Power operation multi-source data monitoring method and device for power distribution area

Abstract

The present application relates to the technical field of circuit power supply system, in particular to a power operation multi-source data monitoring method and equipment of distribution area, wherein the power operation multi-source data monitoring method of distribution area comprises the following steps: obtaining the growth cycle data of high economic crops in the agricultural distribution area, constructing the target DLI value (daily light integral value) curve of the high economic crops in the whole growth cycle, predicting the DLI value provided by the next day's natural light, and calculating the artificial light supplement DLI value required for the next day. The present application discloses a power operation multi-source data monitoring method of distribution area, which introduces the monitoring and calculation of the multi-source data related to the growth parameters of high economic crops in the distribution area, so as to improve the balance degree of power supply and power consumption in the agricultural distribution area, thereby improving the power supply quality of the agricultural distribution area and achieving the purpose of prolonging the service life of the transformer and the electric equipment in the distribution area.

Description

Technical Field

[0001] This invention relates to the field of circuit power supply system technology, and in particular to a method and equipment for monitoring multi-source data of power operation in a power distribution substation. Background Technology

[0002] In a power supply system, the power supply and power consumption within a distribution area should be kept as balanced as possible to ensure stable power supply. If the power supply within the distribution area is greater than the power consumption of the load, the transformer and electrical equipment will operate under high voltage, significantly reducing their service life. If the power supply within the distribution area is less than the power consumption of the load, the current within the distribution area will be too high, causing the transformer windings to overheat and increasing heat loss during power transmission.

[0003] However, the existing agricultural power distribution areas have a poor balance between power supply and consumption. Taking greenhouse cultivation areas as an example, to ensure the rapid growth of high-value crops in greenhouses, supplemental lighting is often required in addition to natural light. Since the light requirements of high-value crops vary at different growth stages, the duration of artificial lighting naturally varies throughout their growth cycle. Existing agricultural power distribution areas are unable to monitor and process this multi-source data, resulting in a poor balance between power supply and consumption, leading to poor power quality and shorter lifespans for transformers and electrical equipment within the distribution areas. Summary of the Invention

[0004] Therefore, it is necessary to provide a multi-source data monitoring method and equipment for power operation in agricultural power distribution substations to address the existing problems in power supply quality deviations and the short service life of transformers and electrical equipment in these substations.

[0005] The above objectives are achieved through the following technical solutions: A method for monitoring the power operation of a power distribution substation, applied to a power distribution substation in an agricultural greenhouse, includes the following steps: Acquire growth cycle data of high-value crops in agricultural distribution areas and construct target DLI (Daily Light Intake) value curves for the entire growth cycle of high-value crops. Predict the DLI value provided by natural light the following day; Calculate the required artificial light DLI value for the next day (the artificial light DLI value is equal to the difference between the target DLI value for the next day and the DLI value provided by natural light the next day). Based on the DLI value of artificial lighting the next day, predict the power load of artificial lighting the next day; The predicted power load data for supplemental lighting the following day is sent to the distribution substation for power dispatching.

[0006] Preferably, the DLI value provided by natural light the following day is predicted using the following method ( ); ; in, The theoretical maximum DLI value for the following day, calculated based on the season and solar altitude angle. Weather impact correction factor (0) ).

[0007] Preferred weather impact correction factor It is obtained by using an index-weighted moving average that integrates weather forecast information and historical weather information from the most recent week. The calculation formula is as follows: ; in, The parameters (0) obtained by calibration using historical data with the goal of minimizing prediction error. 0 ), These are the prediction coefficients derived from the weather forecast for the following day. The actual observed coefficients for the i-th day in the past.

[0008] Preferably, the actual observed coefficients of the i-th day in the past are obtained using the following method. ; ; in, The natural light DLI value actually measured on the i-th day in the past. This represents the theoretical maximum DLI value for the i-th past day.

[0009] Preferably, the natural light DLI value actually measured on the i-th day in the past is obtained by real-time monitoring and integration calculation using photosynthetically active radiation sensors arranged in the greenhouse.

[0010] Preferably, the theoretical maximum DLI value for the past i-th day is obtained using the following method. ; ; in, The average photosynthetically active radiation flux density of the local area under ideal sunny conditions throughout the day. This represents the theoretical sunshine duration of the i-th day in the past.

[0011] Preferably, the greenhouse is equipped with supplemental lighting to provide artificial light for high-value crops.

[0012] Preferably, the electrical load for artificial lighting the next day is equal to the product of the power of the supplemental light and the duration of artificial lighting.

[0013] Preferably, the distribution area is equipped with a photovoltaic energy storage module, configured so that when there is a power surplus, the photovoltaic energy storage module acts as a load for energy storage, and when there is a power shortage, the photovoltaic energy storage module acts as a power source to supply power to the supplementary lighting.

[0014] A power operation multi-source data monitoring device for a distribution transformer substation is used to implement the power operation multi-source data monitoring method for the aforementioned distribution transformer substation.

[0015] The beneficial effects of this invention are: 1. This invention introduces the monitoring and calculation of multi-source data related to the growth parameters of high-value crops in the distribution substation area, and constructs a mathematical model that can predict the electricity consumption of artificial supplemental lighting for high-value crops in agricultural greenhouses. By integrating historical observation data through exponential weighted moving average, the model can reflect both the persistence of weather and give higher weight to recent changes, dynamically responding to changes in weather systems. At the same time, it innovatively introduces weather forecast information, enhancing the model's forward-looking predictive ability, transforming the micro-demands of agricultural production into predictable power loads, enabling the distribution network to shift from passive response to active scheduling, thereby improving the balance between power supply and power consumption in agricultural distribution substation areas, improving the power supply quality of agricultural distribution substation areas, and extending the service life of transformers and electrical equipment in the distribution substation areas.

[0016] 2. The present invention incorporates a photovoltaic energy storage module, which provides a temporary buffer for grid power regulation, further smooths out fluctuations, and improves the resilience and reliability of system operation.

[0017] 3. The prediction framework provided by this invention has strong scalability, making it easy to incorporate more dimensions of weather forecast data (such as cloud cover and precipitation probability) or introduce other environmental sensor data to continuously enhance the accuracy of predictions. Attached Figure Description

[0018] Figure 1 This is a flowchart of the process of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below through embodiments and in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0020] The component designations used in this document, such as "first" and "second," are merely for distinguishing the described objects and do not have any sequential or technical meaning. The terms "connection" and "linkage" used in this invention, unless otherwise specified, include both direct and indirect connections (linkages). It should be understood that the terms "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are used only for the convenience of describing the invention and simplifying the description. They do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the invention.

[0021] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0022] This invention aims to solve the problems of poor power quality and increased equipment wear and tear in agricultural greenhouse power distribution areas caused by fluctuations in supplemental lighting load. The core idea is to achieve accurate prediction of the next day's supplemental lighting load by integrating crop physiological data, environmental monitoring data, meteorological forecast data, and electrical operation data. This predicted data is then fed into the power dispatching system, thereby improving the balance between power supply and consumption in the distribution area. The following will describe the solution in detail, layer by layer, with reference to the accompanying drawings and the claims.

[0023] like Figure 1 As shown, a multi-source data monitoring method for power distribution area operation, applied to agricultural greenhouse power distribution area, includes the following steps: S100: Obtain growth cycle data of high-value crops in the agricultural distribution area and construct the target DLI value (daily light accumulation value) curve of the high-value crops throughout the entire growth cycle. The high-value crops referred to in this invention include strawberries, blueberries, high-value-added flowers, specific medicinal herbs, and off-season fruits and vegetables. Their growth is extremely sensitive to light (photoperiod and light intensity). To ensure that they can mature and be sold on the market at the predetermined time, it is necessary to accurately monitor their growth status and supplement light in time when there is insufficient light. The growth cycle data and corresponding target DLI values ​​of high-value crops can be obtained by integrating multiple channels, such as agronomic databases, or by obtaining recommended DLI ranges for each growth stage of standardized crops (such as seedling stage, vegetative growth stage, flowering and fruit setting stage, fruit enlargement stage, and maturity stage) from public or commercial crop model databases. At the same time, the experience data of local planting experts can also be digitized to form optimized DLI curves for local climate and varieties. In addition, this system or other monitoring equipment can be used to accumulate daily light data on the best performance of similar crops in actual planting over the years. After analysis, the ideal target DLI value can be deduced. Finally, the above data is integrated to form a continuous or piecewise continuous curve with the number of days after planting or calendar date as the horizontal axis and the target DLI value as the vertical axis. This curve is pre-stored in the cloud or edge computing unit of the power operation multi-source data monitoring system in the form of a data table or function model. When the greenhouse manager selects the crop type and planting date on the system interface, the system automatically calls the corresponding target DLI curve, indexes the target DLI curve according to the current date, and determines the target DLI value for the next day, denoted as . .

[0024] S200, predicts the DLI value provided by natural light the following day; The specific methods and steps are explained below.

[0025] S210: Calculate the theoretical maximum DLI value: Based on the latitude and longitude of the distribution station area and the annual day of the next day (t+1), calculate the sunshine duration of the next day according to the astronomical formula of the sun's motion. (h) and the average photosynthetically active radiation flux density over the entire day under absolutely clear skies. ( Then the theoretical maximum DLI value for the next day The calculation formula is as follows: ; in, This is the theoretical maximum DLI value, which physically represents the total number of photosynthetically active radiation photons that each square meter of the Earth's surface may receive under absolutely clear sky conditions the following day. The coefficient 0.0036 is a constant that incorporates unit conversions. This constant is crucial for ensuring the consistency of the formula's units. The unit is per hour, while the average photosynthetically active radiation flux density The unit is Therefore, hours need to be converted to seconds, hence the conversion relationship exists. ,in Used to convert micromoles to moles, this coefficient is essentially the product of time unit conversion and mole unit conversion.

[0026] Among them, the daytime of sunlight the following day Defined as the total duration from sunrise to sunset, its calculation is independent of weather and is determined solely by geographical latitude and date, specifically obtained through the following self-step process.

[0027] S211: Calculate the solar declination angle ( This angle represents the latitude of the subsolar point and is an existing function of the chrono-day.

[0028] S212: Calculate the sunset hour angle ( ); ; in The latitude of the distribution area.

[0029] S213: Calculate the daytime illumination for the next day ( ); ; S214: Calculate the average photosynthetically active radiation flux density ; Average photosynthetically active radiation flux density This represents the average photosynthetically active radiation photon flux density received per unit area and per unit time across the entire day under ideal atmospheric conditions. Its calculation comprehensively considers the solar radiation intensity at the top of the atmosphere, variations in the solar altitude angle, and atmospheric attenuation of radiation (using an ideal atmospheric transmittance model), and is limited to the photosynthetically active wavelength band of 400-700 nm. This value is obtained by analyzing instantaneous data at different times during sunrise to sunset. Integrate the value and divide by the total time (s) to obtain a daily average, in units of . .

[0030] S220: Obtain historical actual observation coefficients: Specifically, deploy photosynthetically active radiation (DLI) sensors inside the greenhouse to monitor and calculate the actual received natural light DLI value for the i-th day (i=0, 1, ..., 6) in real time. Simultaneously calculate the theoretical maximum DLI value for that day. Then the observed coefficient of actual weather impact on the i-th day in the past for; ; This coefficient reflects the degree to which the actual weather conditions on a given historical day reduced sunlight.

[0031] Photosynthetically active radiation (PAR) sensors should be placed in representative locations within the target greenhouse or observation area. Calibrated PAR sensors should be installed horizontally to avoid obstruction, and their monitoring range should represent the light exposure of the crop canopy. The sensors continuously monitor PAR flux density at high frequency. For example, the data logger automatically performs integration and accumulation once per second. The data system uses the date line (local time 00:00) as the dividing point to integrate the monitored values ​​and calculate the actual daily cumulative PAR value for the i-th day (i=0 represents the current day, i=1 represents the previous day, and so on).

[0032] It is a dimensionless number between 0 and 1, whose value intuitively reflects the degree to which the actual weather on a historical day weakened the maximum sunshine intensity under clear skies. When, it indicates that the weather on that day is close to absolutely clear skies, with very little weakening. If the actual light intensity is 30%, it means that the weather on that day (such as dense fog or dark clouds) resulted in actual sunlight being only 30% of the theoretical maximum.

[0033] S230: Obtaining Weather Forecast Prediction Coefficients: The system obtains the next day's weather forecast information (including weather phenomena, cloud cover, etc.) issued by authoritative meteorological departments through an application programming interface (API). Based on preset mapping rules, it converts the weather forecast into a preliminary weather impact prediction coefficient. For example, a mapping can be established: sunny (0.9), cloudy (0.6), overcast (0.3), light rain (0.15), etc. This mapping table can be calibrated based on local historical data.

[0034] S231: Obtaining Structured Weather Forecast Data via Standardized Acceptance: The system uses a built-in application programming interface to automatically request and retrieve next-day weather forecasts issued by authoritative meteorological departments (such as the China Meteorological Administration and the National Atmospheric Administration) for the location of the distribution area on a regular schedule. The retrieved data is in a structured, machine-readable format and contains at least the following key fields: 1. Weather phenomenon codes or descriptions: such as sunny, cloudy turning overcast, light rain, etc.

[0035] 2. Quantitative cloud cover information: The percentage of the sky covered by clouds is expressed as a percentage (30%).

[0036] 3. Precipitation probability and intensity: used as auxiliary judgment factors.

[0037] S232: Preliminary coefficient conversion based on preset mapping rules: The system maintains a weather phenomenon-prediction coefficient mapping table, which defines the preliminary weather impact prediction coefficients from the most common weather conditions. The correspondence is represented by a dimensionless number between 0 and 1, which characterizes the expected reduction in the theoretical maximum sunshine caused by the weather the following day. A basic mapping representation is as follows: Weather Phenomena - Prediction Coefficient Mapping Table Next, the system parses the obtained weather forecast text and matches the keywords in the mapping table. If quantitative cloud cover data is obtained at the same time, linear interpolation can be performed within the corresponding coefficient range to achieve a more refined value (for example, when it is cloudy and the cloud cover is 70%, the value is closer to 0.45).

[0038] S233: Localization and Dynamic Calibration Mechanism of Mapping Tables: The preset mapping tables are not fixed but have the ability to learn and calibrate to ensure that they conform to the actual local meteorological and climatic characteristics. The calibration mechanism includes: 1. Historical data fitting and calibration: The system periodically compares the initial values ​​of weather forecast coefficients for a historical period (such as the past year) with the actual weather impact observation coefficients calculated during the same period. By conducting comparative analysis and using statistical regression, the coefficient values ​​in the mapping table are adjusted to minimize the long-term statistical bias of the predicted values.

[0039] 2. Seasonal and Weather Pattern Correction: Sub-mapping tables can be created for different seasons or different prevailing weather systems. For example, the attenuation characteristics of sunlight by summer convective clouds and winter stratiform clouds are different, and the system can automatically switch or use different mapping tables with weights based on the date.

[0040] 3. Dynamic optimization based on machine learning: Using weather forecast information (including cloud cover, wind direction, humidity, etc.) and historical actual coefficients as training data, a lightweight regression model is trained to directly output the predicted coefficients, thereby achieving nonlinear dynamic optimization of the mapping relationship.

[0041] S240: Fusion Calculation of Final Weather Impact Correction Coefficient: To improve forecast robustness, the exponentially weighted moving average method is used to fuse forward-looking information from weather forecasts with the continuity patterns of historical observations to calculate the final weather impact correction coefficient for the following day. : ; in, The parameters (0) obtained by calibration using historical data with the goal of minimizing prediction error. 0 ), Controlling the level of trust in weather forecasts, The closer the value is to 1, the more the forecast depends on tomorrow's weather forecast. The closer the value is to 0, the more the prediction relies on the inertia of historical observations. Its optimal value reflects the average accuracy of local weather forecasts. Controlling the decay rate of historical observations, The closer the value is to 1, the closer the weights of the data from the past seven days are, and the better it portrays slowly changing weather patterns. The smaller the value, the faster the model responds to sudden weather changes. These are the prediction coefficients obtained based on the weather forecast conversion of the following day. They are generated by the aforementioned step S230 and are preliminary coefficients obtained based on the formatted weather forecast conversion of the following day. They represent the external meteorological model's judgment on the impact of future weather. The actual observation coefficient for the i-th day in the past is obtained from the aforementioned step S220. It is the ratio of the actual daily cumulative photosynthetically active radiation value measured locally over the past 7 consecutive days to the maximum theoretical value during the same period, representing the recent local light decay pattern.

[0042] Furthermore, parameters and Automatic calibration is performed using historical data in a goal-driven manner. The calibration process is as follows: First, data for a historical period is collected, including daily data. ,history The sequence, and the actual observed coefficients of the following day as the true values. With the goal of minimizing prediction error, the objective function is constructed using mean squared error. In parameter space ( The numerical optimization algorithm (such as grid search, conjugate gradient method, etc.) is used to find the value that minimizes the objective function. In addition, automatic recalibration can be set to be performed annually or quarterly to capture seasonal changes. Recalibration can also be triggered when the prediction error increases significantly over a period of time to adapt to long-term changes in the climate model.

[0043] S250: Calculate the predicted DLI value for natural light: the DLI value provided by natural light the following day ( )for; ; in, The theoretical maximum DLI value for the following day, calculated based on the season and solar altitude angle. Weather impact correction factor (0) ).

[0044] S300: Calculate the required artificial light DLI value for the next day (equal to the difference between the target DLI value for the next day and the DLI value provided by natural light on the next day; artificial light is provided by supplemental lighting installed in the greenhouse). The following is a detailed explanation of each step.

[0045] S310: Compare the DLI value required by high-value crops with the DLI value provided by natural light, and calculate the DLI value that needs to be supplemented by supplemental lighting the next day. : ; S320: Judgment If yes, then execute S330; otherwise, execute S340. S330: No supplemental lighting is required; S340: Turn on the fill light; fill light duration is... (Unit: hours)

[0046] The system automatically acquires the rated power P (W) of the supplemental light and its average photosynthetically active radiation flux density measured at the canopy height of tall economic crops. ( ).

[0047] Required supplemental lighting duration (h) is: ; S400: Predict the power load for artificial lighting the next day based on the DLI value of artificial lighting the next day; Predicted electricity load for supplemental lighting the following day ( This is the product of power and time: ; In the case of multiple greenhouses within a single distribution area, the total load is the sum of the loads of each individual greenhouse.

[0048] The S500 sends the predicted next day's supplemental lighting load data to the power operation multi-source data monitoring system of the distribution substation for power dispatching.

[0049] In summary, this invention, by introducing the monitoring and calculation of multi-source data related to the growth parameters of high-value crops in the agricultural distribution area, predicts electricity consumption one day in advance and formulates supplementary lighting plans, rather than waiting until insufficient sunlight to carry out power dispatch. This is beneficial for the power system to plan power transmission strategies in advance, improve the balance between power supply and power consumption in agricultural distribution areas, thereby improving the power supply quality of agricultural distribution areas and extending the service life of transformers and electrical equipment in the distribution areas.

[0050] Furthermore, the automatic acquisition of supplementary lighting parameters in the above steps can not only be used to calculate the supplementary lighting duration, but also, after the supplementary lighting is executed, the system can again collect actual supplementary lighting effect data through environmental sensors for calibration. The data makes the next duration calculation more accurate, forming a closed loop of continuous optimization.

[0051] Furthermore, this invention is particularly applicable to the monitoring of power data in power distribution areas where high-value crops are sensitive to light. Through precise light environment control, it can effectively improve fruit sugar content, color, and overall yield, maximizing economic efficiency and minimizing unnecessary power loss. Moreover, by combining precise light forecasting with the physiological growth needs of high-value crops, it also realizes the scientific, automated, and refined management of supplemental lighting in facility agriculture, which is conducive to achieving intelligent power supply and promoting the further development of agricultural planting towards scientific and intelligent methods.

[0052] In a further embodiment, the distribution substation is also equipped with a photovoltaic power generation module, which includes a solar photovoltaic receiving unit and an energy storage unit. When there is a difference between the predicted electricity consumption for the next day and the actual electricity demand, temporary regulation and management can be carried out through the photovoltaic power generation module.

[0053] When the predicted electricity consumption is greater than the actual demand, the photovoltaic energy storage module is connected to the circuit system as a load to absorb the surplus electricity. When the predicted electricity consumption is less than the actual demand, the photovoltaic energy storage module acts as a backup, enters the discharge mode, and serves as a power source to supply power to loads such as supplementary lighting, thus smoothing out the peak load of the power grid.

[0054] Finally, the system packages and sends the predicted next day's supplementary solar power load curve and the power supply / discharge data of the photovoltaic energy storage modules to the power operation multi-source data monitoring master station system of the distribution substation. Based on this, the master station system optimizes the substation-level power dispatch, such as adjusting transformer operation modes and participating in demand-side response, thereby improving power supply quality and equipment lifespan.

[0055] A power operation multi-source data monitoring device for a distribution transformer substation is provided to implement the aforementioned power operation multi-source data monitoring method for the distribution transformer substation. The device can be an edge intelligent gateway integrating data acquisition, calculation, and communication functions in hardware, and includes the following functional modules in software: Data interface module: Used to connect PAR sensors, supplemental lighting controllers, meteorological information interfaces, photovoltaic inverters, energy storage management systems, and smart meters in the greenhouse to achieve multi-source data acquisition.

[0056] Data storage and processing module: Stores crop growth models, historical environmental data, and equipment parameters, and is responsible for data cleaning, preprocessing, and calculation.

[0057] Load forecasting engine module: It has built-in algorithm models as described above and automatically executes core processes such as target DLI indexing, natural light forecasting, and supplemental lighting load calculation on a regular basis.

[0058] Collaborative control module: Generates charging and discharging control commands for the energy storage system based on prediction results and real-time operating status.

[0059] Communication reporting module: Uploads prediction results and control commands to the distribution automation master station or energy management platform in accordance with standard power communication protocols (such as IEC104, MQTT).

[0060] By implementing the above methods, the device achieves accurate perception and prediction of the fluctuating load of supplemental lighting in agricultural greenhouses, providing crucial data support for the coordinated interaction between power supply and consumption in the distribution area.

[0061] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0062] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A method for monitoring multi-source data of power operation in a power distribution substation, applied to a power distribution substation in an agricultural greenhouse, characterized in that, Includes the following steps: Acquire growth cycle data of high-value crops in agricultural distribution areas and construct target DLI (Daily Light Intake) value curves for the entire growth cycle of high-value crops. Predict the DLI value provided by natural light the following day; The required artificial light DLI value for the next day is calculated as the difference between the target DLI value for the next day and the DLI value provided by natural light on the next day. Based on the DLI value of artificial lighting the next day, predict the power load of artificial lighting the next day; The predicted power load data for supplemental lighting the following day is sent to the distribution substation for power dispatching.

2. The method for monitoring multi-source data of power operation in a distribution substation according to claim 1, characterized in that, The following method is used to predict the DLI value provided by natural light the following day. ); ； in, The theoretical maximum DLI value for the following day, calculated based on the season and solar altitude angle. Weather impact correction factor (0) ).

3. The method for monitoring multi-source data of power operation in a distribution substation according to claim 2, characterized in that, Weather impact correction factor It is obtained by using an index-weighted moving average that integrates weather forecast information and historical weather information from the most recent week. The calculation formula is as follows: ； in, The parameters (0) obtained by calibration using historical data with the goal of minimizing prediction error. 0 ), These are the prediction coefficients derived from the weather forecast for the following day. The actual observed coefficients for the i-th day in the past.

4. The method for monitoring multi-source data of power operation in a distribution substation according to claim 3, characterized in that, The actual observed coefficients for the i-th day in the past were obtained using the following method. ; ； in, The natural light DLI value actually measured on the i-th day in the past. This represents the theoretical maximum DLI value for the i-th past day.

5. The method for monitoring multi-source data of power operation in a distribution substation according to claim 4, characterized in that, The actual measured natural light DLI value on the i-th day was obtained by real-time monitoring and integration using photosynthetically active radiation sensors placed inside the greenhouse.

6. The method for monitoring multi-source data of power operation in a distribution substation according to claim 4, characterized in that, The theoretical maximum DLI value for the past i-th day is obtained using the following method. ; ； in, The average photosynthetically active radiation flux density of the local area under ideal sunny conditions throughout the day. This represents the theoretical sunshine duration of the i-th day in the past.

7. The method for monitoring multi-source data of power operation in a distribution substation according to claim 1, characterized in that, The greenhouse is equipped with supplemental lighting to provide artificial light for high-value crops.

8. The method for monitoring multi-source data of power operation in a distribution substation according to claim 7, characterized in that, The electrical load for artificial lighting the next day is equal to the product of the power of the supplemental light and the duration of artificial lighting.

9. The method for monitoring multi-source data of power operation in a distribution substation according to claim 8, characterized in that, The distribution area is equipped with photovoltaic energy storage modules. When there is a power surplus, the photovoltaic energy storage modules act as a load to store energy. When there is a power shortage, the photovoltaic energy storage modules act as a power source to supply power to the supplementary lights.

10. A multi-source data monitoring device for power operation in a distribution substation, characterized in that, This method is used to implement the multi-source data monitoring method for power operation of a distribution substation as described in any one of claims 1-9.

Images