13. Install isolation devices between each sub-area and adjacent sub-areas according to the sub-area map;

[0015] S14. Establish a sub-grid in each sub-area, the sub-grid including: cables, switches, lightning protection devices, leakage protection devices, power control boxes and transformers;

[0016] And install corresponding electrical equipment, which includes: water pump, oxygenation equipment, lighting equipment, heater and water quality monitoring equipment.

[0017] Preferably, a monitoring point is set in each sub-area, and sensors are deployed in the monitoring point to monitor the operating environment of the fish pond in the sub-area in real time and establish an environmental impact data set;

[0018] The environmental impact dataset includes, but is not limited to, the following data: water temperature Swd, water depth Ss, dissolved oxygen saturation ratio Rjy, water body pH value pH, suspended solid concentration Xfw, and water flow velocity Slsd;

[0019] The water temperature Swd is obtained by measuring with a water temperature sensor; the water depth Ss is obtained by measuring with an ultrasonic sensor; the dissolved oxygen saturation ratio Rjy is obtained by measuring with a dissolved oxygen saturation ratio sensor; the water body pH value pH is obtained by measuring with a pH sensor; the suspended solid concentration Xfw is obtained by measuring with a turbidity sensor; the water flow velocity Slsd is obtained by measuring with a water flow velocity sensor.

[0020] Preferably, the environmental condition index Pn is obtained by extracting the water temperature Swd, water depth Ss, dissolved oxygen saturation ratio Rjy, water body pH value pH, suspended solid concentration Xfw, and water flow velocity Slsd from the environmental impact dataset, and after dimensionless processing, generating the environmental condition index Pn through the following formula:

[0021]

[0022] In the formula, represents the preset standard water temperature threshold of the fishpond, represents the preset water depth threshold of the fishpond, represents the preset standard threshold of the dissolved oxygen saturation ratio, represents the preset standard threshold of the water body pH value, represents the preset maximum tolerance threshold of suspended solids, represents the preset standard threshold of the water flow velocity, w1, w2, w3, w4, w5, and w6 represent weight values, and 0 < w1 < 1, 0 < w2 < 1, 0 < w3 < 1, 0 < w4 < 1, 0 < w5 < 1, 0 < w6 < 1, and their specific values are adjusted and set by the user, w1 + w2 + w3 + w4 + w5 + w6 = 1; C1 represents the first correction constant;

[0023] When the environmental condition index Pn < the first condition threshold, it indicates that the environment of the current sub-region is abnormal, generating a first regulation instruction to trigger the start of the water pump, aeration equipment, and heater. When the environmental condition index Pn ≥ the first condition threshold, it indicates that the environment of the current sub-region is normal and there is no need to trigger a regulation instruction.

[0024] Preferably, the start-up before and after drop, surge mutation data, pressure change data, and flow fluctuation data of each sub-grid power equipment are collected and monitored in real time to establish a load dataset;

[0025] The data of voltage dips and surge mutations before and after the start of the power equipment include: the start-stop frequency Qtpl1 of the water pump, the start-stop time interval T1 of the water pump, the start-stop frequency Qtpl2 of the aeration equipment, the start-stop time interval T2 of the aeration equipment, the start-stop frequency Qtpl3 of the heater, the start-stop time interval T3 of the heater, the starting current QdI1 of the water pump, the starting current QdI2 of the aeration equipment, and the starting current QdI3 of the heating equipment;

[0026] The pressure change data include: the pressure ylz1 in the pump chamber, the differential value bycz1 of the back pressure change in the pump chamber; the pressure ylz2 in the chamber of the aeration equipment, the differential value bycz2 of the back pressure change in the aeration equipment;

[0027] The flow fluctuation data include: the water output flow csll1 of the water pump, the oxygen output yqll2 of the aeration equipment, the temperature rise value Dws1 of the water pump cable, the temperature rise value Dws2 of the aeration equipment cable, the temperature rise value Dws3 of the heating equipment cable, the mechanical vibration value jxzd1 of the water pump, the mechanical vibration value jxzd2 of the aeration equipment, and the heating power output jrll3.

[0028] Preferably, the energy fluctuation index Nby of the water pump, the energy fluctuation index Nzy of the aeration equipment, and the energy fluctuation index Njy of the heater are obtained by calculation using the following formulas:

[0029]

[0030] In the formula, bz1 represents the maximum allowable value of the preset starting current of the water pump, bz2 represents the maximum allowable threshold of the cable temperature rise, bz3 represents the maximum allowable vibration threshold of the water pump, r1, r2, r3, r4, and r5 represent weight values, and 0 < r1 < 1, 0 < r2 < 1, 0 < r3 < 1, 0 < r4 < 1, 0 < r5 < 1. Their specific values are adjusted and set by the user, and r1 + r2 + r3 + r4 + r5 = 1; ln2 represents the logarithmic operation with 2 as the natural base, and C2 represents the second correction constant;

[0031]

[0032] In the formula, bz4 represents the maximum allowable value of the preset starting current of the aeration equipment, bz5 represents the maximum allowable vibration threshold of the aeration equipment, r6, r7, r8, r9, and r10 represent weight values, and 0 < r6 < 1, 0 < r7 < 1, 0 < r8 < 1, 0 < r9 < 1, 0 < r10 < 1. Their specific values are adjusted and set by the user, and r6 + r7 + r8 + r9 + r10 = 1; C3 represents the third correction constant;

[0033]

[0034] Wherein, bz6 represents the maximum tolerable value of the starting current of the preset heating device, r11, r12, r13, and r14 represent weight values, and 0 < r11 < 1, 0 < r12 < 1, 0 < r13 < 1, 0 < r14 < 1. Their specific values are adjusted and set by the user, and r11 + r12 + r13 + r14 = 1; C4 represents the fourth correction constant.

[0035] Preferably, the real-time grid load index Dwfh is calculated by the following formula:

[0036]

[0037] Wherein, I i is the operating current of the i-th power device, P i is the electric power of the i-th power device; V i represents the voltage value of the i-th power device, cos(φ i ) represents the power factor of the i-th power device; i = 1, 2, 3,..., m, and m represents the total number of power devices in the sub-region;

[0038] The real-time grid load index Dwfh and the environmental condition index Pn are associated through the following to generate the sub-region comprehensive load factor Zhfz:

[0039]

[0040] Wherein, represents the inverse influence of the environmental condition index Pn. The worse the environmental condition, the lower Pn is, and its negative impact on Zhfz is greater; α and β are weight values; and 0 < α < 1, 0 < β < 1. Their specific values are adjusted and set by the user, and α + β = 1.

[0041] Preferably, when the sub-region comprehensive load factor Zhfz > the preset load threshold, it indicates that there is a power safety risk in the sub-grid of the current sub-region, and a second warning instruction is sent;

[0042] When the sub-region comprehensive load factor Zhfz ≤ the preset load threshold, it indicates that there is no power safety risk in the sub-grid of the current sub-region, and continuous monitoring is carried out.

[0043] Preferably, when the second warning instruction is received, a multi-level evaluation strategy is triggered, including:

[0044] The water pump energy fluctuation index Nby is compared with the first risk threshold to obtain the first evaluation result, including:

[0045] When the water pump energy fluctuation index Nby < the first risk threshold, it indicates that the power load of the water pump is normal;

[0046] When the water pump energy fluctuation index Nby ≥ the first risk threshold, it indicates that the water pump power load is abnormal, and the first strategy is generated, including: monitoring the blockage of the water pump cavity pipeline and repairing the defects of the water pump connection cable; installing heat sinks on the cables to reduce the number of water pump starts and stops by 20%, and increase the water pump start and stop time interval by 20%; optimizing the start sequence of multiple water pumps in the sub-area, the start interval between two water pumps is not less than 5 minutes, and installing water pump vibration damping pads;

[0047] The energy fluctuation index Nzy of the oxygen enrichment equipment is compared with the second risk threshold to obtain a second assessment result, including:

[0048] When the energy fluctuation index Nzy of the oxygen enrichment equipment is less than the second risk threshold, it indicates that the power load of the oxygen enrichment equipment is normal;

[0049] When the energy fluctuation index Nzy of the aeration equipment is ≥ the second risk threshold, it indicates that the power load of the aeration equipment is abnormal, and the second strategy is generated, including: monitoring whether the air supply pipeline of the aeration equipment is blocked or leaking, and repairing it; repairing the defects of the connecting cable of the aeration equipment, and installing heat sinks on the cables; reducing the start-up and stop times of the aeration equipment by 15%, and extending the start-up and stop time interval of the aeration equipment by 15%; optimizing the start-up sequence of multiple water pumps in the sub-area, the start-up interval between two aeration equipment is not less than 5 minutes, and installing vibration damping pads on the aeration equipment;

[0050] The heater energy fluctuation index Njy is compared with the third risk threshold to obtain a third assessment result, including:

[0051] When the heater energy fluctuation index Njy is less than the third risk threshold, it indicates that the power load of the heater equipment is normal;

[0052] When the heater energy fluctuation index Njy ≥ the third risk threshold, it indicates that the power load of the heater equipment is abnormal, and a third strategy is generated, including: reducing the operating time and power output of the heater by 10%, and extending the start-stop time interval of the heater by 15%, real-time monitoring of water temperature and water flow, avoiding abnormal heater load due to abnormal water temperature or excessive flow rate; removing scale and dirt on the surface of the heater; and optimizing the water flow path and heater position.

[0053] A power grid security risk management and control system based on data analysis, comprising:

[0054] A sub-area division module is used to divide the fish pond into multiple sub-areas, draw sub-area maps, install isolation devices and corresponding power equipment in each sub-area, and build a sub-grid for each sub-area;

[0055] The environmental monitoring module is used to set up monitoring points in each sub-area and deploy various sensors to monitor the fish pond operating environment in real time, including water temperature, water depth, dissolved oxygen saturation, pH value, suspended matter concentration and water flow rate, and establish an environmental impact data set;

[0056] A first calculation module is used to calculate an environmental condition index Pn based on the environmental impact data set, where the environmental condition index Pn reflects the overall condition of the environment in the current sub-area. If the environmental condition index Pn is lower than a first condition threshold, a first control instruction is sent to the outside;

[0057] The load data collection module collects and monitors the drop and surge mutation data, pressure change data, and flow fluctuation data of each sub-grid power equipment before and after startup to establish a load data set;

[0058] The analysis and first prediction module uses the power grid risk prediction model trained by the time series model ARIMA or the deep learning model Transformer to preprocess the load data set for analysis and calculation to obtain: the water pump energy fluctuation index Nby, the aeration equipment energy fluctuation index Nzy, the heater energy fluctuation index Njy, and the power grid load real-time index Dwfh; and associates the environmental condition index Pn with the power grid load real-time index Dwfh to obtain the sub-area comprehensive load coefficient Zhfz. When the sub-area comprehensive load coefficient Zhfz exceeds the preset load threshold, a second warning instruction is sent;

[0059] The second multi-level evaluation module is used to evaluate the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy and the heater energy fluctuation index Njy respectively after receiving the second warning instruction, and obtain corresponding evaluation results;

[0060] The strategy module is used to generate corresponding control strategies according to the corresponding evaluation results.

[0061] The present invention provides a method and system for controlling power grid security risks based on data analysis, which has the following beneficial effects:

[0062] (1) By dividing the fish pond into multiple precisely defined sub-areas and deploying monitoring points and sensors in each sub-area, the changes in environmental conditions inside the fish pond can be monitored and recorded in real time, and an accurate environmental impact data set can be constructed. These data can not only be used to calculate the environmental condition index Pn, but can also be associated with the real-time grid load index Dwfh to form a comprehensive load factor Zhfz, which can timely reflect the power demand and environmental status in the sub-area. In addition, the grid risk prediction model can more accurately predict the energy fluctuations of key equipment such as water pumps, aeration equipment, and heaters, helping managers to formulate more effective equipment operation strategies and load adjustment plans.

[0063] (2) When the environmental condition index Pn is less than the first condition threshold, it means that the environment needs to turn on the water pump, aeration equipment and heater to adjust the environment accordingly. The water pump is turned on to drive the water circulation. The water is circulated through the water pump. The aeration equipment includes an aerator and an aeration equipment. The aerator has a purification function. The water pump or the aerator is turned on to purify the suspended matter in the water. Through accurate monitoring and calculation of the environmental condition index Pn, real-time monitoring and intelligent regulation of the fish pond environment can be achieved, thereby improving the breeding efficiency and environmental protection level.

[0064] (3) As key electrical equipment in fish ponds, water pumps, aerators and heaters have a direct impact on the stability and fluctuation of the power load due to their operating conditions. The calculation of the water pump energy fluctuation index Nby, the aerator energy fluctuation index Nzy and the heater energy fluctuation index Njy can reflect the fluctuation of energy consumption of these equipment during operation, which will directly affect the load characteristics of the power system. By monitoring and analyzing the energy fluctuation index of water pumps, aerators and heaters, abnormal operating conditions or potential failure risks of the equipment can be discovered in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic diagram of the steps of a power grid security risk management method based on data analysis according to the present invention;

[0066] Figure 2 The present invention is a block diagram of a power grid security risk management and control system based on data analysis. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments 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.

[0068] Example 1

[0069] See also Figure 1 The present invention provides a power grid security risk management method based on data analysis, comprising:

[0070] S1. Divide several fish ponds into several sub-areas, install isolation devices between sub-areas and adjacent sub-areas, build a sub-grid for each sub-area, and install corresponding power equipment;

[0071] S2. Setting monitoring points in each sub-area and deploying sensors at the monitoring points to monitor the fish pond operating environment in the sub-area in real time and establish an environmental impact data set; and extracting features from the relevant data information in the environmental impact data set to construct an environmental condition index Pn. If the environmental condition index Pn is lower than the first condition threshold, a first control instruction is sent to the outside.

[0072] S3. After receiving the first control instruction, start the power equipment in the sub-grid in the current sub-region; and collect and monitor the drop and surge mutation data, pressure change data and flow fluctuation data of each sub-grid power equipment before and after startup in real time to establish a load data set;

[0073] S4. Using the power grid risk prediction model trained by the time series model ARIMA or the deep learning model Transformer, the load data set is preprocessed and analyzed and calculated to obtain: the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy, the heater energy fluctuation index Njy and the power grid load real-time index Dwfh; and the environmental condition index Pn and the power grid load real-time index Dwfh are associated to obtain the sub-area comprehensive load coefficient Zhfz. When the sub-area comprehensive load coefficient Zhfz exceeds the preset load threshold, a second warning instruction is sent;

[0074] To train the power grid risk prediction model, using the time series model ARIMA or the deep learning model Transformer, the following steps are required to build and optimize the model: Collect the load data set of each power equipment in the sub-region, clean the data, and handle missing values ​​and outliers. At the same time, standardize or normalize the data to scale it to the same magnitude so that the model can better learn and predict. According to the characteristics of the problem and the nature of the data, select a suitable time series model or deep learning model. Use ARIMA or Transformer to configure the model's hyperparameters, such as sliding window size, seasonal adjustment parameters for ARIMA, number of layers, number of heads, learning rate, etc. for Transformer to optimize the performance of the model. Use the training data set to fit the selected model, that is, learn the parameters in the model so that the model can accurately capture the patterns and trends in the data. Use the validation set to evaluate the model performance and tune the hyperparameters to avoid overfitting or underfitting. Use the trained model to predict the power grid load in the future period to help predict whether the sub-region comprehensive load factor Zhfz will exceed the preset load threshold. During the model application process, it is necessary to update data in real time and continuously monitor the model's predictive performance, and adjust the model or strategy in time to cope with changing environmental conditions and load requirements.

[0075] S5. After receiving the second warning instruction, the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy and the heater energy fluctuation index Njy are evaluated respectively, and after obtaining the corresponding evaluation results, the corresponding control strategy is generated.

[0076] In this embodiment, by dividing the fish pond into a plurality of precisely defined sub-areas and deploying monitoring points and sensors in each sub-area, the environmental condition changes inside the fish pond can be monitored and recorded in real time, and an accurate environmental impact data set can be constructed. These data can not only be used to calculate the environmental condition index Pn, but also be associated with the real-time index of the power grid load Dwfh to form a comprehensive load factor Zhfz, which timely reflects the power demand and environmental status in the sub-area. In addition, through the power grid risk prediction model, the energy fluctuation of key equipment such as water pumps, aeration equipment and heaters can be predicted more accurately, helping managers to formulate more effective equipment operation strategies and load adjustment plans.

[0077] Example 2

[0078] This embodiment is an explanation or improvement of Embodiment 1. Specifically, S1 includes:

[0079] S11, dividing the fish ponds into several sub-areas at equal intervals according to their areas and shapes, and locating the sub-area boundaries using GPS technology or measurement tools;

[0080] S12. Use AutoCAD drawing software to draw a sub-area map and mark each sub-area on the sub-area map, specifically marking as: Zq1, Zq2, Zq3, ..., Zq n , n represents the number of sub-regions, and the fish pond area is marked in each sub-region;

[0081] S13. Install isolation devices between each sub-area and adjacent sub-areas according to the sub-area map;

[0082] S14. Establish a sub-grid in each sub-area, the sub-grid including: cables, switches, lightning protection devices, leakage protection devices, power control boxes and transformers;

[0083] And install corresponding electrical equipment, including: water pumps, oxygenation equipment, lighting equipment, heaters and water quality monitoring equipment.

[0084] In this embodiment, through precise regional division, scientific power grid design and equipment layout, the power management efficiency and operation safety of fish ponds can be effectively improved, ensuring the healthy growth of fish and the stable improvement of production efficiency.

[0085] Example 3

[0086] This embodiment is an explanation or improvement based on Embodiment 1. Specifically, monitoring points are set in each sub-region, and sensors are deployed at the monitoring points to monitor the operating environment of the fish ponds in the sub-regions in real time, and an environmental impact data set is established.

[0087] The environmental impact data set includes, but is not limited to, the following data: water temperature Swd, water depth Ss, dissolved oxygen saturation ratio Rjy, water body pH value pH, suspended solid concentration Xfw, and water flow velocity Slsd.

[0088] The water temperature Swd is obtained by measuring with a water temperature sensor; the water depth Ss is obtained by measuring with an ultrasonic sensor; the dissolved oxygen saturation ratio Rjy is obtained by measuring with a dissolved oxygen saturation ratio sensor; the water body pH value pH is obtained by measuring with a pH sensor; the suspended solid concentration Xfw is obtained by measuring with a turbidity sensor; the water flow velocity Slsd is obtained by measuring with a water flow velocity sensor.

[0089] Specifically, the way to obtain the environmental condition index Pn is to extract the water temperature Swd, water depth Ss, dissolved oxygen saturation ratio Rjy, water body pH value pH, suspended solid concentration Xfw, and water flow velocity Slsd in the environmental impact data set. After dimensionless processing, the environmental condition index Pn is generated through the following formula:

[0090]

[0091] In the formula, represents the preset standard water temperature threshold of the fish pond, represents the preset water depth threshold of the fish pond, represents the preset standard threshold of the dissolved oxygen saturation ratio, represents the preset standard threshold of the water body pH value, represents the preset maximum tolerance threshold of suspended solids, represents the preset standard threshold of the water flow velocity, w1, w2, w3, w4, w5, and w6 represent weight values, and 0 < w1 < 1, 0 < w2 < 1, 0 < w3 < 1, 0 < w4 < 1, 0 < w5 < 1, 0 < w6 < 1. Their specific values are adjusted and set by the user, and w1 + w2 + w3 + w4 + w5 + w6 = 1; C1 represents the first correction constant.

[0092] When the environmental condition index Pn < the first condition threshold, it indicates that the environment of the current sub-region is abnormal, and a first control instruction is generated to trigger the start of the water pump, aeration equipment, and heater. When the environmental condition index Pn ≥ the first condition threshold, it indicates that the environment of the current sub-region is normal and no control instruction needs to be triggered.

[0093] In this embodiment, when the environmental condition index Pn is less than the first condition threshold, it indicates that the environment needs a water pump, an aeration device and a heater to be turned on to adjust the environment accordingly. The water pump is turned on to drive the water circulation. The water is circulated through the water pump. The aeration device includes an aerator and an aeration device. The aerator has a purification function. The water pump or the aerator is turned on to purify the suspended matter in the water. By accurately monitoring and calculating the environmental condition index Pn, real-time monitoring and intelligent regulation of the fish pond environment can be achieved, thereby improving the breeding efficiency and environmental protection level.

[0094] Example 4

[0095] This embodiment is an explanation or improvement of the embodiment 1. Specifically, the drop and surge mutation data, pressure change data and flow fluctuation data of each sub-grid power equipment before and after startup are collected and monitored in real time to establish a load data set.

[0096] The drop and surge mutation data before and after the start of power equipment include: water pump start and stop frequency Qtpl1, water pump start and stop time interval T1, oxygenation equipment start and stop frequency Qtpl2, oxygenation equipment start and stop time interval T2, heater start and stop frequency Qtpl3, heater start and stop time interval T3, water pump starting current QdI1, oxygenation equipment starting current QdI2 and heating equipment starting current QdI3; start and stop frequency, frequent start and stop will increase the instantaneous load fluctuation of the power grid and affect stability. Starting current, water pumps, oxygenation equipment and heating equipment usually generate higher starting current when starting, which may cause short-term voltage drop or current surge, affecting the safety of the power grid;

[0097] The number of starts and stops and the time interval of the equipment are monitored through Hall sensors or electronic counters; the current conditions of each device when it is started are measured in real time through current sensors;

[0098] The pressure change data include: pump chamber pressure ylz1, pump chamber back pressure change difference bycz1, aeration equipment chamber pressure ylz2 and aeration equipment back pressure change difference bycz2; the pressure sensor can be used to monitor the pump chamber pressure and back pressure changes of the water pump in real time. The pressure sensor is also used to monitor the pressure and back pressure changes in the chamber inside the aeration equipment;

[0099] Pump chamber pressure ylz1: Slight changes in the grid frequency may affect the speed and efficiency of the pump motor, thereby affecting the overall power consumption and the operational stability of the pump. Back pressure changes bycz1: Changes in the pump outlet pressure, such as sudden valve closure, can cause drastic fluctuations in the current, causing impacts on the grid. Excessively high or low pump chamber pressure may cause abnormal loads on the pump motor, thereby affecting power consumption and grid stability.

[0100] Traffic fluctuation data includes:

[0101] Water pump outlet flow rate csll1: The actual flow rate of the water pump outlet is measured by a flow sensor;

[0102] Oxygen output of the aeration equipment yqll2: The oxygen output of the aeration equipment is measured using a corresponding oxygen sensor;

[0103] Temperature rise of the water pump cable Dws1, temperature rise of the aeration equipment cable Dws2, and temperature rise of the heating equipment cable Dws3: The temperature rise of the cable is monitored by devices such as temperature sensors or infrared thermometers to reflect the heat changes during the operation of the equipment;

[0104] Mechanical vibration value of the water pump jxzd1 and mechanical vibration value of the aeration equipment jxzd2: The mechanical vibration of the equipment is measured by vibration sensors to evaluate the stability of the equipment operation state;

[0105] Heating power output jrll3: The power output of the heating equipment is monitored in real time by a power sensor or a current sensor.

[0106] The above data is cleaned, outliers are removed, and dimensionless normalization processing is performed;

[0107] Specifically, the water pump energy fluctuation index Nby, the aeration equipment energy fluctuation index Nzy, and the heater energy fluctuation index Njy are calculated and obtained through the following formulas:

[0108]

[0109] In the formula, bz1 represents the maximum allowable starting current value of the preset water pump, bz2 represents the maximum allowable cable temperature rise threshold, bz3 represents the maximum allowable vibration threshold of the water pump, r1, r2, r3, r4, and r5 represent weight values, and 0 < r1 < 1, 0 < r2 < 1, 0 < r3 < 1, 0 < r4 < 1, 0 < r5 < 1. Their specific values are adjusted and set by the user, and r1 + r2 + r3 + r4 + r5 = 1; ln2 represents the logarithmic operation with the natural number 2 as the base, and C2 represents the second correction constant;

[0110]

[0111] In the formula, bz4 represents the maximum allowable starting current value of the preset aeration equipment, bz5 represents the maximum allowable vibration threshold of the aeration equipment, r6, r7, r8, r9, and r10 represent weight values, and 0 < r6 < 1, 0 < r7 < 1, 0 < r8 < 1, 0 < r9 < 1, 0 < r10 < 1. Their specific values are adjusted and set by the user, and r6 + r7 + r8 + r9 + r10 = 1; C3 represents the third correction constant;

[0112]

[0113] In the formula, bz6 represents the maximum allowable starting current of the preset heating device, r11, r12, r13, and r14 represent weight values, and 0 < r11 < 1, 0 < r12 < 1, 0 < r13 < 1, 0 < r14 < 1. Their specific values are adjusted and set by the user, and r11 + r12 + r13 + r14 = 1; C4 represents the fourth correction constant.

[0114] In this embodiment, the water pump, aeration equipment, and heater are key power equipment in the aquaculture pond, and their operating states directly affect the stability and fluctuation of the power load. The calculation of the energy fluctuation index Nby of the water pump, the energy fluctuation index Nzy of the aeration equipment, and the energy fluctuation index Njy of the heater can reflect the energy consumption fluctuation of these equipment during operation, and these fluctuations will directly affect the load characteristics of the power system. If the energy fluctuation is large, it may lead to the instability of the power load, thereby increasing the risk of the power system. By monitoring and analyzing the energy fluctuation indexes of the water pump, aeration equipment, and heater, the abnormal operating state or potential failure risk of the equipment can be detected in time. For example, a sudden increase in the energy fluctuation index may indicate frequent start-stop, energy consumption fluctuation, or power fluctuation of the equipment, which may be a sign of unstable equipment operation or an impending failure. Taking preventive maintenance measures in time can effectively reduce the impact of equipment failures on the stability of the power system and aquaculture activities.

[0115] Embodiment 5. This embodiment is an explanatory description or improvement based on Embodiment 1. Specifically, the real-time grid load index Dwfh is calculated through the following formula:

[0116]

[0117] In the formula, I i is the operating current of the i-th power equipment, and P i is the electric power of the i-th power equipment; V i represents the voltage value of the i-th power equipment, and cos(φ i ) represents the power factor of the i-th power equipment; i = 1, 2, 3,..., m, where m represents the total number of power equipment in the sub-region;

[0118] The real-time grid load index Dwfh and the environmental condition index Pn are correlated as follows to generate the sub-region comprehensive load factor Zhfz:

[0119]

[0120] In the formula, It indicates that the environmental condition index Pn has an inverse influence. The worse the environmental condition, the lower Pn is, and the greater the negative impact on Zhfz is. α and β are weight values. 0<α<1, 0<β<1. The specific value is adjusted and set by the user, α+β=1.

[0121] When the sub-region comprehensive load factor Zhfz> the preset load threshold, it indicates that the sub-grid of the current sub-region has a power safety risk, and a second early warning instruction is sent;

[0122] When the sub-area comprehensive load factor Zhfz ≤ the preset load threshold, it means that there is no power safety risk in the sub-grid of the current sub-area and continuous monitoring is performed.

[0123] In this embodiment, by calculating and associating the effective real-time index Dwfh of the grid load and the sub-region comprehensive load factor Zhfz with the environmental condition index Pn, it is possible to effectively manage and prevent safety risks in the power system of the fish pond, thereby improving management efficiency and production safety.

[0124] Embodiment 6: This embodiment is an explanation or improvement of Embodiment 1. Specifically, when the second warning instruction is received, a multi-level evaluation strategy is triggered, including:

[0125] The water pump energy fluctuation index Nby is compared with the first risk threshold to obtain a first assessment result, including:

[0126] When the water pump energy fluctuation index Nby is less than the first risk threshold, it means that the water pump power load is normal;

[0127] When the water pump energy fluctuation index Nby ≥ the first risk threshold, it indicates that the water pump power load is abnormal, and the first strategy is generated, including: monitoring the blockage of the water pump cavity pipeline and repairing the defects of the water pump connection cable; installing heat sinks on the cables to reduce the number of water pump starts and stops by 20%, and increase the water pump start and stop time interval by 20%; optimizing the start sequence of multiple water pumps in the sub-area, the start interval between two water pumps is not less than 5 minutes, and installing water pump vibration damping pads;

[0128] The energy fluctuation index Nzy of the oxygen enrichment equipment is compared with the second risk threshold to obtain a second assessment result, including:

[0129] When the energy fluctuation index Nzy of the oxygen enrichment equipment is less than the second risk threshold, it indicates that the power load of the oxygen enrichment equipment is normal;

[0130] When the energy fluctuation index Nzy of the aeration equipment is ≥ the second risk threshold, it indicates that the power load of the aeration equipment is abnormal, and the second strategy is generated, including: monitoring whether the air supply pipeline of the aeration equipment is blocked or leaking, and repairing it; repairing the defects of the connecting cable of the aeration equipment, and installing heat sinks on the cables; reducing the start-up and stop times of the aeration equipment by 15%, and extending the start-up and stop time interval of the aeration equipment by 15%; optimizing the start-up sequence of multiple water pumps in the sub-area, the start-up interval between two aeration equipment is not less than 5 minutes, and installing vibration damping pads on the aeration equipment;

[0131] The heater energy fluctuation index Njy is compared with the third risk threshold to obtain a third assessment result, including:

[0132] When the heater energy fluctuation index Njy is less than the third risk threshold, it indicates that the power load of the heater equipment is normal;

[0133] When the heater energy fluctuation index Njy ≥ the third risk threshold, it indicates that the power load of the heater equipment is abnormal, and a third strategy is generated, including: reducing the operating time and power output of the heater by 10%, and extending the start-stop time interval of the heater by 15%, real-time monitoring of water temperature and water flow, avoiding abnormal heater load due to abnormal water temperature or excessive flow rate; removing scale and dirt on the surface of the heater; and optimizing the water flow path and heater position.

[0134] In this embodiment, according to the first evaluation result, the second evaluation result and the third evaluation result, the system can immediately adopt targeted first strategy, second strategy and third strategy. For example, for abnormal water pumps, oxygenation equipment or heaters, the system can quickly dispatch maintenance teams or take optimization operations to reduce equipment loss and extend service life. Stable power supply is a key factor in ensuring the production efficiency of fish ponds and the health of fish. Multi-level evaluation effectively improves the stability and reliability of electricity in the production process by ensuring the normal operation of each power equipment. Data collection and analysis during the evaluation process can help the system implement preventive maintenance measures. By monitoring equipment operation and data changes, the system can predict possible power problems and intervene in advance, avoiding production interruptions and losses caused by equipment failures.

[0135] Example 7, please refer to Figure 2 ,A power grid security risk management and control system based on data analysis, including,

[0136] A sub-area division module is used to divide the fish pond into multiple sub-areas, draw sub-area maps, install isolation devices and corresponding power equipment in each sub-area, and build a sub-grid for each sub-area;

[0137] The environmental monitoring module is used to set up monitoring points in each sub-area and deploy various sensors to monitor the fish pond operating environment in real time, including water temperature, water depth, dissolved oxygen saturation, pH value, suspended matter concentration and water flow rate, and establish an environmental impact data set;

[0138] A first calculation module is used to calculate an environmental condition index Pn based on the environmental impact data set, where the environmental condition index Pn reflects the overall condition of the environment in the current sub-area. If the environmental condition index Pn is lower than a first condition threshold, a first control instruction is sent to the outside;

[0139] The load data collection module collects and monitors the drop and surge mutation data, pressure change data, and flow fluctuation data of each sub-grid power equipment before and after startup to establish a load data set;

[0140] The analysis and first prediction module uses the power grid risk prediction model trained by the time series model ARIMA or the deep learning model Transformer to preprocess the load data set and then analyze and calculate to obtain: the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy, the heater energy fluctuation index Njy and the power grid load real-time index Dwfh; and associates the environmental condition index Pn with the power grid load real-time index Dwfh to obtain the sub-area comprehensive load coefficient Zhfz. When the sub-area comprehensive load coefficient Zhfz exceeds the preset load threshold, a second warning instruction is sent;

[0141] The second multi-level evaluation module is used to evaluate the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy and the heater energy fluctuation index Njy respectively after receiving the second warning instruction, and obtain corresponding evaluation results;

[0142] The strategy module is used to generate corresponding control strategies according to the corresponding evaluation results.

[0143] In this embodiment, firstly, the system effectively solves the problems of undivided areas and unreasonable equipment layout in traditional management through refined sub-area division and power grid design. Isolation devices and special power equipment are installed in each sub-area to ensure the reliability and stability of power supply and reduce the impact caused by equipment operation conflicts or failures.

[0144] Secondly, the environmental monitoring module uses various sensors to monitor water quality, temperature, dissolved oxygen, flow rate and other indicators in real time to establish an environmental impact data set. These data not only help to control power equipment in real time, but also support the establishment and optimization of prediction models to ensure that the power grid operates in the best condition.

[0145] Furthermore, through a multi-level evaluation strategy, the system can quickly respond to and evaluate the operating status of various types of power equipment, such as water pumps, aeration equipment, and heaters, detect abnormalities in a timely manner, and take corresponding measures, such as optimizing the start-stop sequence, adjusting operating parameters, etc., to reduce equipment losses and improve efficiency.

[0146] Finally, the introduction of the real-time grid load index Dwfh and the sub-region comprehensive load factor Zhfz effectively warns and manages power safety risks. When the load exceeds the preset threshold, the system will issue an alarm and trigger the corresponding emergency plan to ensure the safety of fish pond production and the continuous operation of equipment in a timely manner.

[0147] In summary, the power grid security risk management and control system based on data analysis has comprehensively improved the power management effect of fish ponds by improving the accuracy and response speed of power control. It not only protects the ecological environment and healthy growth of fish, but also provides stable and reliable power support for the aquaculture industry, thereby promoting the improvement of production efficiency and economic benefits.

[0148] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A power grid security risk management method based on data analysis, characterized in that: include, S1. Divide several fish ponds into several sub-areas, install isolation devices between sub-areas and adjacent sub-areas, build a sub-grid for each sub-area, and install corresponding power equipment; S2. Set up monitoring points in each sub-area and deploy sensors at the monitoring points to monitor the operating environment of the fish ponds in the sub-area in real time and establish an environmental impact data set; the environmental impact data set includes but is not limited to the following data: water temperature Swd, water depth Ss, dissolved oxygen saturation ratio Rjy, water body pH, suspended matter concentration Xfw and water flow velocity Slsd; The water temperature Swd is measured and obtained by a water temperature sensor; the water depth Ss is measured and obtained by an ultrasonic sensor; the dissolved oxygen saturation ratio Rjy is measured and obtained by a dissolved oxygen saturation ratio sensor; the water body pH is measured and obtained by a pH sensor; the suspended matter concentration Xfw is measured and obtained by a turbidity sensor; the water flow velocity Slsd is measured and obtained by a water flow velocity sensor; and extracting features from relevant data information in the environmental impact data set to construct an environmental condition index Pn. If the environmental condition index Pn is lower than a first condition threshold, a first control instruction is sent to the outside; The environmental condition index Pn is obtained by extracting the water temperature Swd, water depth Ss, dissolved oxygen saturation ratio Rjy, water body pH, suspended solids concentration Xfw and water flow velocity Slsd from the environmental impact data set, and after dimensionless processing, the environmental condition index Pn is generated by the following formula: ； In the formula, Indicates the preset standard water temperature threshold of the fish pond. Indicates the preset threshold of the water depth of the preset fish pond. Indicates the preset standard threshold value of dissolved oxygen saturation percentage. Indicates the preset water pH value standard threshold. Indicates the preset maximum suspended matter tolerance threshold. represents the preset water velocity standard threshold, w1, w2, w3, w4, w5 and w6 represent weight values, represents the first correction constant; When the environmental condition index Pn is less than the first condition threshold, it indicates that the current sub-region environment is abnormal, and a first control instruction is generated to trigger the start of the water pump, the oxygenation equipment, and the heater. When the environmental condition index Pn is greater than or equal to the first condition threshold, it indicates that the current sub-region environment is normal, and no control instruction needs to be triggered. S3, after receiving the first control instruction, starting the power equipment in the sub-grid in the current sub-region; The data of drop and surge mutation, pressure change and flow fluctuation before and after the start-up of each sub-grid power equipment are collected and monitored in real time to establish a load data set; The drop and surge mutation data before and after the start of the power equipment include: water pump start and stop frequency Qtpl1, water pump start and stop time interval T1, oxygenation equipment start and stop frequency Qtpl2, oxygenation equipment start and stop time interval T2, heater start and stop frequency Qtpl3, heater start and stop time interval T3, water pump starting current QdI1, oxygenation equipment starting current QdI2 and heating equipment starting current QdI3; The pressure change data include: pump chamber pressure ylz1, pump chamber back pressure change difference bycz1; oxygenation equipment chamber pressure ylz2, oxygenation equipment back pressure change difference bycz2; The flow fluctuation data include: water pump outlet flow csll1, oxygen output of aeration equipment yqll2, temperature rise of water pump cable Dws1, temperature rise of aeration equipment cable Dws2, temperature rise of heating equipment cable Dws3, mechanical vibration value of water pump jxzd1, mechanical vibration value of aeration equipment jxzd2 and heating power output jrll3; S4. Using the power grid risk prediction model trained by the time series model ARIMA or the deep learning model Transformer, the load data set is preprocessed and analyzed and calculated to obtain: the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy, the heater energy fluctuation index Njy and the power grid load real-time index Dwfh; and the environmental condition index Pn and the power grid load real-time index Dwfh are associated to obtain the sub-area comprehensive load coefficient Zhfz. When the sub-area comprehensive load coefficient Zhfz exceeds the preset load threshold, a second warning instruction is sent; The water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy and the heater energy fluctuation index Njy are calculated and obtained by the following formula: ； In the formula, bz1 represents the maximum bearing value of the preset water pump starting current. represents the maximum cable temperature rise threshold, bz3 represents the maximum vibration threshold of the pump, r1, r2, r3, r4 and r5 represent weight values, represents the second correction constant; ； In the formula, bz4 represents the maximum start-up current tolerance value of the preset oxygen enrichment equipment, bz5 represents the maximum vibration threshold of the oxygen enrichment equipment, r6, r7, r8, r9 and r10 represent weight values, represents the third correction constant; ； In the formula, bz6 represents the maximum start-up current tolerance value of the preset heating equipment, r11, r12, r13 and r14 represent weight values, represents the fourth correction constant; The real-time index of the power grid load Dwfh is calculated by the following formula: ； ； In the formula, It is The operating current of the electrical equipment, It is The electrical power of each electrical device; Indicates The voltage value of the electrical equipment, Indicates The power factor of each electrical device; i= 1, 2, 3, ...、m , m Indicates the total number of power equipment in the sub-area; The real-time index of grid load Dwfh and the environmental condition index Pn are associated with each other to generate the sub-region comprehensive load factor Zhfz: ； In the formula, It indicates that the environmental condition index Pn has an inverse effect. The worse the environmental condition, the lower Pn is, and the greater its negative impact on Zhfz is; and is the weight value; S5. After receiving the second warning instruction, the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy and the heater energy fluctuation index Njy are evaluated respectively, and after obtaining the corresponding evaluation results, the corresponding control strategy is generated.

2. A power grid security risk management and control method based on data analysis according to claim 1, characterized in that: S1 includes: S11, dividing the fish ponds into several sub-areas at equal intervals according to their areas and shapes, and locating the sub-area boundaries using GPS technology or measurement tools; S12. Use AutoCAD drawing software to draw a sub-area map and mark each sub-area on the sub-area map, specifically marking as: Zq1, Zq2, Zq3, ..., Zq n , n represents the number of sub-regions, and the fish pond area is marked in each sub-region; S13. Install isolation devices between each sub-area and adjacent sub-areas according to the sub-area map; S14. Establish a sub-grid in each sub-area, the sub-grid including: cables, switches, lightning protection devices, leakage protection devices, power control boxes and transformers; And install corresponding electrical equipment, which includes: water pump, oxygenation equipment, lighting equipment, heater and water quality monitoring equipment.

3. A power grid security risk management and control method based on data analysis according to claim 1, characterized in that: When the sub-region comprehensive load factor Zhfz> the preset load threshold, it indicates that the sub-grid of the current sub-region has a power safety risk, and a second early warning instruction is sent; When the sub-area comprehensive load factor Zhfz ≤ the preset load threshold, it means that there is no power safety risk in the sub-grid of the current sub-area and continuous monitoring is performed.

4. The method for controlling power grid security risks based on data analysis according to claim 1, characterized in that: When the second warning instruction is received, a multi-level evaluation strategy is triggered, including: The water pump energy fluctuation index Nby is compared with the first risk threshold to obtain a first assessment result, including: When the water pump energy fluctuation index Nby is less than the first risk threshold, it means that the water pump power load is normal; When the water pump energy fluctuation index Nby ≥ the first risk threshold, it indicates that the water pump power load is abnormal, and the first strategy is generated, including: monitoring the blockage of the water pump cavity pipeline and repairing the defects of the water pump connection cable; installing heat sinks on the cables to reduce the number of water pump starts and stops by 20%, and increase the water pump start and stop time interval by 20%; optimizing the start sequence of multiple water pumps in the sub-area, the start interval between two water pumps is not less than 5 minutes, and installing water pump vibration damping pads; The energy fluctuation index Nzy of the oxygen enrichment equipment is compared with the second risk threshold to obtain a second assessment result, including: When the energy fluctuation index Nzy of the oxygen enrichment equipment is less than the second risk threshold, it indicates that the power load of the oxygen enrichment equipment is normal; When the energy fluctuation index Nzy of the aeration equipment is ≥ the second risk threshold, it indicates that the power load of the aeration equipment is abnormal, and the second strategy is generated, including: monitoring whether the air supply pipeline of the aeration equipment is blocked or leaking, and repairing it; repairing the defects of the connecting cable of the aeration equipment, and installing heat sinks on the cables; reducing the start-up and stop times of the aeration equipment by 15%, and extending the start-up and stop time interval of the aeration equipment by 15%; optimizing the start-up sequence of multiple water pumps in the sub-area, the start-up interval between two aeration equipment is not less than 5 minutes, and installing vibration damping pads on the aeration equipment; The heater energy fluctuation index Njy is compared with the third risk threshold to obtain a third assessment result, including: When the heater energy fluctuation index Njy is less than the third risk threshold, it indicates that the power load of the heater equipment is normal; When the heater energy fluctuation index Njy ≥ the third risk threshold, it indicates that the power load of the heater equipment is abnormal, and a third strategy is generated, including: reducing the operating time and power output of the heater by 10%, and extending the start-stop time interval of the heater by 15%, real-time monitoring of water temperature and water flow, avoiding abnormal heater load due to abnormal water temperature or excessive flow rate; removing scale and dirt on the surface of the heater; and optimizing the water flow path and heater position.

5. A power grid security risk management and control system based on data analysis, applied to a power grid security risk management and control method based on data analysis as claimed in any one of claims 1 to 4, characterized in that: It includes a sub-area division module, which is used to divide the fish pond into multiple sub-areas, draw sub-area maps, install isolation devices and corresponding power equipment in each sub-area, and build a sub-grid for each sub-area; The environmental monitoring module is used to set monitoring points in each sub-area, deploy various sensors to monitor the fish pond operating environment in real time, including water temperature, water depth, dissolved oxygen saturation, pH value, suspended matter concentration and water flow velocity, and establish an environmental impact data set; the environmental impact data set includes but is not limited to the following data: water temperature Swd, water depth Ss, dissolved oxygen saturation ratio Rjy, water body pH, suspended matter concentration Xfw and water flow velocity Slsd; The water temperature Swd is measured and obtained by a water temperature sensor; the water depth Ss is measured and obtained by an ultrasonic sensor; the dissolved oxygen saturation ratio Rjy is measured and obtained by a dissolved oxygen saturation ratio sensor; the water body pH is measured and obtained by a pH sensor; the suspended matter concentration Xfw is measured and obtained by a turbidity sensor; the water flow velocity Slsd is measured and obtained by a water flow velocity sensor; A first calculation module is used to calculate an environmental condition index Pn based on the environmental impact data set, where the environmental condition index Pn reflects the overall condition of the environment in the current sub-area. If the environmental condition index Pn is lower than a first condition threshold, a first control instruction is sent to the outside; The environmental condition index Pn is obtained by extracting the water temperature Swd, water depth Ss, dissolved oxygen saturation ratio Rjy, water body pH, suspended solids concentration Xfw and water flow velocity Slsd from the environmental impact data set, and after dimensionless processing, the environmental condition index Pn is generated by the following formula: ； In the formula, Indicates the preset standard water temperature threshold of the fish pond. Indicates the preset threshold of the water depth of the preset fish pond. Indicates the preset standard threshold value of dissolved oxygen saturation percentage. Indicates the preset water pH value standard threshold. Indicates the preset maximum suspended matter tolerance threshold. represents the preset water velocity standard threshold, w1, w2, w3, w4, w5 and w6 represent weight values, represents the first correction constant; When the environmental condition index Pn is less than the first condition threshold, it indicates that the current sub-region environment is abnormal, and a first control instruction is generated to trigger the start of the water pump, the oxygenation equipment, and the heater. When the environmental condition index Pn is greater than or equal to the first condition threshold, it indicates that the current sub-region environment is normal, and no control instruction needs to be triggered. The load data collection module collects and monitors the drop and surge mutation data, pressure change data, and flow fluctuation data of each sub-grid power equipment before and after startup to establish a load data set; The drop and surge mutation data before and after the start of the power equipment include: water pump start and stop frequency Qtpl1, water pump start and stop time interval T1, oxygenation equipment start and stop frequency Qtpl2, oxygenation equipment start and stop time interval T2, heater start and stop frequency Qtpl3, heater start and stop time interval T3, water pump starting current QdI1, oxygenation equipment starting current QdI2 and heating equipment starting current QdI3; The pressure change data include: pump chamber pressure ylz1, pump chamber back pressure change difference bycz1; oxygenation equipment chamber pressure ylz2, oxygenation equipment back pressure change difference bycz2; The flow fluctuation data include: water pump outlet flow csll1, oxygen output of aeration equipment yqll2, temperature rise of water pump cable Dws1, temperature rise of aeration equipment cable Dws2, temperature rise of heating equipment cable Dws3, mechanical vibration value of water pump jxzd1, mechanical vibration value of aeration equipment jxzd2 and heating power output jrll3; The analysis and first prediction module uses the power grid risk prediction model trained by the time series model ARIMA or the deep learning model Transformer to preprocess the load data set for analysis and calculation to obtain: the water pump energy fluctuation index Nby, the aeration equipment energy fluctuation index Nzy, the heater energy fluctuation index Njy, and the power grid load real-time index Dwfh; and associates the environmental condition index Pn with the power grid load real-time index Dwfh to obtain the sub-area comprehensive load coefficient Zhfz. When the sub-area comprehensive load coefficient Zhfz exceeds the preset load threshold, a second warning instruction is sent; The water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy and the heater energy fluctuation index Njy are calculated and obtained by the following formula: ； In the formula, bz1 represents the maximum bearing value of the preset water pump starting current. represents the maximum cable temperature rise threshold, bz3 represents the maximum vibration threshold of the pump, r1, r2, r3, r4 and r5 represent weight values, represents the second correction constant; ； In the formula, bz4 represents the maximum start-up current tolerance value of the preset oxygen enrichment equipment, bz5 represents the maximum vibration threshold of the oxygen enrichment equipment, r6, r7, r8, r9 and r10 represent weight values, represents the third correction constant; ； In the formula, bz6 represents the maximum start-up current tolerance value of the preset heating equipment, r11, r12, r13 and r14 represent weight values, represents the fourth correction constant; The real-time index of the power grid load Dwfh is calculated by the following formula: ； ； In the formula, It is The operating current of the electrical equipment, It is The electrical power of each electrical device; Indicates The voltage value of the electrical equipment, Indicates The power factor of each electrical device; i= 1, 2, 3, ...、m , m Indicates the total number of power equipment in the sub-area; The real-time index of grid load Dwfh and the environmental condition index Pn are associated with each other to generate the sub-region comprehensive load factor Zhfz: ； In the formula, It indicates that the environmental condition index Pn has an inverse effect. The worse the environmental condition, the lower Pn is, and the greater its negative impact on Zhfz is; and is the weight value; The second multi-level evaluation module is used to evaluate the water pump energy fluctuation index Nby, the oxygenation equipment energy fluctuation index Nzy and the heater energy fluctuation index Njy respectively after receiving the second warning instruction, and obtain corresponding evaluation results; The strategy module is used to generate corresponding control strategies according to the corresponding evaluation results.

Images