Power load prediction system and method based on power data

Abstract

The invention discloses a power load prediction system and method based on power data, and belongs to the technical field of data processing methods suitable for the prediction purpose. Weather information is collected, and the influence condition of abnormal weather on crops is evaluated according to a weather evaluation model; crop information is collected, and the growth state of crops is evaluated according to the crop evaluation model; analyzing the irrigation demand of the set area according to the irrigation demand model; historical power data and historical irrigation volume data are collected, and the power consumption condition is predicted according to the power consumption prediction model; acquiring distribution transformer data, and evaluating the abnormal condition of the distribution transformer according to the distribution transformer evaluation model; according to the method, the power load of the distribution transformer is comprehensively evaluated by predicting the irrigation power consumption and monitoring the abnormal condition of the distribution transformer in real time, the irrigation power consumption demand can be responded in time, and it is ensured that agricultural water is not affected by insufficient power supply.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing methods suitable for prediction purposes, and preferably relates to a power load prediction system and method based on power data. Background Art

[0002] Agricultural power forecast is a forecast of electricity demand and usage in the agricultural sector, usually based on historical data, agricultural development trends, technological progress factors, etc. This forecast is of great significance to agricultural production and power supply, and can help the agricultural sector plan power facilities, optimize resource allocation, and improve energy utilization efficiency. The main purpose of agricultural power forecast is to provide decision support for agricultural production and power supply. By predicting future electricity demand and usage, the agricultural sector can reasonably plan power facilities, optimize resource allocation, and improve energy utilization efficiency, thereby ensuring the smooth progress of agricultural production.

[0003] When supplying electricity to agriculture, the existing technology mostly converts the transmitted electricity into electricity for agricultural appliances through transformers. Electricity for agricultural appliances is usually used during a specific time period. For example, irrigation is usually done during a specific time period in the morning. This results in a large operating load on the transformer during this time period, which is prone to abnormal conditions. The existing technology lacks a strategy for first predicting irrigation electricity consumption and real-time monitoring of abnormal conditions of distribution transformers, and then comprehensively evaluating the power load of distribution transformers, resulting in the inability to timely predict potential faults.

[0004] In order to solve the above problems, the present invention designs a power load forecasting system and method based on power data. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention designs a power load prediction system and method based on power data. The present invention collects weather information, and evaluates the impact of abnormal weather on crops according to a weather evaluation model; collects crop information, and evaluates the growth status of crops according to a crop evaluation model; analyzes the irrigation demand of a set area according to an irrigation demand model; collects historical power data and historical irrigation volume data, and predicts power consumption according to a power consumption prediction model; collects distribution transformer data, and evaluates the abnormal conditions of distribution transformers according to a distribution transformer evaluation model; and evaluates whether the distribution transformer can operate normally according to a power load evaluation model. The present invention comprehensively evaluates the power load of distribution transformers by predicting irrigation power consumption and real-time monitoring of abnormal conditions of distribution transformers, which helps to respond to irrigation power demand in a timely manner and ensure that agricultural water use is not affected by insufficient power supply.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for predicting power load based on power data comprises the following specific steps:

[0008] Step 1: Collect weather information within a set period and evaluate the impact of abnormal weather on crops based on the weather assessment model;

[0009] Step 2: Collect crop information in a set area and evaluate the growth status of the crops according to a crop evaluation model;

[0010] Step 3: Obtain the impact of weather on crops and the growth status of crops, and analyze the irrigation demand of the set area according to the irrigation demand model;

[0011] Step 4: Collect historical power data and historical irrigation data, and predict power consumption based on the power consumption prediction model;

[0012] Step 5: Collect distribution transformer data, and evaluate the abnormal condition of the distribution transformer according to the distribution transformer evaluation model;

[0013] Step 6: Obtain the irrigation power consumption and the abnormal conditions of the distribution transformer, and evaluate whether the distribution transformer can operate normally according to the power load assessment model.

[0014] Preferably, the step 1 includes the following specific steps:

[0015] S11, collecting weather information within a set period, the weather information including temperature, precipitation and wind speed;

[0016] S12, importing temperature, precipitation and wind speed into the weather anomaly impact value calculation formula to calculate the impact value of weather on crops, the weather anomaly impact value calculation formula is:

[0017] ; In the formula, is the temperature factor, is the precipitation factor, is the wind speed factor, is the ith temperature data collected within the set period, , is the total number of temperature data collected within the set period, is the total precipitation collected within the set period, is the kth wind speed data collected within the set period, is the total number of wind speed data collected within the set period. hour, The value is 0, when hour, The value is 0, when hour, The value is 0, when hour, and The values ​​are all 0. ,when hour, The value is 0, To increase the maximum temperature range required for crop irrigation, To increase the minimum temperature range for crop irrigation requirements, To increase the minimum value of the precipitation range required for crop irrigation, To increase the maximum value of the precipitation range required for crop irrigation, The minimum value of the precipitation range to reduce the demand for crop irrigation, The maximum value of the precipitation range to reduce crop irrigation demand, To increase the maximum value of the wind speed range required for crop irrigation, The minimum value of the wind speed range that increases the demand for crop irrigation.

[0018] Preferably, the step 2 comprises the following specific steps:

[0019] S21, collecting crop information of a set area, wherein the crop information includes soil moisture and leaf area;

[0020] S22, introducing soil moisture and leaf area into a crop growth status abnormal value calculation formula to calculate the crop growth status abnormal value, the crop growth status abnormal value calculation formula is:

[0021] ;

[0022] In the formula, is the soil moisture factor, is the leaf area factor, is the soil moisture collected at the vth test point, is the total number of test points set, is the standard soil moisture, is the leaf area of ​​the jth plant collected, is the total number of plants collected, is the standard leaf area of ​​the plant, hour, The value is 0, when hour, The value is 0.

[0023] Preferably, the step three includes the following specific steps:

[0024] The abnormal weather impact value and the abnormal crop growth state value are introduced into the crop irrigation demand calculation formula to calculate the irrigation demand of the set area. The crop irrigation demand calculation formula is:

[0025] ;

[0026] In the formula, is the weather anomaly influencing factor, It is an abnormal factor for crop growth. The basic irrigation demand.

[0027] Preferably, the step 4 includes the following specific steps:

[0028] S41. Collect historical electricity consumption data and historical irrigation volume data, construct an irrigation neural network model whose input is crop irrigation demand and output is irrigation electricity consumption, divide the historical electricity consumption data and historical irrigation volume data into 60% parameter training set and 40% parameter test set, input 60% parameter training set into the irrigation neural network model for training to obtain an irrigation initial neural network model, input 40% parameter test set into the irrigation initial neural network model for testing, and output the optimal irrigation initial neural network model with the highest accuracy in judging irrigation electricity consumption as the irrigation neural network model;

[0029] S42. The output strategy formula of a specific neuron in the irrigation neural network model is:

[0030] ;

[0031] In the formula, is the irrigation power output of the x+1 layer y-term neuron, is the connection weight between the x-th layer neuron u and the x+1 layer y-term neuron, is the total number of neurons in the xth layer, is the crop irrigation demand input of the x-th layer neuron u, is the bias of the linear relationship between the x-th layer neuron u and the x+1 layer y-term neuron, is the Sigmoid activation function;

[0032] S43, inputting the crop irrigation demand into the irrigation neural network model to obtain the output of irrigation electricity consumption;

[0033] S44, collecting irrigation time, and importing the irrigation time and irrigation power consumption into a power calculation formula to obtain power. The power calculation formula is: ;

[0034] In the formula, For irrigation electricity consumption, For irrigation time.

[0035] Preferably, the step five includes the following specific steps:

[0036] S51, collecting distribution transformer data, wherein the distribution transformer data includes temperature, noise and voltage;

[0037] S52, introducing the temperature, noise and voltage of the distribution transformer into the distribution transformer abnormal value calculation formula to calculate the abnormal value of the distribution transformer, the distribution transformer abnormal value calculation formula is:

[0038] ;

[0039] In the formula, is the distribution transformer temperature factor, is the noise factor of the distribution transformer, is the distribution transformer voltage factor, To collect the number of time periods of distribution transformers, is the temperature of the distribution transformer collected in the rth time period, is the standard temperature of the distribution transformer. hour, The value is 0. is the noise of the distribution transformer collected in the rth time period, is the standard noise of the distribution transformer. hour, The value is 0. is the voltage of the distribution transformer collected in the rth time period, It is the standard voltage of distribution transformer.

[0040] Preferably, the step six includes the following specific steps:

[0041] S61, importing the power and the abnormal value of the distribution transformer into the power load calculation formula to calculate the power load of the distribution transformer, the power load calculation formula is:

[0042] ;

[0043] In the formula, is the calculated power, is the conversion factor of abnormal impact of distribution transformer, is the correction factor;

[0044] S62. Compare the calculated power load with the preset power load threshold. If the calculated power load is less than or equal to the preset power load threshold, it is determined that the distribution transformer is operating normally. If the calculated power load is greater than the preset power load threshold, it is determined that the distribution transformer is operating abnormally and the location of the abnormal distribution transformer is reported.

[0045] A power load forecasting system based on power data, used to implement a power load forecasting method based on power data, including a control module, an information collection module, a weather assessment module, a crop assessment module, an irrigation demand analysis module, a power consumption forecasting module, a distribution transformer assessment module, a power load assessment module and a judgment module;

[0046] Preferably, the control module is used to control the operation of the information collection module, the weather assessment module, the crop assessment module, the irrigation demand analysis module, the power consumption prediction module, the distribution transformer assessment module, the power load assessment module and the judgment module;

[0047] Preferably, the information collection module is used to collect weather information within a set period, crop information of a set area, historical power data, historical irrigation volume data, irrigation time and distribution transformer data;

[0048] The weather assessment module is used to import temperature, precipitation and wind speed into the weather anomaly impact value calculation formula to calculate the impact value of weather on crops;

[0049] The crop evaluation module is used to import soil moisture and leaf area into the crop growth state abnormal value calculation formula to calculate the crop growth state abnormal value;

[0050] The irrigation demand analysis module is used to import the weather anomaly impact value and the crop growth state abnormal value into the crop irrigation demand calculation formula to calculate the irrigation demand of the set area;

[0051] The power consumption prediction module is used to input the crop irrigation demand into the irrigation neural network model to obtain the output of irrigation power consumption, and then input the irrigation time and irrigation power consumption into the power calculation formula to obtain power;

[0052] The distribution transformer evaluation module is used to import the temperature, noise and voltage of the distribution transformer into the distribution transformer abnormal value calculation formula to calculate the abnormal value of the distribution transformer;

[0053] The power load evaluation module is used to import the power and distribution transformer abnormal values ​​into the power load calculation formula to calculate the power load of the distribution transformer;

[0054] The judgment module is used to compare the calculated power load with the preset power load threshold. If the calculated power load is less than or equal to the preset power load threshold, it is judged that the distribution transformer is operating normally; if the calculated power load is greater than the preset power load threshold, it is judged that the distribution transformer is operating abnormally and the location of the abnormal distribution transformer is reported.

[0055] Beneficial effects of the present invention: The present invention collects weather information, and evaluates the impact of abnormal weather on crops according to the weather evaluation model; collects crop information, and evaluates the growth status of crops according to the crop evaluation model; analyzes the irrigation demand of a set area according to the irrigation demand model; collects historical power data and historical irrigation volume data, and predicts power consumption according to the power consumption prediction model; collects distribution transformer data, and evaluates the abnormality of the distribution transformer according to the distribution transformer evaluation model; and evaluates whether the distribution transformer can operate normally according to the power load evaluation model;

[0056] The present invention predicts irrigation electricity consumption and monitors abnormal conditions of distribution transformers in real time, comprehensively assesses the power load of distribution transformers, and helps to respond to irrigation electricity demand in a timely manner during the peak irrigation period, ensuring that agricultural water use is not affected by insufficient power supply;

[0057] By real-time monitoring of the transformer's operating status, potential faults can be predicted, maintenance can be performed in advance, and power inconvenience caused by sudden faults can be avoided;

[0058] Based on the electricity load data, the power supply plan can be updated in a timely manner, the operation of the power system can be optimized, and the irrigation efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 A schematic diagram of a flow chart of a method for predicting power load based on power data according to the present invention;

[0061] Figure 2 This is a flow chart of step 4 in a method for predicting power load based on power data of the present invention;

[0062] Figure 3 The present invention is a schematic diagram of the overall framework of a power load forecasting system based on power data. DETAILED DESCRIPTION

[0063] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present invention will be more comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0064] See also Figure 1 The present invention provides an embodiment: a method for predicting power load based on power data, which comprises the following specific steps:

[0065] Step 1: Collect weather information within a set period and evaluate the impact of abnormal weather on crops based on the weather assessment model;

[0066] In this embodiment, step one includes the following specific steps:

[0067] S11, collecting weather information within a set period, the weather information including temperature, precipitation and wind speed;

[0068] It should be specifically noted that weather information for a set period in the future can be obtained through weather forecast websites or official meteorological websites;

[0069] S12. The temperature, precipitation and wind speed are introduced into the calculation formula of the weather anomaly impact value to calculate the impact value of the weather on the crops. The calculation formula of the weather anomaly impact value is:

[0070] ; In the formula, is the temperature factor, is the precipitation factor, is the wind speed factor, is the ith temperature data collected within the set period, , is the total number of temperature data collected within the set period, is the total precipitation collected within the set period, is the kth wind speed data collected within the set period, is the total number of wind speed data collected within the set period. hour, The value is 0, when hour, The value is 0, when hour, The value is 0, when hour, and The values ​​are all 0. ,when hour, The value is 0, To increase the maximum temperature range required for crop irrigation, To increase the minimum temperature range for crop irrigation requirements, To increase the minimum value of the precipitation range required for crop irrigation, To increase the maximum value of the precipitation range required for crop irrigation, The minimum value of the precipitation range to reduce the demand for crop irrigation, The maximum value of the precipitation range to reduce crop irrigation demand, To increase the maximum value of the wind speed range required for crop irrigation, The minimum value of the wind speed range that increases the demand for crop irrigation.

[0071] It should be specifically noted that temperature affects the transpiration of crops. High temperature accelerates the evaporation of water in crops and increases the water demand of crops. For most crops, the upper limit of temperature is usually around 30-35°C. If the temperature exceeds this, the crops may be subjected to heat stress and the transpiration is aggravated. Therefore, for example, this embodiment The value is 35°C, The value is 30°C;

[0072] Precipitation directly affects the replenishment of soil moisture. Too much rainfall may cause the soil to be too wet, while insufficient rainfall may cause soil drought. For most crops, when the monthly precipitation is 10-20% lower than normal, signs of mild drought may begin to appear, such as leaf wilt. When the monthly precipitation is 20-40% lower than normal, crop growth may be significantly affected, with increased leaf wilting and reduced yield. In terms of months, monthly precipitation below 50-100 mm will have a drought effect on crops; when the monthly precipitation exceeds 20-40% of normal, it may cause the soil to be too wet, affecting root respiration and nutrient absorption; when the monthly precipitation exceeds 40-60% of normal, it may cause crop root rot, increased diseases and a significant decrease in yield. In terms of months, monthly precipitation exceeding 200-300 mm may have a moderate waterlogging effect on crops. Therefore, illustratively, when the set period is month, this embodiment The value is 50mm. The value is 100mm. The value is 200mm. The value is 300mm;

[0073] Wind speed affects the rate of evaporation of water from the surface of crops. The higher the wind speed, the faster the crops lose water. Generally speaking, wind speeds exceeding 20-30 km / h will cause damage to crops and significantly increase water evaporation. Therefore, for example, this embodiment The value is 30 km / h. The value is 20 km / h.

[0074] Step 2: Collect crop information in a set area and evaluate the growth status of the crops according to a crop evaluation model;

[0075] In this embodiment, step 2 includes the following specific steps:

[0076] S21, collecting crop information in a set area, where the crop information includes soil moisture and leaf area;

[0077] Among them, it should be specifically explained that soil moisture collection is carried out by selecting multiple points evenly distributed in the farmland, vertically inserting the soil moisture sensor into the soil, usually at a depth of 5-10 cm (the specific depth is determined by the crop type and growth stage), starting the data collection device, and the sensor automatically reads the soil moisture data and transmits it to the data processing platform or smart device; collecting soil moisture helps to understand the soil moisture status, formulate a reasonable irrigation plan, avoid the impact of excessive or insufficient moisture on crop growth, and improve the efficiency of water resource utilization;

[0078] Leaf area collection is done by randomly selecting evenly distributed plants in the farmland, scanning or photographing the leaves of the plants using a leaf area meter or scanner, analyzing the leaf images using specialized software, calculating the leaf area, and recording the calculated leaf area data in correspondence with the plant number. Leaf area helps to understand the growth status of crops, and adjusting management measures such as irrigation according to changes in leaf area can improve the health of crops.

[0079] S22, introducing soil moisture and leaf area into a crop growth status abnormal value calculation formula to calculate the crop growth status abnormal value, the crop growth status abnormal value calculation formula is:

[0080] ;

[0081] In the formula, is the soil moisture factor, is the leaf area factor, is the soil moisture collected at the vth test point, is the total number of test points set, is the standard soil moisture, is the leaf area of ​​the jth plant collected, is the total number of plants collected, is the standard leaf area of ​​the plant, hour, The value is 0, when hour, The value is 0.

[0082] Specifically, the method for obtaining the standard soil moisture is as follows: multiple sampling points are evenly selected according to the size of the farmland and the soil type. At each sampling point, soil samples are taken from the surface to a certain depth (usually 0-20 cm). The soil moisture is directly measured using a soil moisture meter. The average of the measured soil moisture data is taken as the standard soil moisture.

[0083] The method for obtaining the standard leaf area of ​​the plant is as follows: according to the crop variety and growth stage, a certain number of plants representing the growth conditions are selected in the farmland, the leaf area is directly measured using a leaf area meter, and the average value of plants of the same variety and growth stage is taken as the standard leaf area of ​​the plant.

[0084] Step 3: Obtain the impact of weather on crops and the growth status of crops, and analyze the irrigation demand of the set area according to the irrigation demand model;

[0085] In this embodiment, step three includes the following specific steps:

[0086] The abnormal weather impact value and the abnormal crop growth status value are introduced into the crop irrigation demand calculation formula to calculate the irrigation demand of the set area. The crop irrigation demand calculation formula is:

[0087] ;

[0088] In the formula, is the weather anomaly influencing factor, It is an abnormal factor for crop growth. The basic irrigation demand.

[0089] Among them, it should be specifically noted that the basic irrigation demand It is obtained by taking the average of the historical basic irrigation demand, and the method for obtaining the historical basic irrigation demand is:

[0090] Collect historical meteorological data (such as average temperature, average rainfall, average evaporation, relative humidity, wind speed), historical soil data (such as soil type, soil water retention capacity, soil depth), historical crop data (such as crop type, crop growth cycle, crop water requirement, crop root depth), geographic location and time data (such as latitude and longitude, altitude, seasonal changes);

[0091] Calculate potential evapotranspiration (potential evapotranspiration refers to the total amount of water absorbed by crops from the soil and emitted to the atmosphere under water-free conditions). The evapotranspiration calculation formula is as follows:

[0092] ;

[0093] In the formula, is the rate of change of saturated water vapor pressure with temperature (kPa / ℃), is the net radiation (MJ / m² / day), is the soil heat flux density (MJ / m² / day), is the psychrometric constant (kPa / ℃), is the wind speed at a height of 2 meters (m / s). The specific height is set according to the measurement height. is the average temperature (℃), is the saturated water vapor pressure (kPa), is the actual water vapor pressure (kPa);

[0094] The crop coefficient reflects the ratio of the water requirement of crops at different growth stages to the water requirement of reference crops. The crop coefficient is divided into three stages: initial stage, middle development stage and final stage;

[0095] Calculate actual evapotranspiration. Actual evapotranspiration is the actual water requirement of crops at a specific growth stage. The actual evapotranspiration calculation formula is as follows:

[0096] ;

[0097] In the formula, is the crop coefficient;

[0098] The baseline irrigation demand refers to the amount of irrigation water that needs to be supplemented to meet the water demand of crops in the absence of rainfall. The calculation formula for the baseline irrigation demand is as follows:

[0099] ;

[0100] In the formula, is the effective rainfall.

[0101] Step 4: Collect historical power data and historical irrigation data, and predict power consumption based on the power consumption prediction model;

[0102] See also Figure 2 In this embodiment, step 4 includes the following specific steps:

[0103] S41. Collect historical electricity consumption data and historical irrigation volume data, construct an irrigation neural network model whose input is crop irrigation demand and output is irrigation electricity consumption, divide the historical electricity consumption data and historical irrigation volume data into 60% parameter training set and 40% parameter test set, input 60% parameter training set into the irrigation neural network model for training to obtain an irrigation initial neural network model, input 40% parameter test set into the irrigation initial neural network model for testing, and output the optimal irrigation initial neural network model with the highest accuracy in judging irrigation electricity consumption as the irrigation neural network model;

[0104] Among them, it should be specifically explained that the method for obtaining historical power data of farmland is as follows: determine the time range (such as the past three months, the past year, etc.) and resolution (hourly, daily, and weekly statistics) of the required historical power consumption data, obtain historical power consumption data, analyze the historical power consumption data through statistical analysis tools or deep learning models, and extract information (such as power consumption changes, power consumption trends, peak load periods, etc.);

[0105] The method for obtaining the historical irrigation data of farmland is as follows: determine the time range (such as the past three months, the past year, etc.) and resolution (hourly, daily, weekly statistics) of the required historical irrigation data, query the farmland management records or the operation records of the irrigation system, etc.;

[0106] Analyze the relationship between historical irrigation volume and electricity consumption based on the acquired data, including trend analysis and correlation analysis;

[0107] S42. The output strategy formula of a specific neuron in the irrigation neural network model is:

[0108] ;

[0109] In the formula, is the irrigation power output of the x+1 layer y-term neuron, is the connection weight between the x-th layer neuron u and the x+1 layer y-term neuron, is the total number of neurons in the xth layer, is the crop irrigation demand input of the x-th layer neuron u, is the bias of the linear relationship between the x-th layer neuron u and the x+1 layer y-term neuron, is the Sigmoid activation function;

[0110] S43, inputting the crop irrigation demand into the irrigation neural network model to obtain the output of irrigation electricity consumption;

[0111] S44, collecting irrigation time, and importing the irrigation time and irrigation power consumption into a power calculation formula to obtain power. The power calculation formula is: ;

[0112] In the formula, For irrigation electricity consumption, For irrigation time.

[0113] It should be specifically noted that the irrigation time is carried out according to a certain cycle according to a pre-set irrigation plan, such as irrigation once every certain number of days, each time for 45 minutes, so the irrigation time can be directly obtained by collecting historical irrigation time.

[0114] Step 5: Collect distribution transformer data, and evaluate the abnormal condition of the distribution transformer according to the distribution transformer evaluation model;

[0115] In this embodiment, step five includes the following specific steps:

[0116] S51, collecting distribution transformer data, where the distribution transformer data includes temperature, noise and voltage;

[0117] Among them, it should be specifically explained that the distribution transformer temperature data collection method is: install a temperature sensor near the transformer oil tank or winding (such as a temperature sensor such as a thermocouple or thermistor), set the collection frequency, and record the temperature data;

[0118] The noise data collection method is as follows: install the noise sensor on the side or top of the transformer tank, but keep a certain distance to avoid the reflection of sound from the transformer shell, set the collection frequency, and record the noise data (the noise measurement is usually averaged over a specific time period);

[0119] The voltage data collection method is: install a voltage sensor. For the low-voltage side, the sensor can be directly installed on the low-voltage outlet of the transformer. For the high-voltage side, the sensor needs to be installed on the cable or busbar on the high-voltage side to collect and record voltage data in real time;

[0120] S52, the temperature, noise and voltage of the distribution transformer are introduced into the distribution transformer abnormal value calculation formula to calculate the abnormal value of the distribution transformer. The distribution transformer abnormal value calculation formula is:

[0121] ;

[0122] In the formula, is the distribution transformer temperature factor, is the noise factor of the distribution transformer, is the distribution transformer voltage factor, To collect the number of time periods of distribution transformers, is the temperature of the distribution transformer collected in the rth time period, is the standard temperature of the distribution transformer. hour, The value is 0. is the noise of the distribution transformer collected in the rth time period, is the standard noise of the distribution transformer. hour, The value is 0. is the voltage of the distribution transformer collected in the rth time period, It is the standard voltage of distribution transformer.

[0123] Among them, it should be specifically explained that the standard temperature of the distribution transformer, the standard noise of the distribution transformer and the standard voltage of the distribution transformer are obtained by collecting the operating temperature, noise and voltage of the distribution transformers in normal operation in farmland in 50 different regions within a set time, and taking the average values ​​as the standard temperature, standard noise and standard voltage of the distribution transformer.

[0124] Step 6: Obtain the irrigation power consumption and the abnormal conditions of the distribution transformer, and evaluate whether the distribution transformer can operate normally according to the power load assessment model.

[0125] In this embodiment, step six includes the following specific steps:

[0126] S61. Import the power and distribution transformer abnormal value into the power load calculation formula to calculate the power load of the distribution transformer. The power load calculation formula is:

[0127] ;

[0128] In the formula, is the calculated power, is the conversion factor of abnormal impact of distribution transformer, is the correction factor;

[0129] S62. Compare the calculated power load with the preset power load threshold. If the calculated power load is less than or equal to the preset power load threshold, it is determined that the distribution transformer is operating normally. If the calculated power load is greater than the preset power load threshold, it is determined that the distribution transformer is operating abnormally and the location of the abnormal distribution transformer is reported.

[0130] Among them, it should be specifically noted that the temperature factor , precipitation factor , wind speed factor , soil moisture factor , leaf area factor 、Weather anomaly impact factors , abnormal growth factors of crops , distribution transformer temperature factor , Distribution transformer noise factor , distribution transformer voltage factor , Distribution transformer abnormality affects conversion factor , correction factor The method for determining the value of the power load threshold is as follows: select farmland in 50 different areas, collect weather information and import it into the weather assessment model to evaluate the abnormal weather impact value; collect crop information and import it into the crop assessment model to evaluate the abnormal value of crop growth status; import the abnormal weather impact value and the abnormal value of crop growth status into the irrigation demand model to analyze the irrigation demand in the set area; collect historical power data and historical irrigation data and import them into the power consumption prediction model to predict irrigation power consumption; collect distribution transformer data and import them into the distribution transformer assessment model to evaluate the abnormal value of distribution transformer; import the abnormal value of power and distribution transformer into the power load assessment model to evaluate the power load of distribution transformer; select 15 experts in the power industry to judge the irrigation demand and equipment abnormal value, and then combine them to predict the power load; import the power load predicted by the experts and the power load of the distribution transformer evaluated by the power load assessment model into the fitting software for analysis, find the set of data with the highest similarity, and find the corresponding temperature factor , precipitation factor , wind speed factor , soil moisture factor , leaf area factor 、Weather anomaly impact factors , abnormal growth factors of crops , distribution transformer temperature factor , Distribution transformer noise factor , distribution transformer voltage factor , Distribution transformer abnormality affects conversion factor , correction factor and the value of the power load threshold.

[0131] See also Figure 3 Another embodiment provided by the present invention is: a power load forecasting system based on power data, which is used to implement a power load forecasting method based on power data, including a control module, an information collection module, a weather assessment module, a crop assessment module, an irrigation demand analysis module, a power consumption forecasting module, a distribution transformer assessment module, a power load assessment module and a judgment module.

[0132] In this embodiment, the control module is used to control the operation of the information collection module, the weather assessment module, the crop assessment module, the irrigation demand analysis module, the electricity consumption prediction module, the distribution transformer assessment module, the power load assessment module and the judgment module.

[0133] In this embodiment, the information collection module is used to collect weather information within a set period, crop information of a set area, historical power data, historical irrigation volume data, irrigation time and distribution transformer data;

[0134] The weather assessment module is used to import temperature, precipitation and wind speed into the weather anomaly impact value calculation formula to calculate the impact value of weather on crops;

[0135] The crop evaluation module is used to import soil moisture and leaf area into the crop growth state abnormal value calculation formula to calculate the crop growth state abnormal value;

[0136] The irrigation demand analysis module is used to import the abnormal weather impact value and the abnormal crop growth state value into the crop irrigation demand calculation formula to calculate the irrigation demand of the set area;

[0137] The power consumption prediction module is used to input the crop irrigation demand into the irrigation neural network model to obtain the output of irrigation power consumption, and then import the irrigation time and irrigation power consumption into the power calculation formula to obtain power;

[0138] The distribution transformer evaluation module is used to import the temperature, noise and voltage of the distribution transformer into the distribution transformer abnormal value calculation formula to calculate the abnormal value of the distribution transformer;

[0139] The power load evaluation module is used to import the power and distribution transformer abnormal values ​​into the power load calculation formula to calculate the power load of the distribution transformer;

[0140] The judgment module is used to compare the calculated power load with the preset power load threshold. If the calculated power load is less than or equal to the preset power load threshold, it is judged that the distribution transformer is operating normally; if the calculated power load is greater than the preset power load threshold, it is judged that the distribution transformer is operating abnormally and the location of the abnormal distribution transformer is reported.

[0141] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may 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 programs are loaded or executed on a computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may 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 may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or / and a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may 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 may be a solid-state hard disk.

[0142] In the description of this specification, the descriptions with reference to the terms "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example, and the specific features, structures, materials or characteristics described may be combined in an appropriate manner in any one or more embodiments or examples.

Claims

1. A method for predicting power load based on power data, characterized in that: The specific steps include: Step 1: Collect weather information within a set period and evaluate the impact of abnormal weather on crops based on the weather assessment model; Step 2: Collect crop information in a set area and evaluate the growth status of the crops according to a crop evaluation model; Step 3: Obtain the impact of weather on crops and the growth status of crops, and analyze the irrigation demand of the set area according to the irrigation demand model; Step 4: Collect historical power data and historical irrigation data, and predict power consumption based on the power consumption prediction model; Step 5: Collect distribution transformer data, and evaluate the abnormal condition of the distribution transformer according to the distribution transformer evaluation model; Step 6: Obtain the irrigation power consumption and the abnormal conditions of the distribution transformer, and evaluate whether the distribution transformer can operate normally according to the power load assessment model.

2. A method for predicting power load based on power data as claimed in claim 1, characterized in that: The step 1 includes the following specific steps: S11, collecting weather information within a set period, the weather information including temperature, precipitation and wind speed; S12, importing temperature, precipitation and wind speed into the weather anomaly impact value calculation formula to calculate the impact value of weather on crops, the weather anomaly impact value calculation formula is: ; In the formula, is the temperature factor, is the precipitation factor, is the wind speed factor, is the ith temperature data collected within the set period, , is the total number of temperature data collected within the set period, is the total precipitation collected within the set period, is the kth wind speed data collected within the set period, is the total number of wind speed data collected within the set period. hour, The value is 0, when hour, The value is 0, when hour, The value is 0, when hour, and The values ​​are all 0. ,when hour, The value is 0, To increase the maximum temperature range required for crop irrigation, To increase the minimum temperature range for crop irrigation requirements, To increase the minimum value of the precipitation range required for crop irrigation, To increase the maximum value of the precipitation range required for crop irrigation, The minimum value of the precipitation range to reduce the demand for crop irrigation, The maximum value of the precipitation range to reduce the demand for crop irrigation, To increase the maximum value of the wind speed range required for crop irrigation, The minimum value of the wind speed range that increases the demand for crop irrigation.

3. A method for predicting power load based on power data as claimed in claim 2, characterized in that: The step 2 includes the following specific steps: S21, collecting crop information of a set area, wherein the crop information includes soil moisture and leaf area; S22, introducing soil moisture and leaf area into a crop growth status abnormal value calculation formula to calculate the crop growth status abnormal value, the crop growth status abnormal value calculation formula is: ； In the formula, is the soil moisture factor, is the leaf area factor, is the soil moisture collected at the vth test point, is the total number of test points set, is the standard soil moisture, is the leaf area of ​​the jth plant collected, is the total number of plants collected, is the standard leaf area of ​​the plant, hour, The value is 0, when hour, The value is 0.

4. A method for predicting electric load based on electric power data as claimed in claim 3, characterized in that: The step three includes the following specific steps: The abnormal weather impact value and the abnormal crop growth state value are introduced into the crop irrigation demand calculation formula to calculate the irrigation demand of the set area. The crop irrigation demand calculation formula is: ； In the formula, is the weather anomaly influencing factor, It is an abnormal factor for crop growth. The basic irrigation demand.

5. The method for predicting power load based on power data according to claim 4, characterized in that: The step 4 includes the following specific steps: S41. Collect historical electricity consumption data and historical irrigation volume data, construct an irrigation neural network model whose input is crop irrigation demand and output is irrigation electricity consumption, divide the historical electricity consumption data and historical irrigation volume data into 60% parameter training set and 40% parameter test set, input 60% parameter training set into the irrigation neural network model for training to obtain an irrigation initial neural network model, input 40% parameter test set into the irrigation initial neural network model for testing, and output the optimal irrigation initial neural network model with the highest accuracy in judging irrigation electricity consumption as the irrigation neural network model; S42. The output strategy formula of a specific neuron in the irrigation neural network model is: ； In the formula, is the irrigation power output of the x+1 layer y-term neuron, is the connection weight between the x-th layer neuron u and the x+1 layer y-term neuron, is the total number of neurons in the xth layer, is the crop irrigation demand input of the x-th layer neuron u, is the bias of the linear relationship between the x-th layer neuron u and the x+1 layer y-term neuron, is the Sigmoid activation function; S43, inputting the crop irrigation demand into the irrigation neural network model to obtain the output of irrigation electricity consumption; S44, collecting irrigation time, and importing the irrigation time and irrigation power consumption into a power calculation formula to obtain power. The power calculation formula is: ; In the formula, For irrigation electricity consumption, For irrigation time.

6. A method for predicting electric load based on electric power data as claimed in claim 5, characterized in that: The step five includes the following specific steps: S51, collecting distribution transformer data, wherein the distribution transformer data includes temperature, noise and voltage; S52, importing the temperature, noise and voltage of the distribution transformer into the distribution transformer abnormal value calculation formula to calculate the abnormal value of the distribution transformer, the distribution transformer abnormal value calculation formula is: ； In the formula, is the distribution transformer temperature factor, is the noise factor of the distribution transformer, is the distribution transformer voltage factor, To collect the number of time periods of distribution transformers, is the temperature of the distribution transformer collected in the rth time period, is the standard temperature of the distribution transformer. hour, The value is 0. is the noise of the distribution transformer collected in the rth time period, is the standard noise of the distribution transformer. hour, The value is 0. is the voltage of the distribution transformer collected in the rth time period, It is the standard voltage of distribution transformer.

7. A method for predicting electric load based on electric power data as claimed in claim 6, characterized in that: The step six includes the following specific steps: S61, importing the power and the abnormal value of the distribution transformer into the power load calculation formula to calculate the power load of the distribution transformer, the power load calculation formula is: ； In the formula, is the calculated power, is the conversion factor of abnormal impact of distribution transformer, is the correction factor; S62. Compare the calculated power load with the preset power load threshold. If the calculated power load is less than or equal to the preset power load threshold, it is determined that the distribution transformer is operating normally. If the calculated power load is greater than the preset power load threshold, it is determined that the distribution transformer is operating abnormally and the location of the abnormal distribution transformer is reported.

8. A power load forecasting system based on power data, used to implement the power load forecasting method based on power data as claimed in any one of claims 1 to 7, characterized in that: It includes a control module, an information collection module, a weather assessment module, a crop assessment module, an irrigation demand analysis module, a power consumption forecasting module, a distribution transformer assessment module, a power load assessment module and a judgment module; the control module is used to control the operation of the information collection module, the weather assessment module, the crop assessment module, the irrigation demand analysis module, the power consumption forecasting module, the distribution transformer assessment module, the power load assessment module and the judgment module; The information collection module is used to collect weather information within a set period, crop information in a set area, historical power data, historical irrigation volume data, irrigation time and distribution transformer data; The weather assessment module is used to import temperature, precipitation and wind speed into the weather anomaly impact value calculation formula to calculate the impact value of weather on crops; The crop evaluation module is used to import soil moisture and leaf area into the crop growth state abnormal value calculation formula to calculate the crop growth state abnormal value; The irrigation demand analysis module is used to import the weather anomaly impact value and the crop growth state abnormal value into the crop irrigation demand calculation formula to calculate the irrigation demand of the set area.

9. The power load forecasting system based on power data according to claim 8, characterized in that: The power consumption prediction module is used to input the crop irrigation demand into the irrigation neural network model to obtain the output of irrigation power consumption, and then input the irrigation time and irrigation power consumption into the power calculation formula to obtain power; The distribution transformer evaluation module is used to import the temperature, noise and voltage of the distribution transformer into the distribution transformer abnormal value calculation formula to calculate the abnormal value of the distribution transformer; The power load evaluation module is used to import the power and distribution transformer abnormal values ​​into the power load calculation formula to calculate the power load of the distribution transformer; The judgment module is used to compare the calculated power load with the preset power load threshold. If the calculated power load is less than or equal to the preset power load threshold, it is judged that the distribution transformer is operating normally; if the calculated power load is greater than the preset power load threshold, it is judged that the distribution transformer is operating abnormally and the location of the abnormal distribution transformer is reported.

Images