Power Demand Response Scheduling Method Based on Dynamic Prediction Model

Abstract

A power demand response scheduling method based on a dynamic prediction model, the method comprising: acquiring in real time the environmental data, crop growth demand data and energy supply data inside and outside the greenhouse, and preprocessing the environmental data, crop growth demand data and energy supply data to construct a data set. Constructing a gas exchange model and a kinetic nutrient transport model based on the data set, and outputting the parameters and states of the gas exchange model and the kinetic nutrient transport model. Analyzing, through a Bayesian network, the parameters and states output by the gas exchange model and the kinetic nutrient transport model to predict the change trend of the environmental data inside the greenhouse in the first future time period, and outputting the prediction result of the future environmental data. Formulating an energy scheduling plan according to the prediction result of the future environmental data through a multi-objective optimization algorithm, determining the energy usage strategies of the heating, cooling and lighting systems, so as to output an optimal energy scheduling plan.

Description

Technical Field

[0001] The present invention belongs to the technical fields of intelligent agricultural production and energy scheduling, and more specifically, relates to a power demand response scheduling method based on a dynamic prediction model. Background Art

[0002] With the acceleration of the global agricultural modernization process, agricultural greenhouses, as important facilities for ensuring efficient and stable crop production, have an increasing demand for precise control of environmental conditions. Environmental parameters such as temperature, humidity, and light in the greenhouse need to be maintained within a specific range to promote the optimal growth of crops. To achieve this goal, greenhouses widely rely on heating, cooling, and lighting systems, and the energy demands of these systems are not only huge but also highly volatile and are more susceptible to external climate conditions. Therefore, how to efficiently and intelligently manage the energy use of greenhouses has become the key to improving agricultural production efficiency and reducing operating costs.

[0003] Currently, the energy management of agricultural greenhouses mainly adopts rule-based control methods and traditional demand response (DR) systems. These systems usually rely on preset environmental parameters and energy use strategies and lack the ability to dynamically respond to real-time data. With the development of information technology and intelligent control technology, power demand response systems based on model prediction have gradually been introduced into greenhouse energy management, using prediction models to predict future energy demands and environmental changes and optimizing energy scheduling plans accordingly to achieve efficient energy use and cost minimization. At the same time, some greenhouses have begun to combine the use of renewable energy (such as solar energy) with traditional energy (such as grid power supply) to improve the sustainability and stability of energy supply.

[0004] However, in the existing greenhouse energy management methods, due to the diversity and sensitivity of the crop growth cycle, different crops and their different growth stages have different and highly sensitive demands for environmental conditions, while the existing DR systems lack sufficient flexibility in adjusting energy use and are difficult to accurately match the diverse crop demands and dynamic growth cycles. In addition, according to the difficulty of hybrid management of renewable energy and traditional energy, agricultural greenhouses often need to simultaneously utilize renewable energy such as solar energy and traditional energy such as grid power supply, and there are still certain technical problems in the existing DR systems for efficiently coordinating and managing the hybrid use of these two types of energy, which to a certain extent affects the energy utilization efficiency and the overall stability of the greenhouse system. Summary of the Invention

[0005] To solve the deficiencies existing in the prior art, the purpose of the present invention is to solve the above-mentioned defects and further propose a power demand response scheduling method based on a dynamic prediction model.

[0006] The present invention adopts the following technical solutions.

[0007] The first aspect of the present invention discloses a power demand response scheduling method based on a dynamic prediction model, and the method includes:

[0008] Real-time obtain the environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse, and preprocess the environmental data, crop growth demand data, and energy supply data to construct a data set;

[0009] Based on the data set, construct a gas exchange model and a kinetic nutrient transport model, and output the parameters and states of the gas exchange model and the kinetic nutrient transport model;

[0010] Through a Bayesian network, analyze the parameters and states output by the gas exchange model and the kinetic nutrient transport model to predict the change trend of the environmental data inside the greenhouse in the first future time period, and output the prediction result of the future environmental data;

[0011] Through a multi-objective optimization algorithm, formulate an energy scheduling plan according to the prediction result of the future environmental data, determine the energy usage strategies of the heating, cooling, and lighting systems, so as to output the optimal energy scheduling plan;

[0012] Among them, the environmental data includes temperature, humidity, light intensity, carbon dioxide concentration, and nutrient solution flow rate, the energy supply data includes solar energy and electric energy, the preprocessing includes missing value processing, outlier detection, and data smoothing processing, the gas exchange model is used to simulate the dynamic changes of carbon dioxide concentration and oxygen in the greenhouse, and the kinetic nutrient transport model is used to simulate the transport and distribution of nutrient solution in the hydroponic system.

[0013] Further, the real-time obtainment of the environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse, and the preprocessing of the environmental data, crop growth demand data, and energy supply data to construct a data set includes:

[0014] Real-time monitor the environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse through multiple sensors and energy monitoring devices, and construct an original data set based on the environmental data, crop growth demand data, and energy supply data;

[0015] Use the mean value of the corresponding data column in the original data set as the filling value to fill in the missing values of the original data set, and use the three-sigma principle to detect the outliers in the original data set. When an outlier is detected, replace the outlier with the median of the corresponding column in the original data set;

[0016] Smooth the data of the original dataset by the moving average method, and integrate the cleaned environmental data, crop growth demand data, and energy supply data to output an integrated dataset.

[0017] Further, the real-time acquisition of environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse, and the preprocessing of the environmental data, crop growth demand data, and energy supply data to construct a dataset further includes:

[0018] Perform standardization and normalization processing on the integrated dataset to eliminate the influence of different dimensions and magnitudes in the integrated dataset on the gas exchange model and the kinetic nutrient transport model, and output the converted dataset;

[0019] Among them, the expression for standardization processing is:

[0020]

[0021] The expression for normalization processing is:

[0022]

[0023] In the formula, and are the standardization result and the normalization result of the element in the i-th row and j-th column respectively of is the element in the i-th row and j-th column of the integrated dataset, is the mean value of the j-th column, is the standard deviation of the j-th column, and are the minimum value and the maximum value of the j-th column respectively.

[0024] Further, constructing a gas exchange model and a kinetic nutrient transport model based on the dataset, and outputting the parameters and states of the gas exchange model and the kinetic nutrient transport model, includes:

[0025] Obtain the first basic parameters required by the gas exchange model from the converted dataset, where the first basic parameters include the carbon dioxide concentration, oxygen concentration, ventilation rate, and photosynthesis rate inside and outside the greenhouse, and construct the first basic dataset of the gas exchange model;

[0026] Based on the first basic dataset, establish a kinetic gas exchange equation describing the change of carbon dioxide concentration and oxygen concentration in the greenhouse over time, and the expression of the kinetic gas exchange equation is:

[0027]

[0028]

[0029] In the formula, is the change rate of carbon dioxide concentration over time, is the change rate of oxygen concentration over time, is the total gas volume in the greenhouse, is the ventilation rate, is the photosynthesis rate, is the carbon dioxide concentration entering the greenhouse, is the oxygen concentration entering the greenhouse, and are the carbon dioxide concentration and oxygen concentration in the greenhouse at time t, respectively, is the total photosynthetic area of the crops at time t.

[0030] Furthermore, constructing a gas exchange model and a kinetic nutrient transport model based on the dataset and outputting the parameters and states of the gas exchange model and the kinetic nutrient transport model further includes:

[0031] Obtaining the second basic parameters required for the kinetic nutrient transport model from the converted dataset, where the second basic parameters include nutrient solution flow rate, nutrient concentration in the nutrient solution, total plant root area, and nutrient absorption rate, and constructing a second basic parameter set;

[0032] Based on the second basic parameter set, establishing a kinetic nutrient transport equation describing the change of nutrients in the nutrient solution. The expression of the kinetic nutrient transport equation is:

[0033]

[0034] In the formula, is the change rate of nutrient concentration over time, is the volume of the nutrient solution storage tank, is the nutrient concentration of the input nutrient solution, is the total plant root area, is the nutrient solution flow rate, is the nutrient concentration in the nutrient solution at time t, is the nutrient absorption rate;

[0035] Calibrate the parameters of the gas exchange model and the kinetic nutrient transport model by minimizing the error between the model prediction value and the actual monitoring value, and divide the first basic parameter set and the second basic parameter set into a training set and a validation set by using cross-validation or the hold-out method, and calculate the coefficient of determination and mean square error indicators to verify the gas exchange model and the kinetic nutrient transport model, and output the calibrated model output parameters and states.

[0036] Further, analyze the parameters and states output by the Bayesian network based on the gas exchange model and the kinetic nutrient transport model to predict the change trend of the greenhouse environment data in the first future time period, and output the prediction result of the future environment data, including:

[0037] Construct a Bayesian network training dataset based on the output parameters and states of the calibrated model, and determine the dependence relationship between each environmental data in the Bayesian network through a structure learning algorithm to construct a Bayesian network structure;

[0038] Use the maximum likelihood estimation or Bayesian estimation algorithm to calculate the conditional probability table of each node according to the Bayesian network training dataset, and train the Bayesian network in combination with the Bayesian network structure and the Bayesian network training dataset, and adjust the model structure and parameters through cross-validation to obtain a trained Bayesian network model;

[0039] Among them, the Bayesian network structure consists of a node set and an edge set. The node set represents each environmental data, and the edge set represents the directed dependence relationship between nodes. The structure learning algorithm includes a search algorithm with scoring and a constraint-based algorithm. The trained Bayesian network model is used to predict and output the prediction result of the future environmental data according to the current or historical environmental data.

[0040] Further, the multi-objective optimization algorithm includes an optimization objective function and a predefined set of constraint conditions. The optimization objective function contains multiple sub-objectives, and the sub-objectives include minimizing energy cost, maximizing energy utilization efficiency, and ensuring environmental stability;

[0041] Formulate an energy scheduling plan according to the prediction result of the future environmental data through the multi-objective optimization algorithm, determine the energy usage strategies of the heating, cooling, and lighting systems, and output the optimal energy scheduling plan, including:

[0042] Based on the weight coefficients of each sub-objective in the optimization objective function, perform weighted summation on the sub-objectives to obtain a comprehensive optimization objective function, and combine the set of constraint conditions to determine the configuration parameters through the non-dominated sorting genetic algorithm to construct a configured multi-objective optimization algorithm;

[0043] Call the configured multi-objective optimization algorithm to generate a solution set of approximate Pareto optimal solutions based on the comprehensive optimization objective function and the set of constraint conditions, and screen out the optimal energy scheduling plan from the solution set according to the actual requirements and priorities;

[0044] Among them, the configuration parameters include population size, number of iterations, crossover rate, and mutation rate. Each solution in the solution set corresponds to an energy scheduling plan.

[0045] The second aspect of the present invention discloses a scheduling device for a power demand response system based on model prediction, and the device includes:

[0046] A data preprocessing module, configured to obtain in real time the environmental data inside and outside the greenhouse, the crop growth demand data, and the energy supply data, and preprocess the environmental data, the crop growth demand data, and the energy supply data to construct a data set;

[0047] A model construction module, configured to construct a gas exchange model and a kinetic nutrient transport model based on the data set, and output the parameters and states of the gas exchange model and the kinetic nutrient transport model;

[0048] A future environment prediction module, configured to analyze through a Bayesian network based on the parameters and states output by the gas exchange model and the kinetic nutrient transport model to predict the change trend of the environmental data inside the greenhouse in the first future time period, and output the prediction result of the future environmental data;

[0049] An energy scheduling screening module, configured to formulate an energy scheduling plan according to the prediction result of the future environmental data through a multi-objective optimization algorithm, determine the energy usage strategies of the heating, cooling, and lighting systems, and output an optimal energy scheduling plan;

[0050] Wherein, the environmental data includes temperature, humidity, light intensity, carbon dioxide concentration, and nutrient solution flow rate, the energy supply data includes solar energy and electric energy, the preprocessing includes missing value processing, outlier detection, and data smoothing processing, the gas exchange model is used to simulate the dynamic changes of carbon dioxide concentration and oxygen in the greenhouse, and the kinetic nutrient transport model is used to simulate the transport and distribution of nutrient solution in the hydroponic system.

[0051] The third aspect of the present invention discloses a terminal, including a processor and a storage medium; characterized in that:

[0052] The storage medium is used to store instructions;

[0053] The processor is configured to operate according to the instructions to execute the steps of the method described in the first aspect.

[0054] The fourth aspect of the present invention discloses a computer-readable storage medium, on which a computer program is stored, characterized in that when the program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0055] The beneficial effects of the present invention are that, compared with the prior art, the present invention has the following advantages:

[0056] By constructing a gas exchange model and a kinetic nutrient transport model, combining with a Bayesian network to predict environmental data for a period of time in the future, and formulating and screening the optimal energy scheduling scheme through a multi-objective optimization algorithm according to the prediction results, the energy can be flexibly scheduled in a greenhouse where the diversity and sensitivity of the crop growth cycle are relatively high, thereby improving the accuracy of matching the energy required for the growth of diverse crops. At the same time, the energy utilization efficiency and the stability of the energy scheduling system are improved in the scenario of mixed use of renewable energy and traditional energy. Brief Description of the Drawings

[0057] Figure 1 It is a schematic flow chart of the power demand response scheduling method based on a dynamic prediction model provided by the present invention. Detailed Embodiments

[0058] The following further describes the present application with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and cannot be used to limit the protection scope of the present application.

[0059] As Figure 1 shown, in one embodiment, a power demand response scheduling method based on a dynamic prediction model includes the following steps:

[0060] Step S110, obtain the environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse in real time, and preprocess the environmental data, crop growth demand data, and energy supply data to construct a data set.

[0061] Among them, the environmental data includes temperature, humidity, light intensity, carbon dioxide concentration, and nutrient solution flow rate, the energy supply data includes solar energy and electric energy, and the preprocessing includes missing value processing, outlier detection, and data smoothing processing.

[0062] In some embodiments, the power demand response scheduling method based on a dynamic prediction model provided by the present invention obtains the environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse in real time, and preprocesses the environmental data, crop growth demand data, and energy supply data to construct a data set, which specifically includes the following steps:

[0063] Step S111, monitor the environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse in real time through multiple sensors and energy monitoring devices, and construct an original data set based on the environmental data, crop growth demand data, and energy supply data.

[0064] Step S112, fill the missing values in the original dataset with the mean value of the corresponding data column in the original dataset, and detect the outliers in the original dataset using the three-sigma principle. When an outlier is detected, replace the outlier with the median of the corresponding column in the original dataset.

[0065] Step S113, perform data smoothing on the original dataset by the moving average method, and integrate the cleaned environmental data, crop growth demand data, and energy supply data to output an integrated dataset.

[0066] In some embodiments, the power demand response scheduling method based on a dynamic prediction model provided by the present invention obtains the environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse in real time, and preprocesses the environmental data, crop growth demand data, and energy supply data to construct a dataset. Specifically, it further includes the following steps:

[0067] Step S114, perform standardization and normalization processing on the integrated dataset to eliminate the influence of different dimensions and magnitudes in the integrated dataset on the gas exchange model and the kinetic nutrient transport model, and output the converted dataset.

[0068] Among them, the expression for standardization processing is:

[0069]

[0070] The expression for normalization processing is:

[0071]

[0072] In the formula, and are the standardization result and the normalization result of the element in the i-th row and j-th column respectively, is the element in the i-th row and j-th column of the integrated dataset, is the mean value of the j-th column, is the standard deviation of the j-th column, is the standard deviation of the j-th column, and are the minimum value and the maximum value of the j-th column respectively.

[0073] Step S120, construct a gas exchange model and a kinetic nutrient transport model based on the dataset, and output the parameters and states of the gas exchange model and the kinetic nutrient transport model.

[0074] Among them, the gas exchange model is used to simulate the dynamic changes of carbon dioxide concentration and oxygen in the greenhouse, and the kinetic nutrient transport model is used to simulate the transport and distribution of nutrient solution in the hydroponic system.

[0075] In some embodiments, the power demand response scheduling method based on a dynamic prediction model provided by the present invention constructs a gas exchange model and a kinetic nutrient transport model based on a data set, and outputs the parameters and states of the gas exchange model and the kinetic nutrient transport model, which specifically include the following steps:

[0076] Step S121, obtain the first basic parameters required for the gas exchange model from the converted data set. The first basic parameters include the carbon dioxide concentration, oxygen concentration, ventilation rate, and photosynthesis rate inside and outside the greenhouse, and construct the first basic data set of the gas exchange model.

[0077] Step S122, establish a kinetic gas exchange equation describing the changes in carbon dioxide concentration and oxygen concentration in the greenhouse over time based on the first basic data set. The expression of the kinetic gas exchange equation is:

[0078]

[0079]

[0080] In the formula, is the change rate of carbon dioxide concentration over time, is the change rate of oxygen concentration over time, is the total gas volume in the greenhouse, is the ventilation rate, is the photosynthesis rate, is the carbon dioxide concentration entering the greenhouse, is the oxygen concentration entering the greenhouse, and are the carbon dioxide concentration and oxygen concentration in the greenhouse at time t respectively, is the total photosynthetic area of crops at time t.

[0081] In some embodiments, the power demand response scheduling method based on a dynamic prediction model provided by the present invention constructs a gas exchange model and a kinetic nutrient transport model based on a data set, and outputs the parameters and states of the gas exchange model and the kinetic nutrient transport model, which specifically further include the following steps:

[0082] Step S123, obtain the second basic parameters required for the kinetic nutrient transport model from the converted data set. The second basic parameters include the nutrient solution flow rate, nutrient concentration in the nutrient solution, total plant root area, and nutrient absorption rate, and construct the second basic parameter set

[0083] Step S124, establish a kinetic nutrient transport equation describing the changes in nutrients in the nutrient solution based on the second basic parameter set. The expression of the kinetic nutrient transport equation is:

[0084]

[0085] In the formula, is the change rate of nutrient concentration over time, is the volume of the nutrient solution storage tank, is the nutrient concentration of the input nutrient solution, is the total root area of the plants, is the nutrient solution flow rate, is the nutrient concentration in the nutrient solution at time t, is the nutrient absorption rate.

[0086] Step S125: Calibrate the parameters of the gas exchange model and the kinetic nutrient transport model by minimizing the error between the model prediction value and the actual monitoring value, and divide the first basic parameter set and the second basic parameter set into a training set and a validation set by using cross-validation or the holdout method, and calculate the coefficient of determination and the mean square error index to verify the gas exchange model and the kinetic nutrient transport model, and output the calibrated model output parameters and states.

[0087] Step S130: Analyze based on the parameters and states output by the gas exchange model and the kinetic nutrient transport model through a Bayesian network to predict the change trend of the greenhouse environment data in the first future time period, and output the prediction result of the future environment data.

[0088] In some embodiments, the power demand response scheduling method based on the dynamic prediction model provided by the present invention analyzes based on the parameters and states output by the gas exchange model and the kinetic nutrient transport model through a Bayesian network to predict the change trend of the greenhouse environment data in the first future time period, and output the prediction result of the future environment data, specifically including the following steps:

[0089] Step S131: Construct a Bayesian network training data set based on the calibrated model output parameters and states, and determine the dependence relationship between the environmental data in the Bayesian network according to the Bayesian network training data set through a structure learning algorithm to construct a Bayesian network structure.

[0090] Step S132: Calculate the conditional probability table of each node according to the Bayesian network training data set by using the maximum likelihood estimation or the Bayesian estimation algorithm, and train the Bayesian network in combination with the Bayesian network structure and the Bayesian network training data set, and adjust the model structure and parameters through cross-validation to obtain the trained Bayesian network model.

[0091] Among them, the Bayesian network structure consists of a node set and an edge set. The node set represents various environmental data, and the edge set represents the directed dependence relationship between nodes. The structure learning algorithm includes a search algorithm that gives scores and a constraint-based algorithm. The trained Bayesian network model is used to predict and output the prediction results of future environmental data based on current or historical environmental data.

[0092] Step S140, formulate an energy scheduling plan according to the prediction results of future environmental data through a multi-objective optimization algorithm, determine the energy usage strategies of the heating, cooling, and lighting systems, so as to output the optimal energy scheduling plan.

[0093] Among them, the multi-objective optimization algorithm includes an optimization objective function and a predefined set of constraint conditions. The optimization objective function contains multiple sub-objectives, and the sub-objectives include minimizing energy cost, maximizing energy utilization efficiency, and ensuring environmental stability.

[0094] In some embodiments, the power demand response scheduling method based on a dynamic prediction model provided by the present invention formulates an energy scheduling plan according to the prediction results of future environmental data through a multi-objective optimization algorithm, determines the energy usage strategies of the heating, cooling, and lighting systems, so as to output the optimal energy scheduling plan, and specifically includes the following steps:

[0095] Step S141, based on the weight coefficients of each sub-objective in the optimization objective function, perform weighted summation on the sub-objectives to obtain a comprehensive optimization objective function, and in combination with the set of constraint conditions, determine the configuration parameters through a non-dominated sorting genetic algorithm to construct a configured multi-objective optimization algorithm.

[0096] Step S142, call the configured multi-objective optimization algorithm to generate a solution set of approximate Pareto optimal solutions based on the comprehensive optimization objective function and the set of constraint conditions, and screen out the optimal energy scheduling plan from the solution set according to the actual requirements and priorities.

[0097] Among them, the configuration parameters include population size, number of iterations, crossover rate, and mutation rate. Each solution in the solution set corresponds to an energy scheduling plan.

[0098] The above-mentioned power demand response scheduling method based on a dynamic prediction model predicts environmental data for a period of time in the future by constructing a gas exchange model and a kinetic nutrient transport model, and in combination with a Bayesian network, and formulates and screens the optimal energy scheduling plan through a multi-objective optimization algorithm according to the prediction results. It can flexibly schedule energy in a greenhouse where the diversity and sensitivity of the crop growth cycle are relatively high, thereby improving the accuracy of matching energy for the growth needs of diverse crops. At the same time, it improves the energy utilization efficiency and the stability of the energy scheduling system in the scenario of mixed use of renewable energy and traditional energy.

[0099] In a specific embodiment, the power demand response scheduling method based on a dynamic prediction model provided by the present invention includes steps 1 to 4:

[0100] Step 1, data collection and preprocessing, outputting a high-quality data set after preprocessing for subsequent modeling and prediction.

[0101] Collect real-time environmental data inside and outside the greenhouse, including temperature, humidity, light intensity, carbon dioxide concentration, nutrient solution flow rate, etc. In addition, collect physiological demand data of different crops and their respective growth stages, as well as the supply situations of renewable energy (such as solar energy) and traditional energy (such as the power grid).

[0102] Specifically, it includes steps 1.1 to 1.4:

[0103] Step 1.1, real-time environmental data collection.

[0104] Collect real-time environmental data inside and outside the agricultural greenhouse, including temperature, humidity, light intensity, carbon dioxide concentration, etc. In addition, obtain crop growth demand data and supply data of renewable energy (such as solar energy) and traditional energy (such as the power grid). These data are monitored and recorded in real time through sensors and energy monitoring devices installed at key positions in the greenhouse. Subsequently, based on the collected data, an original data set is constructed. The original data set is represented as a matrix, where each row in the matrix is the temperature, humidity, light intensity, carbon dioxide concentration, renewable energy supply amount, and traditional energy supply amount at the same time point, and each column is the temperature or humidity or light intensity or carbon dioxide concentration or renewable energy supply amount or traditional energy supply amount at different time points.

[0105] Step 1.2, data cleaning.

[0106] Clean the original data set obtained in step 1.1 to remove missing values and outliers, and perform smoothing processing on it to ensure the accuracy and consistency of the data.

[0107] During the process of missing value processing, for each element in the original data set matrix, if the corresponding element is missing, the mean value of this column is used as the filling value for filling. When detecting and processing outliers, the three-sigma principle is used to detect outliers. If an element is marked as an outlier, the median of this column is used to replace the outlier. During the data smoothing process, the moving average method is used for data smoothing processing, and finally the cleaned data set is obtained.

[0108] Step 1.3, data integration.

[0109] Integrate the cleaned environmental data, crop growth demand data, and energy supply data obtained in step 1.2 to form a unified data set, that is, an integrated data set, for subsequent analysis and modeling.

[0110] Step 1.4, Data conversion.

[0111] The integrated dataset is standardized and normalized to obtain a converted dataset, which is used to eliminate the influence of different dimensions and magnitudes on the subsequent model building and improve the data consistency and the convergence speed of the model.

[0112] Specifically, the expression for standardization is:

[0113]

[0114] The expression for normalization is:

[0115]

[0116] In the formula, and are the standardization result and the normalization result of the element in the i-th row and j-th column respectively, is the element in the i-th row and j-th column of the integrated dataset, is the mean value of the j-th column, is the standard deviation of the j-th column, and and are the minimum value and the maximum value of the j-th column respectively.

[0117] Step 2, Establish a gas exchange and kinetic nutrient transport model, and output the parameters and states of the gas exchange model and the kinetic nutrient transport model.

[0118] Based on the collected data, a gas exchange model and a kinetic nutrient transport model are constructed. Among them, the gas exchange model is used to simulate the dynamic changes of carbon dioxide and oxygen in the greenhouse to ensure the gas supply required for crop photosynthesis. The kinetic nutrient transport model simulates the transport and distribution of nutrient solution in the hydroponic system to ensure that crops obtain balanced nutrition.

[0119] Specifically, it includes steps 2.1 to 2.5:

[0120] Step 2.1, Determine the basic parameters of the gas exchange model.

[0121] Based on the preprocessed high-quality dataset, first determine the basic parameters required for the gas exchange model. The basic parameters include the carbon dioxide concentration, oxygen concentration, ventilation rate, and photosynthesis rate inside and outside the greenhouse, and then construct a basic parameter set for the gas exchange model, and this parameter set is represented as a vector composed of the carbon dioxide concentration entering the greenhouse, the oxygen concentration entering the greenhouse, the ventilation rate, and the photosynthesis rate.

[0122] Step 2.2, Derive the gas exchange kinetic equation.

[0123] Using the basic parameter set of gas exchange constructed in Step 2.1, establish a kinetic equation that describes the variation of carbon dioxide and oxygen concentrations in the greenhouse over time. This equation takes into account the gas introduced by ventilation, the carbon dioxide consumed by crop photosynthesis, and the oxygen released.

[0124] Specifically, the expression of the kinetic gas exchange equation is:

[0125]

[0126]

[0127] In the formula, is the rate of change of carbon dioxide concentration over time, is the rate of change of oxygen concentration over time, is the total gas volume in the greenhouse, is the ventilation rate, is the photosynthesis rate, is the carbon dioxide concentration entering the greenhouse, is the oxygen concentration entering the greenhouse, and are the carbon dioxide concentration and oxygen concentration in the greenhouse at time t, respectively, is the total photosynthetic area of the crops at time t.

[0128] Step 2.3, determine the basic parameters of the kinetic nutrient transport model.

[0129] Based on the preprocessed high-quality data set, determine the basic parameters required for the kinetic nutrient transport model. These parameters include nutrient solution flow rate, nutrient concentration, and plant absorption rate. Subsequently, based on these basic parameters, construct a basic parameter set for the kinetic nutrient transport model, which is represented as a vector composed of the nutrient solution flow rate, the nutrient concentration in the nutrient solution, the total root area of the plants, and the nutrient absorption rate.

[0130] Step 2.4, establish the kinetic nutrient transport equation.

[0131] Using the basic parameter set of kinetic nutrient transport constructed in Step 2.3, establish a kinetic equation that describes the variation of nutrient concentration in the nutrient solution over time. This equation takes into account the flow of the nutrient solution, the absorption of nutrients by plants, and the recycling of nutrients.

[0132] Specifically, the expression of the kinetic nutrient transport equation is:

[0133]

[0134] In the formula, is the rate of change of nutrient concentration over time, is the volume of the nutrient solution storage tank, is the nutrient concentration of the input nutrient solution, is the total area of plant roots, is the nutrient solution flow rate, is the nutrient concentration in the nutrient solution at time t, is the nutrient absorption rate.

[0135] Step 2.5, Parameter calibration and model verification.

[0136] Calibrate the parameters of the gas exchange model and the kinetic nutrient transport model through experimental data and historical data to ensure the accuracy and reliability of the models. Use statistical methods and error analysis to evaluate the agreement between model predictions and actual data.

[0137] Parameter calibration is carried out by minimizing the error between the model predicted value and the actual observed value, and its expression is:

[0138]

[0139] In the formula, is the model parameter vector, is the actual observed value at the i-th time point, is the model predicted value at the i-th time point.

[0140] During the model verification process, the dataset is divided into a training set and a validation set using cross-validation or the holdout method to evaluate the prediction performance of the model, and the coefficient of determination and the mean square error indexes are calculated, and their expressions are:

[0141]

[0142]

[0143] In the formula, is the average of the actual observed values, n is the total number of elements in the dataset, and other variables are the same as above and will not be elaborated here. Among them, a higher value and a lower value indicate that the model has good prediction performance.

[0144] Based on the above process, finally output the calibrated parameters and states of the gas exchange model and the kinetic nutrient transport model respectively.

[0145] Step 3, Construct a Bayesian network for environmental parameter prediction and output the probability prediction results of future environmental parameters.

[0146] Use a Bayesian network to model the dependencies between environmental parameters during crop growth for probabilistic prediction. By analyzing the outputs of the gas exchange model and the kinetic nutrient transport model, predict the possible trends of various environmental parameters in the greenhouse over a period of time in the future.

[0147] Specifically, it includes steps 3.1 to 3.5:

[0148] Step 3.1, prepare the training data for the Bayesian network.

[0149] Use the parameters and states of the gas exchange model and the kinetic nutrient transport model established in step 2 to organize and prepare the training data required for the Bayesian network. Ensure that all relevant environmental parameters and model state data are correctly extracted and formatted for use in the modeling and training of the Bayesian network.

[0150] In this embodiment, the Bayesian network training data set can be represented as a matrix. Each row of the matrix is the carbon dioxide concentration, oxygen concentration, nutrient concentration, temperature, humidity, and light intensity at the same time point, and each column is the carbon dioxide concentration or oxygen concentration or nutrient concentration or temperature or humidity or light intensity at different time points.

[0151] Step 3.2, determine the structure of the Bayesian network.

[0152] Through the structure learning algorithm, determine the dependencies between various environmental parameters in the Bayesian network. Select a suitable structure learning method (such as a score-based search algorithm, a constraint-based algorithm, or a hybrid method) to construct a network structure that reflects the mutual influence of variables in the actual greenhouse environment. The Bayesian network structure consists of a node set and an edge set. The node set represents each environmental data, and the edge set represents the directed dependency between nodes.

[0153] In this embodiment, in greenhouse management, based on the constraint-based algorithm and the score-based search algorithm, the carbon dioxide concentration may affect the oxygen concentration and nutrient concentration, and the temperature may affect the humidity and light intensity. Determine these dependencies through structure learning and construct a network structure that reflects the mutual influence of variables in the actual environment.

[0154] Step 3.3, parameter learning and probability estimation.

[0155] After determining the Bayesian network structure, perform parameter learning to estimate the conditional probability distribution of each node. Adopt the maximum likelihood estimation (MLE) or Bayesian estimation method to calculate the conditional probability table (CPT) of each node according to the training data DBN.

[0156] In this embodiment, the conditional probability table is used to represent the probability distribution of each node when its parent node takes a specific value, and its expression is:

[0157]

[0158] In the formula, represents node i, is the parent node of node i, is the value of node i, is the combination of values of the parent node.

[0159] In greenhouse management, through MLE or Bayesian estimation, calculate the probability distributions of carbon dioxide concentration, oxygen concentration, and nutrient concentration under different environmental conditions (such as different temperatures and humidities). For example, calculate the temperature and humidity when the probability that the carbon dioxide concentration

[0160] is 400 ppm. In this embodiment, the MLE method estimates the conditional probability through direct counting, is applicable to large-scale data sets, and ensures that the parameters of the Bayesian network reflect the actual environmental data. Bayesian estimation avoids the problem of probability being 0 by introducing prior information, is applicable to the situation of less data or different data, and can improve the robustness of the model.

[0161] Step 3.4, model training and optimization.

[0162] Use the Bayesian network training data set to train the Bayesian network, optimize the network parameters, and adjust the model structure and parameters through cross-validation or other validation methods to improve the accuracy and robustness of prediction.

[0163] During the cross-validation process, divide the data set into a training set and a validation set, repeat the training and validation process, and select the best-performing model parameters. In addition, hyperparameter tuning can adjust the hyperparameters (such as smoothing parameters) in the Bayesian network to optimize the model performance.

[0164] In greenhouse management, through cross-validation and hyperparameter tuning, ensure that the Bayesian network model can accurately predict the change trends of carbon dioxide, oxygen, and nutrient concentrations under different light, temperature, and humidity conditions. For example, by adjusting the smoothing parameter, optimize the prediction accuracy of carbon dioxide under high light intensity. In addition, by minimizing the prediction error, it can be ensured that the Bayesian network model accurately reflects the dependence relationship between environmental parameters. Cross-validation can improve the generalization ability of the model and avoid overfitting through multiple trainings and validations.

[0165] Step 3.5, probability prediction of future environmental parameters.

[0166] Use the optimized Bayesian network model through training to perform probability prediction on the environmental data in the greenhouse for a period of time in the future. That is, input the current or historical environmental parameter status, calculate the probability distribution of future parameters through Bayesian inference, and output the probability prediction results of future environmental parameters.

[0167] Specifically, the Bayesian inference formula is:

[0168]

[0169] In the formula, is the environmental parameter at the future time point, is the current or historical environmental parameter status, m = 6 is the number of future environmental parameters, is the parent node of each future parameter in the dependency relationship in the Bayesian network.

[0170] In greenhouse management, through Bayesian inference, using the current environmental parameter status (such as current temperature, humidity, light intensity, etc.), predict the probability distribution of these parameters for a period of time in the future. Bayesian inference calculates the joint probability distribution of future parameters through the known current status, using the network structure and conditional probability table. The adjustment rate of each future parameter is determined by the status of its parent node, ensuring that the prediction results reflect the actual dependency relationship and dynamic changes.

[0171] Step 4, use the multi-objective optimization algorithm to formulate an energy scheduling plan and output the optimal energy scheduling plan.

[0172] Based on the prediction results of the Bayesian network, apply the multi-objective optimization algorithm to balance among multiple objectives (such as energy cost, crop yield, environmental stability), and optimize the energy scheduling plan. The optimization algorithm will determine the energy usage strategies of the heating, cooling, and lighting systems, and reasonably allocate the usage ratio of renewable energy and traditional energy.

[0173] Specifically, it includes Step 4.1 to Step 4.4:

[0174] Step 4.1, define the optimization objectives and constraints.

[0175] Clarify the optimization objectives and constraints of energy scheduling. The main objectives include minimizing energy cost, maximizing energy utilization efficiency, and ensuring environmental stability. The constraints include the requirements of environmental parameters in the greenhouse, the supply limitations of renewable energy and traditional energy, and the physical limitations of equipment operation.

[0176] In this embodiment, the optimization objective function includes multiple sub-objectives, that is, minimizing energy cost, maximizing energy utilization efficiency, and ensuring environmental stability. Among them, the sub-objective expressions are:

[0177]

[0178]

[0179]

[0180] In the formula, 、 、 are the minimization of energy cost, the maximization of energy utilization efficiency, and the guarantee of environmental stability respectively, is the total number of scheduling time periods, is the unit cost of renewable energy at time t, is the amount of renewable energy used at time t, is the unit cost of traditional energy at time t, is the amount of traditional energy used at time t, is the total amount of energy actually used at time t, is the total amount of available energy at time t, is the degree of satisfaction of the actual environmental parameters in the greenhouse at time t, is the degree of satisfaction of the desired environmental parameters in the greenhouse at time t.

[0181] Step 4.2, construct a multi-objective optimization model.

[0182] Based on the defined optimization objectives and constraint conditions, construct a multi-objective optimization model, and use the weighted summation method to combine multiple objective functions into a single objective function for applying an optimization algorithm to solve.

[0183] Specifically, based on the weight coefficients of each sub-objective in the optimization objective function, perform weighted summation on the sub-objectives to obtain a comprehensive optimization objective function, and combine it with the constraint condition set to determine the configuration parameters through the non-dominated sorting genetic algorithm to construct a configured multi-objective optimization algorithm.

[0184] Step 4.3, select a multi-objective optimization algorithm suitable for energy scheduling, such as particle swarm optimization, genetic algorithm, or non-dominated sorting genetic algorithm. First, configure algorithm parameters, such as population size, number of iterations, crossover rate, and mutation rate, etc., to ensure the efficiency and effect of the optimization process, and obtain a configured multi-objective optimization algorithm model.

[0185] Step 4.4, perform multi-objective optimization and generate a solution set.

[0186] Run the configured multi-objective optimization algorithm to generate a set of approximate Pareto optimal solutions, and output the corresponding solution set. These solutions achieve the best balance among different objectives for further selection and application. Each solution in the solution set is an energy scheduling plan, which defines the energy usage strategy at each time point. Additionally, the solution set represents different trade-off plans, and users can select the most suitable plan according to actual needs.

[0187] Step 4.5, screen and determine the optimal energy scheduling plan.

[0188] Screen out the optimal energy scheduling plan from the generated solution set. According to actual needs and priorities, select the plan that best meets the objective balance and ensure that it satisfies all constraints.

[0189] Among them, the optimal energy scheduling plan can be expressed as:

[0190]

[0191] In the formula, is the optimal amount of renewable energy used at time t, is the optimal amount of traditional energy used at time t. Other variables are the same as above and will not be elaborated here.

[0192] Next, the scheduling device of the power demand response system based on model prediction provided by the present invention will be described. The scheduling device of the power demand response system based on model prediction described below can be correspondingly referred to the power demand response scheduling method based on the dynamic prediction model described above.

[0193] In one embodiment, a scheduling device of a power demand response system based on model prediction includes a data preprocessing module, a model construction module, a future environment prediction module, and an energy scheduling screening module.

[0194] The data preprocessing module is used to obtain the environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse in real time, and preprocess the environmental data, crop growth demand data, and energy supply data to construct a data set.

[0195] The model construction module is used to construct a gas exchange model and a kinetic nutrient transport model based on the data set, and output the parameters and states of the gas exchange model and the kinetic nutrient transport model.

[0196] The future environment prediction module is used to analyze through a Bayesian network based on the parameters and states output by the gas exchange model and the kinetic nutrient transport model to predict the change trend of the environmental data inside the greenhouse in the first future time period, and output the prediction result of the future environmental data.

[0197] The energy scheduling screening module is used to formulate an energy scheduling plan according to the prediction results of future environmental data through a multi-objective optimization algorithm, determine the energy usage strategies of the heating, cooling, and lighting systems, and output the optimal energy scheduling plan.

[0198] Among them, the environmental data includes temperature, humidity, light intensity, carbon dioxide concentration, and nutrient solution flow rate. The energy supply data includes solar energy and electric energy. The preprocessing includes missing value processing, outlier detection, and data smoothing processing. The gas exchange model is used to simulate the dynamic changes of carbon dioxide concentration and oxygen in the greenhouse. The kinetic nutrient transport model is used to simulate the transport and distribution of nutrient solution in the hydroponic system.

[0199] In this embodiment, for the scheduling device of the model prediction-based power demand response system provided by the present invention, the data preprocessing module is specifically used for:

[0200] Real-time monitor the environmental data, crop growth demand data, and energy supply data inside and outside the greenhouse through multiple sensors and energy monitoring devices, and construct an original data set based on the environmental data, crop growth demand data, and energy supply data.

[0201] Fill in the missing values of the original data set with the mean value of the corresponding data column in the original data set, and use the three-sigma principle to detect the outliers in the original data set. When an outlier is detected, replace the outlier with the median of the corresponding column in the original data set.

[0202] Perform data smoothing processing on the original data set through the moving average method, and integrate the cleaned environmental data, crop growth demand data, and energy supply data to output an integrated data set.

[0203] In this embodiment, for the scheduling device of the model prediction-based power demand response system provided by the present invention, the data preprocessing module is specifically further used for:

[0204] Perform standardization and normalization processing on the integrated data set to eliminate the influence of different dimensions and magnitudes in the integrated data set on the gas exchange model and the kinetic nutrient transport model, and output the converted data set.

[0205] Among them, the expression for standardization processing is:

[0206]

[0207] The expression for normalization processing is:

[0208]

[0209] In the formula, and are the element of the i-th row and j-th column respectively The standardized result and the normalized result, is the element in the i-th row and j-th column of the integrated dataset, is the mean value of the j-th column, is the standard deviation of the j-th column, and are the minimum value and the maximum value of the j-th column respectively.

[0210] In this embodiment, for the power demand response system scheduling device based on model prediction provided by the present invention, the model construction module is specifically configured to:

[0211] Obtain the first basic parameters required for the gas exchange model from the converted dataset. The first basic parameters include the carbon dioxide concentration, oxygen concentration, ventilation rate, and photosynthesis rate inside and outside the greenhouse, and construct the first basic dataset of the gas exchange model.

[0212] Based on the first basic dataset, establish a kinetic gas exchange equation describing the change of carbon dioxide concentration and oxygen concentration in the greenhouse over time. The expression of the kinetic gas exchange equation is:

[0213]

[0214]

[0215] In the formula, is the change rate of carbon dioxide concentration over time, is the change rate of oxygen concentration over time, is the total gas volume in the greenhouse, is the ventilation rate, is the photosynthesis rate, is the carbon dioxide concentration entering the greenhouse, is the oxygen concentration entering the greenhouse, and are the carbon dioxide concentration and oxygen concentration in the greenhouse at time t respectively, is the total photosynthetic area of crops at time t.

[0216] In this embodiment, for the power demand response system scheduling device based on model prediction provided by the present invention, the model construction module is specifically further configured to:

[0217] Obtain the second basic parameters required for the kinetic nutrient transport model from the converted dataset. The second basic parameters include the nutrient solution flow rate, nutrient concentration in the nutrient solution, total plant root area, and nutrient absorption rate, and construct the second basic parameter set

[0218] Based on the second basic parameter set, establish a kinetic nutrient transport equation describing the change of nutrients in the nutrient solution. The expression of the kinetic nutrient transport equation is:

[0219]

[0220] In the formula, is the change rate of nutrient concentration with time, is the volume of the nutrient solution storage tank, is the nutrient concentration of the input nutrient solution, is the total root area of the plant, is the nutrient solution flow rate, is the nutrient concentration in the nutrient solution at time t, is the nutrient absorption rate.

[0221] The gas exchange model and the kinetic nutrient transport model are calibrated by minimizing the error between the model predicted values and the actual monitored values, and the first basic parameter set and the second basic parameter set are divided into a training set and a validation set by using cross-validation or the holdout method, and the coefficient of determination and the mean square error index are calculated to verify the gas exchange model and the kinetic nutrient transport model, and the calibrated model output parameters and states are output.

[0222] In this embodiment, for the power demand response system scheduling device provided by the present invention based on model prediction, the future environment prediction module is specifically used for:

[0223] Construct a Bayesian network training data set based on the calibrated model output parameters and states, and determine the dependency relationship between each environmental data in the Bayesian network according to the Bayesian network training data set through a structure learning algorithm, so as to construct a Bayesian network structure.

[0224] Calculate the conditional probability table of each node according to the Bayesian network training data set by using the maximum likelihood estimation or Bayesian estimation algorithm, and train the Bayesian network in combination with the Bayesian network structure and the Bayesian network training data set, and adjust the model structure and parameters through cross-validation to obtain the trained Bayesian network model.

[0225] Among them, the Bayesian network structure consists of a node set and an edge set. The node set represents each environmental data, and the edge set represents the directed dependency relationship between the nodes. The structure learning algorithm includes a scoring-based search algorithm and a constraint-based algorithm. The trained Bayesian network model is used to predict and output the prediction results of future environmental data according to the current or historical environmental data.

[0226] In this embodiment, for the power demand response system scheduling device provided by the present invention based on model prediction, the multi-objective optimization algorithm includes an optimization objective function and a predefined constraint condition set. The optimization objective function contains multiple sub-objectives, and the sub-objectives include minimizing the energy cost, maximizing the energy utilization efficiency, and ensuring environmental stability.

[0227] The energy scheduling screening module is specifically used for:

[0228] Based on the weight coefficients of each sub-goal in the optimization objective function, the sub-goals are weighted and summed to obtain a comprehensive optimization objective function. Combining with the constraint condition set, the configuration parameters are determined through the non-dominated sorting genetic algorithm to construct a configured multi-objective optimization algorithm.

[0229] Call the configured multi-objective optimization algorithm to generate a solution set of approximate Pareto optimal solutions based on the comprehensive optimization objective function and the constraint condition set, and screen out the optimal energy scheduling plan from the solution set according to the actual requirements and priorities.

[0230] Among them, the configuration parameters include population size, number of iterations, crossover rate, and mutation rate. Each solution in the solution set corresponds to an energy scheduling plan.

[0231] This disclosure may be a system, method, and / or computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for causing a processor to implement various aspects of this disclosure.

[0232] The computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device, such as a punched card or raised structures in grooves having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium used herein is not construed as an instantaneous signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0233] The computer-readable program instructions described herein can be downloaded to various computing / processing devices from a computer-readable storage medium or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0234] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer-readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present disclosure.

[0235] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0236] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, when executed by the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more boxes of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that causes a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises a manufacture including instructions for implementing various aspects of the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0237] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, such that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0238] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the boxes may occur out of the order noted in the figures. For example, two consecutive boxes may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each box of the block diagrams and / or flowcharts, and combinations of boxes in the block diagrams and / or flowcharts, can be implemented by a special-purpose hardware-based system for performing the specified functions or acts, or by a combination of special-purpose hardware and computer instructions.

[0239] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for dispatching power demand response based on a dynamic prediction model, characterized in that: The method comprises: Acquire environmental data inside and outside the greenhouse, crop growth demand data, and energy supply data in real time, and pre-process the environmental data, crop growth demand data, and energy supply data to construct a data set; Constructing a gas exchange model and a kinetic nutrient transfer model based on the data set, and outputting parameters and states of the gas exchange model and the kinetic nutrient transfer model; Analyze the parameters and states output by the gas exchange model and the kinetic nutrient transfer model through a Bayesian network to predict the change trend of the environmental data in the greenhouse in the first time period in the future, and output the prediction results of the future environmental data; Formulate an energy scheduling plan based on the prediction results of the future environmental data through a multi-objective optimization algorithm, determine the energy use strategy of the heating, cooling and lighting systems, and output the optimal energy scheduling plan; The environmental data include temperature, humidity, light intensity, carbon dioxide concentration and nutrient solution flow rate; the energy supply data include solar energy and electrical energy; the preprocessing includes missing value processing, outlier detection and data smoothing; the gas exchange model is used to simulate the dynamic changes of carbon dioxide concentration and oxygen in the greenhouse; the kinetic nutrient transport model is used to simulate the transmission and distribution of nutrient solution in the hydroponic system; The step of constructing a gas exchange model and a kinetic nutrient transfer model based on the data set, and outputting parameters and states of the gas exchange model and the kinetic nutrient transfer model, includes: Acquire the first basic parameters required by the gas exchange model from the converted data set, the first basic parameters including the carbon dioxide concentration, oxygen concentration, ventilation rate and photosynthesis rate inside and outside the greenhouse, and construct the first basic data set of the gas exchange model; Based on the first basic data set, a kinetic gas exchange equation is established to describe the change of carbon dioxide concentration and oxygen concentration in the greenhouse over time. The expression of the kinetic gas exchange equation is: In the formula, is the rate of change of carbon dioxide concentration over time, is the rate of change of oxygen concentration over time, is the total volume of greenhouse gases, is the ventilation rate, is the photosynthesis rate, is the concentration of carbon dioxide entering the greenhouse, is the oxygen concentration entering the greenhouse, and are the carbon dioxide concentration and oxygen concentration in the greenhouse at time t, is the total photosynthetic area of ​​crops at time t; Acquire the second basic parameters required by the kinetic nutrient transfer model from the converted data set, the second basic parameters including nutrient solution flow rate, nutrient concentration in the nutrient solution, total plant root area and nutrient absorption rate, and construct a second basic parameter set; Based on the second basic parameter set, a kinetic nutrient transfer equation describing the nutrient changes in the nutrient solution is established. The expression of the kinetic nutrient transfer equation is: In the formula, is the rate of change of nutrient concentration over time, is the volume of the nutrient solution storage tank, is the nutrient concentration of the input nutrient solution, is the total root area of ​​the plant, is the nutrient solution flow rate, is the nutrient concentration in the nutrient solution at time t, is the nutrient absorption rate.

2. The power demand response scheduling method based on the dynamic prediction model according to claim 1 is characterized in that: The real-time acquisition of environmental data inside and outside the greenhouse, crop growth demand data, and energy supply data, and preprocessing of the environmental data, crop growth demand data, and energy supply data to construct a data set includes: Monitoring the environmental data, crop growth demand data and energy supply data inside and outside the greenhouse in real time through multiple sensors and energy monitoring equipment, and constructing an original data set based on the environmental data, crop growth demand data and energy supply data; Filling missing values ​​in the original data set with the mean of the corresponding data column in the original data set as the filling value, and detecting outliers in the original data set using the three sigma principle, so that when an outlier is detected, the outlier is replaced with the median of the corresponding column in the original data set; The raw data set is smoothed by a moving average method, and the cleaned environmental data, crop growth demand data, and energy supply data are integrated to output an integrated data set.

3. The power demand response scheduling method based on the dynamic prediction model according to claim 2 is characterized in that: The real-time acquisition of environmental data inside and outside the greenhouse, crop growth demand data, and energy supply data, and preprocessing the environmental data, crop growth demand data, and energy supply data to construct a data set also includes: Standardizing and normalizing the integrated data set to eliminate the influence of different dimensions and magnitudes in the integrated data set on the gas exchange model and the kinetic nutrient transfer model, and outputting the converted data set; The standardized processing expression is: The normalized expression is: In the formula, and are the i-th row and j-th list elements respectively The standardized and normalized results of is the element in the i-th row and j-th column of the integrated data set, is the mean of the jth column, is the standard deviation of the jth column, and are the minimum and maximum values ​​of the jth column respectively.

4. The power demand response scheduling method based on the dynamic prediction model according to claim 3 is characterized in that: The Bayesian network is used to analyze the parameters and states output by the gas exchange model and the kinetic nutrient transfer model to predict the change trend of the environmental data in the greenhouse in the first time period in the future, and output the prediction results of the future environmental data, including: Constructing a Bayesian network training data set based on the calibrated model output parameters and states, and determining the dependency between the environmental data in the Bayesian network according to the Bayesian network training data set through a structural learning algorithm to construct a Bayesian network structure; The conditional probability table of each node is calculated according to the Bayesian network training data set using a maximum likelihood estimation or Bayesian estimation algorithm, and the Bayesian network is trained in combination with the Bayesian network structure and the Bayesian network training data set, and the model structure and parameters are adjusted through cross-validation to obtain a trained Bayesian network model; Among them, the Bayesian network structure consists of a node set and an edge set, the node set represents each environmental data, the edge set represents the directed dependency relationship between nodes, the structural learning algorithm includes a scoring search algorithm and a constraint-based algorithm, and the trained Bayesian network model is used to predict and output the prediction results of the future environmental data based on current or historical environmental data.

5. The power demand response scheduling method based on the dynamic prediction model according to claim 4 is characterized in that: The multi-objective optimization algorithm includes an optimization objective function and a predefined set of constraints, wherein the optimization objective function includes multiple sub-objectives, wherein the sub-objectives include minimizing energy costs, maximizing energy utilization efficiency, and ensuring environmental stability; The energy scheduling scheme is formulated according to the prediction results of the future environmental data by the multi-objective optimization algorithm, and the energy use strategy of the heating, cooling and lighting systems is determined to output the optimal energy scheduling scheme, including: Based on the weight coefficient of each sub-objective in the optimization objective function, the sub-objectives are weighted and summed to obtain a comprehensive optimization objective function, and the configuration parameters are determined by a non-dominated sorting genetic algorithm in combination with the constraint condition set to construct a configured multi-objective optimization algorithm; Calling the configured multi-objective optimization algorithm to generate a solution set of approximate Pareto optimal solutions based on the comprehensive optimization objective function and the constraint condition set, and screening out the optimal energy scheduling solution from the solution set according to actual needs and priorities; The configuration parameters include population size, number of iterations, crossover rate and mutation rate, and each solution in the solution set corresponds to an energy scheduling scheme.

6. A power demand response system dispatching device based on model prediction, applied to any method of claims 1-5, characterized in that: The device comprises: A data preprocessing module, used to obtain environmental data inside and outside the greenhouse, crop growth demand data, and energy supply data in real time, and preprocess the environmental data, crop growth demand data, and energy supply data to construct a data set; A model building module, used to build a gas exchange model and a kinetic nutrient transfer model based on the data set, and output parameters and states of the gas exchange model and the kinetic nutrient transfer model; A future environment prediction module is used to analyze the parameters and states output by the gas exchange model and the kinetic nutrient transfer model through a Bayesian network to predict the change trend of the environmental data in the greenhouse within the first time period in the future and output the prediction results of the future environmental data; An energy scheduling screening module is used to formulate an energy scheduling plan according to the prediction results of the future environmental data through a multi-objective optimization algorithm, determine the energy use strategy of the heating, cooling and lighting systems, and output the optimal energy scheduling plan; Among them, the environmental data includes temperature, humidity, light intensity, carbon dioxide concentration and nutrient solution flow rate, the energy supply data includes solar energy and electrical energy, the preprocessing includes missing value processing, outlier detection and data smoothing processing, the gas exchange model is used to simulate the dynamic changes of carbon dioxide concentration and oxygen in the greenhouse, and the kinetic nutrient transfer model is used to simulate the transmission and distribution of nutrient solution in the hydroponic system.

7. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images