Energy scheduling control system and method based on demand side response

Abstract

The invention relates to the technical field of energy scheduling control, and particularly discloses an energy scheduling control system and method based on demand side response. Comprising a user side data acquisition module, a user demand prediction analysis module, an energy supply and demand matching analysis module, an energy scheduling instruction generation module, an edge collaborative scheduling control module and an energy scheduling effect evaluation module. According to the method, comprehensive data of a user side is collected, a dynamic demand side response model is constructed in combination with historical data, and a user demand prediction index is obtained through analysis; and fusing the power grid state data and the prediction index, generating an energy supply and demand matching result, further generating a differentiated scheduling instruction, continuously monitoring the scheduling effect through a closed-loop feedback mechanism, and optimizing a subsequent strategy, so that the energy scheduling efficiency and the system flexibility are remarkably improved, the operation cost is reduced, and the power grid stability is enhanced. And renewable energy consumption is effectively promoted, and the method is suitable for energy scheduling scene demand side management of multiple types of users.

Description

Technical Field

[0001] The present invention relates to the technical field of energy dispatching control, and in particular to an energy dispatching control system and method based on demand-side response. Background Art

[0002] With the continuous growth of energy demand and the large-scale access of renewable energy, the power system's demand for flexibility is increasing day by day. The energy dispatching control system based on demand-side response has become an important research direction because it can optimize resource allocation, improve system operation efficiency, and enhance grid stability.

[0003] In the Chinese invention application with the publication number CN112086978B, an energy dispatching and control system based on demand-side response is disclosed, including: a cloud management system, a microgrid subsystem, and a power grid system, providing an energy Internet system based on incentive-based demand-side response. When the peak load of the power system appears, the system dispatching agency sends an interruption request signal to the microgrid subsystem, and the microgrid subsystem responds by turning off the interruptible load and delivering the energy in the energy storage device to the power grid.

[0004] In the above invention application, it mainly relies on a fixed interruption request signal mechanism, lacks in-depth excavation of user-side flexibility resources and real-time dynamic adjustment capabilities, and is difficult to adapt to the complex dispatching requirements under the volatility of new energy output and the scenario of multi-energy flow coupling. In addition, the optimization goal of this system is relatively single, and it fails to fully consider the comprehensive balance of multiple objectives such as economy, environmental protection, and user satisfaction, which may lead to the inflexibility and inefficiency of the dispatching strategy in practical applications. At the same time, the existing technology still has deficiencies in aspects such as intelligent response, real-time performance, and dynamic regulation capabilities, restricting its wide application in complex energy environments. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide an energy dispatching control system and method based on demand-side response to solve the problems proposed in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solution: An energy dispatching control system based on demand-side response, including: a user-side data acquisition module, a user demand prediction and analysis module, an energy supply and demand matching analysis module, an energy dispatching instruction generation module, an edge collaborative dispatching control module, and an energy dispatching effect evaluation module; The user-side data acquisition module: is used to collect the electricity consumption behavior data, device status data, and environmental parameters on the user side in real time through a distributed sensing network, and generate a dynamic demand-side response model in combination with the historical electricity consumption behavior pattern; User demand prediction and analysis module: Based on the collected electricity consumption behavior data and the dynamic demand-side response model, analyze the electricity consumption behavior data to obtain the user demand prediction index; Energy supply and demand matching analysis module: Used to receive the power system grid status data, combine the user demand prediction index, conduct the matching analysis of energy supply and demand, and generate the energy supply and demand matching result; Energy dispatch instruction generation module: Based on the energy supply and demand matching result, generate energy dispatch instructions for different user groups and different time periods, and make real-time corrections to the energy dispatch instructions according to the real-time status of the power grid and the user response behavior; Edge collaborative dispatch control module: Used to receive the energy dispatch instructions, and through the edge computing node or the cloud server, send the energy dispatch instructions to the user-side equipment in real time, and regulate the operation mode of the user-side electrical equipment in real time; Energy dispatch effect evaluation module: Used to monitor the energy dispatch execution result in real time, evaluate the energy dispatch effect based on the actual energy dispatch result, and feedback the evaluation result to the dispatch instruction generation module to optimize the subsequent strategy.

[0007] Preferably, the execution method of the user-side data acquisition module is specifically as follows: Deploy a multi-level distributed sensing network, including an electricity consumption behavior data acquisition layer, a device status data monitoring layer, and an environmental parameter perception layer, and collect the comprehensive data on the user side in real time. The comprehensive data includes electricity consumption behavior data, device status data, and environmental parameters; Preprocess the collected comprehensive data, read the preprocessed comprehensive data, extract the historical electricity consumption behavior pattern data from the local database or cloud storage, integrate the comprehensive data and the historical electricity consumption behavior pattern using a weighted fusion algorithm, and train the integrated data using a deep learning algorithm to generate a dynamic demand-side response model.

[0008] Preferably, the execution method of the user demand prediction and analysis module is specifically as follows: Extract the characteristics of the electricity consumption behavior data, including electric power, electricity consumption, electricity price, and electricity consumption time, and extract the characteristic values of the electricity consumption behavior data. The characteristic values of the electricity consumption behavior data include the peak-valley difference rate of electricity consumption, price sensitivity index, electricity consumption fluctuation coefficient, and electricity consumption time distribution coefficient; Based on the four characteristic values of the peak-valley difference rate of electricity consumption, price sensitivity index, electricity consumption fluctuation coefficient, and electricity consumption time distribution coefficient, calculate the user demand prediction index by taking the fourth root of the product of the four characteristic values Tu .

[0009] Preferably, the extraction method of the peak-valley difference rate of electricity consumption is specifically as follows: Extract all the power consumption data points within the statistical time period from the database, arrange them in chronological order, traverse the extracted power consumption data, and find the maximum value as the peak power consumption , and find the minimum value as the valley power consumption , and obtain the average power consumption , subtract the valley power consumption from the peak power consumption , and then divide the result by the average power consumption to calculate the peak-to-valley difference rate of power consumption ; The extraction method of the price sensitivity index is specifically as follows: Based on the electricity price adjustment records of the power company, determine the time points when the electricity price changes. Taking the electricity price change nodes as the boundaries, divide the statistical time period into two sub-time periods before and after the electricity price change, and respectively count the electricity consumption E before the electricity price change and the total electricity consumption after the change , calculate the change in electricity consumption . At the same time, record the electricity price P before the electricity price change and the electricity price after the change , calculate the change in electricity price , and respectively import them into the price sensitivity index model to calculate the price sensitivity index Sp ; The extraction method of the electricity consumption fluctuation coefficient is specifically as follows: Obtain the number of electricity consumption data points n within the statistical time period, and extract the electricity consumption at each time point within the statistical time period from the database and the average electricity consumption , and respectively import them into the electricity consumption fluctuation coefficient model to calculate the electricity consumption fluctuation coefficient Ce ; The extraction method of the electricity consumption time distribution coefficient is specifically as follows: Divide the statistical time period into m time periods. For each time period j, count the duration of this time period , and calculate the average power consumption within this time period , sum up all the time period durations to determine the total duration of the statistical time period T , and calculate the electricity consumption time distribution coefficient through the electricity consumption time distribution coefficient formula Ct .

[0010] Preferably, the execution method of the energy supply-demand matching analysis module is specifically as follows: Obtain the grid status data of the current power system. The grid status data includes the power supply capacity, grid load level, electricity price information, and various renewable energy output prediction data in the target area within consecutive time periods. At the same time, receive the user demand prediction index from the user demand prediction analysis module; Align the power grid state data and the user demand prediction index in terms of time according to a preset time granularity and perform normalization processing; Construct an energy supply-demand matching matrix with time slices as the horizontal axis and user groups as the vertical axis , where each unit value in the matrix represents the energy supply-demand difference of the h-th user group in the g-th time slice; Set an adjustment weight factor for each user group , and import the adjustment weight factor into the energy supply-demand matching matrix to generate a comprehensive matching index matrix , and analyze and judge the comprehensive matching index matrix to generate an energy supply-demand matching result.

[0011] Preferably, the specific content of analyzing and judging the comprehensive matching index matrix to generate an energy supply-demand matching result is as follows: Perform a traversal analysis on the comprehensive matching index matrix to judge the supply-demand status of each user group in each time slice. If the comprehensive matching index matrix is less than a preset threshold, it is marked as energy supply-demand tension. If the comprehensive matching index matrix is greater than or equal to the preset threshold, it is marked as normal energy supply-demand, and an energy supply-demand matching result is generated according to the classification results of different states.

[0012] Preferably, the execution mode of the edge collaborative scheduling control module is specifically as follows: Receive the energy scheduling instruction from the energy scheduling instruction generation module, decompose the energy scheduling instruction into multiple sub-instructions according to the user group identifier in the energy scheduling instruction, and distribute the sub-instructions to the corresponding edge computing nodes or cloud servers; Receive the sub-instruction, and convert the sub-instruction into a device-level control command according to the user device information library stored locally; Establish a secure communication connection with the user-side device, and send the device-level control command to the user-side device through a wired network, a wireless network or a power line carrier channel; Adjust the operation mode of the user-side electrical equipment according to the sent control command, including the switch state, power level, operation cycle and temperature setting value.

[0013] Preferably, the execution mode of the energy scheduling effect evaluation module is specifically as follows: Obtain the expected target values set in the energy scheduling instruction, including the load response target value Lt, the frequency target value Ft and the cost target value Ct; Collect the actual execution data in the real-time monitoring system, including the actual load response value La, the actual frequency value Fa and the actual cost value Ca; For each parameter value in the expected target value, calculate the absolute difference from the corresponding parameter value in the actual execution data, and obtain the absolute deviation of load response, absolute deviation of frequency, and absolute deviation of cost. Based on the absolute deviation of load response, absolute deviation of frequency, and absolute deviation of cost, calculate the load response deviation rate Ldr, frequency deviation rate Fdr, and cost deviation rate Cdr. Construct an energy dispatch effect evaluation index model, and import the load response deviation rate Ldr, frequency deviation rate Fdr, and cost deviation rate Cdr into the energy dispatch effect evaluation index model respectively to calculate the energy dispatch effect evaluation index.

[0014] To achieve the above object, the present invention provides the following technical solution: An energy dispatch control method based on demand-side response, implementing the above energy dispatch control system based on demand-side response, includes the following steps: S1: Collect user-side data: Real-time collect the electricity consumption behavior data, device status data, and environmental parameters of the user side through a distributed sensing network, and generate a dynamic demand-side response model in combination with the historical electricity consumption behavior pattern. S2: User demand prediction and analysis: Based on the collected electricity consumption behavior data and the dynamic demand-side response model, analyze the electricity consumption behavior data to obtain the user demand prediction index. S3: Energy supply-demand matching analysis: Receive the power system grid status data, and combine the user demand prediction index to perform energy supply-demand matching analysis to generate an energy supply-demand matching result. S4: Generate energy dispatch instructions: Based on the energy supply-demand matching result, generate energy dispatch instructions for different user groups and different time periods, and perform real-time correction of the energy dispatch instructions according to the real-time status of the power grid and the user response behavior. S5: Edge collaborative dispatch control: Receive the energy dispatch instructions, and through the edge computing node or the cloud server, send the energy dispatch instructions to the user-side devices in real time to regulate the operation mode of the user-side electrical equipment in real time. S6: Energy dispatch effect evaluation: Real-time monitor the energy dispatch execution result, evaluate the energy dispatch effect based on the actual energy dispatch result, and feedback the evaluation result to the dispatch instruction generation module to optimize the subsequent strategy.

[0015] As described above, the energy dispatch control system and method based on demand-side response provided by the present invention have at least the following beneficial effects: An energy scheduling control system and method based on demand-side response provided by the present invention collect user electricity consumption behaviors, device states, and environmental parameters in real time through a distributed sensing network, generate a dynamic demand-side response model in combination with historical data, and obtain a user demand prediction index through analysis; an energy supply-demand matching analysis module integrates grid status data and the prediction index to generate an energy supply-demand matching result; an energy scheduling instruction generation module generates differentiated scheduling instructions based on the matching result and corrects the instructions in real time through a dynamic regulation mechanism; an edge collaborative scheduling control module relies on edge computing nodes or cloud servers to achieve real-time regulation of the operation modes of user-side devices; an energy scheduling effect evaluation module evaluates the scheduling effect by monitoring the execution result to form a closed-loop optimization mechanism of "data collection - prediction analysis - matching scheduling - control feedback". The present invention realizes the precise matching and dynamic adjustment of user demands and grid supplies, significantly improves the energy scheduling efficiency, system flexibility, and user response accuracy, effectively reduces the operation cost, enhances the grid stability, and promotes the consumption of renewable energy, and is applicable to scenarios such as smart grids, microgrids, and industrial parks. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on the following drawings without creative efforts.

[0017] Figure 1 It is a schematic structural diagram of an energy scheduling control system based on demand-side response of the present invention.

[0018] Figure 2 It is a schematic flow diagram of an energy scheduling control method based on demand-side response of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0020] Embodiment 1 Please refer to Figure 1 As shown, the present invention provides an energy scheduling control system based on demand-side response, including a user-side data collection module, a user demand prediction and analysis module, an energy supply-demand matching analysis module, an energy scheduling instruction generation module, an edge collaborative scheduling control module, and an energy scheduling effect evaluation module; User-side data acquisition module: It is used to collect real-time electricity consumption behavior data, device status data, and environmental parameters on the user side through a distributed sensing network, and generate a dynamic demand-side response model in combination with historical electricity consumption behavior patterns; In this embodiment, it should be specifically noted that the execution manner of the user-side data acquisition module is as follows: Deploy a multi-level distributed sensing network, including an electricity consumption behavior data acquisition layer, a device status data monitoring layer, and an environmental parameter perception layer, to collect comprehensive data on the user side in real time. The comprehensive data includes electricity consumption behavior data, device status data, and environmental parameters; The electricity consumption behavior data acquisition layer is composed of smart meters, branch metering devices, and current transformers, and collects electricity consumption behavior data such as power, current, voltage, power factor, and electricity consumption; The device status data monitoring layer is composed of smart sockets, smart switches, and device-embedded sensors, and monitors device status data such as device switch status, operation mode, and operation efficiency; The environmental parameter perception layer is composed of temperature and humidity sensors, light sensors, CO2 concentration sensors, and human presence sensors, and collects environmental parameters, where the environmental parameters include temperature, humidity, and light intensity; Preprocess the collected comprehensive data, read the preprocessed comprehensive data, extract historical electricity consumption behavior pattern data from the local database or cloud storage, integrate the comprehensive data and historical electricity consumption behavior patterns using a weighted fusion algorithm, and use a deep learning algorithm to train the integrated data to generate a dynamic demand-side response model. The dynamic demand-side response model can predict the user's future electricity consumption demand based on the current electricity consumption behavior, device status, and environmental parameters.

[0021] Represent the electricity consumption behavior data, device status data, and environmental parameters as vectors respectively, specifically: electricity consumption behavior data vector ,device status data vector ,environmental parameter vector , corresponding to temperature, humidity, and light intensity respectively; The dynamic demand-side response model can be represented by the function M: ,where Y represents the predicted future electricity consumption demand of the user, and H represents the historical electricity consumption behavior pattern data.

[0022] User demand prediction and analysis module: Based on the collected electricity consumption behavior data and the dynamic demand-side response model, analyze the electricity consumption behavior data to obtain a user demand prediction index; In this embodiment, it should be specifically noted that the execution manner of the user demand prediction and analysis module is as follows: Extract the characteristics of electricity consumption behavior data, where the characteristics of the electricity consumption behavior data include electric power, electricity consumption, electricity price, and electricity consumption time, and extract the characteristic values of the electricity consumption behavior data. The characteristic values of the electricity consumption behavior data include the peak-valley difference rate of electricity consumption, the price sensitivity index, the electricity consumption fluctuation coefficient, and the electricity consumption time distribution coefficient; The extraction method of the peak-valley difference rate of electricity consumption is as follows: Extract all the electric power data points within the statistical time period from the database, arrange them in chronological order, traverse the extracted electric power data, and find the maximum value as the peak value of electric power , and the minimum value as the valley value of electric power , and obtain the average electric power , subtract the peak value of electric power from the valley value of electric power , and then divide the result by the average electric power to calculate the peak-valley difference rate of electricity consumption ; It should be specifically noted that one day is used as the statistical time period.

[0023] The extraction method of the price sensitivity index is as follows: Based on the electricity price adjustment records of the power company, determine the time points when the electricity price changes. Taking the electricity price change nodes as the boundaries, divide the statistical time period into two sub-time periods before and after the electricity price change, and respectively count the electricity consumption E before the electricity price change and the total electricity consumption after the change , calculate the change amount of electricity consumption , at the same time, record the electricity price P before the electricity price change and the electricity price after the change , calculate the change amount of electricity price , and respectively import them into the price sensitivity index model to calculate the price sensitivity index Sp ; The calculation formula of the price sensitivity index model is: , and the price sensitivity index reflects the sensitivity of the user's electricity consumption to the change of electricity price. The larger the index, the more sensitive the user is to the change of electricity price; The extraction method of the electricity consumption fluctuation coefficient is as follows: Obtain the number of electricity consumption data points n within the statistical time period, and extract the electricity consumption at each time point within the statistical time period from the database and the average electricity consumption , and respectively import them into the electricity consumption fluctuation coefficient model to calculate the electricity consumption fluctuation coefficient Ce ; The calculation formula of the electricity consumption fluctuation coefficient is: ,The electricity consumption fluctuation coefficient reflects the fluctuation of the user’s electricity consumption during the statistical time period. The larger the coefficient is, the more dramatic the fluctuation of electricity consumption; The method for extracting the power consumption time distribution coefficient is as follows: Divide the statistical time period into m time periods, and for each time period j, count the duration of the time period , and calculate the average power consumption during this period , sum up the duration of all time periods to determine the total duration of the statistical time period T The power consumption time distribution coefficient is calculated by the power consumption time distribution coefficient formula Ct ; The calculation formula of the power consumption time distribution coefficient is: ,The electricity consumption time distribution coefficient reflects the distribution characteristics of the user’s electricity consumption in different time periods, and the size of the coefficient can reflect the concentration of the user’s electricity consumption in each time period; Based on the four characteristic values of electricity peak-valley difference rate, price sensitivity index, electricity consumption fluctuation coefficient and electricity consumption time distribution coefficient, the user demand forecast index is calculated by taking the fourth root of the product of the four characteristic values. Tu .

[0024] The user demand prediction index Tu The calculation formula is: .

[0025] Energy supply and demand matching analysis module: used to receive power system grid status data, combine user demand forecast index, perform energy supply and demand matching analysis, and generate energy supply and demand matching results; In this embodiment, it should be specifically explained that the execution method of the energy supply and demand matching analysis module is as follows: Acquire the grid status data of the current power system, wherein the grid status data includes the power supply capacity of the target area in a continuous period, the grid load level, electricity price information and various renewable energy output forecast data, and at the same time, receive the user demand forecast index from the user demand forecast analysis module; According to the preset time granularity (such as 15 minutes as a time slice), the grid status data and the user demand forecast index are time-aligned and normalized; Construct an energy supply and demand matching matrix with time slices as the horizontal axis and user groups as the vertical axis , each cell value in the matrix represents the energy supply and demand difference of the hth user group in the gth time slice; The specific calculation method is: ,in, represents the power supply capability value of the hth user group in the gth time slice, It represents the predicted electricity demand value of the h-th user group in the g-th time slice; Set an adjustment weight factor for each user group , and import the adjustment weight factor into the energy supply-demand matching matrix to generate a comprehensive matching index matrix , and analyze and judge the comprehensive matching index matrix to generate an energy supply-demand matching result; The specific calculation method of the comprehensive matching index matrix is as follows: , and the comprehensive matching index is used to measure the degree of supply-demand imbalance and its adjustment priority under a specific time slice and user group.

[0026] In this embodiment, it should be specifically noted that the specific content of analyzing and judging the comprehensive matching index matrix to generate an energy supply-demand matching result is as follows: Traverse and analyze the comprehensive matching index matrix to judge the supply-demand status of each user group in each time slice. If the comprehensive matching index matrix is less than the preset threshold, it is marked as energy supply-demand tension. If the comprehensive matching index matrix is greater than or equal to the preset threshold, it is marked as normal energy supply-demand, and an energy supply-demand matching result is generated according to the classification results of different states.

[0027] Energy scheduling instruction generation module: Based on the energy supply-demand matching result, generate energy scheduling instructions for different user groups and different time periods, and make real-time corrections to the energy scheduling instructions according to the real-time state of the power grid and the user response behavior; In this embodiment, it should be specifically noted that the execution method of the energy scheduling instruction generation module is as follows: Receive the energy supply-demand matching result transmitted by the energy supply-demand matching analysis module, generate energy scheduling instructions for different user groups and different time periods based on the energy supply-demand matching result, and make real-time corrections to the energy scheduling instructions according to the real-time state of the power grid and the user response behavior; For example, for a user in an industrial park, the energy scheduling instruction generation module may generate an instruction to lower the air conditioner temperature setting value; for a residential user, it may generate an instruction to postpone the start time of the washing machine.

[0028] Edge collaborative scheduling control module: Used to receive the energy scheduling instruction, and through an edge computing node or a cloud server, send the energy scheduling instruction to the user-side device in real time to regulate the operation mode of the user-side electrical equipment in real time; In this embodiment, it should be specifically noted that the execution method of the edge collaborative scheduling control module is as follows: Receive the energy dispatch instruction of the energy dispatch instruction generation module, decompose the energy dispatch instruction into multiple sub-instructions according to the user group identifier in the energy dispatch instruction, and distribute the sub-instructions to the corresponding edge computing nodes or cloud servers; Receive the sub-instruction, and convert the sub-instruction into a device-level control command according to the user device information library stored locally; Establish a secure communication connection with the user-side device, and send the device-level control command to the user-side device through a wired network, a wireless network or a power line carrier channel; Adjust the operation mode of the user-side electrical equipment according to the issued control command, including the switch state, power level, operation cycle and temperature set value.

[0029] Energy dispatch effect evaluation module: used to monitor the execution result of energy dispatch in real time, evaluate the energy dispatch effect based on the actual energy dispatch result, and feedback the evaluation result to the dispatch instruction generation module to optimize the subsequent strategy.

[0030] In this embodiment, it should be specifically noted that the execution method of the energy dispatch effect evaluation module is as follows: Obtain the expected target values set in the energy dispatch instruction, including the load response target value Lt, the frequency target value Ft and the cost target value Ct; Collect the actual execution data in the real-time monitoring system, including the actual load response value La, the actual frequency value Fa and the actual cost value Ca; Take the absolute value of the difference between the corresponding parameter values in the expected target value and the corresponding parameter values in the actual execution data respectively, and calculate the load response absolute deviation, the frequency absolute deviation and the cost absolute deviation; Based on the load response absolute deviation, the frequency absolute deviation and the cost absolute deviation, calculate the load response deviation rate Ldr, the frequency deviation rate Fdr and the cost deviation rate Cdr; The specific calculation formula is as follows: , where Ldr represents the load response deviation rate; , where Fdr represents the frequency deviation rate; , where Cdr represents the cost deviation rate; Construct an energy dispatch effect evaluation index model, import the load response deviation rate Ldr, the frequency deviation rate Fdr and the cost deviation rate Cdr into the energy dispatch effect evaluation index model respectively, and calculate the energy dispatch effect evaluation index; The specific calculation formula of the energy dispatch effect evaluation index ESI is as follows; , where respectively represent the weight coefficients of the load response deviation rate, the frequency deviation rate, and the cost deviation rate, and ; Based on the energy dispatch effect evaluation index, the energy dispatch effect is evaluated. The specific evaluation content is as follows: Compare the energy dispatch effect evaluation index with the preset effect evaluation index threshold. If the energy dispatch effect evaluation index is greater than or equal to the preset effect evaluation index threshold, it is determined that the energy dispatch effect meets the expectation. If the energy dispatch effect evaluation index is less than the preset effect evaluation index threshold, it is determined that the energy dispatch effect does not meet the expectation. Mark the data where the energy dispatch effect does not meet the expectation as the energy dispatch effect evaluation result, and feedback the evaluation result to the dispatch instruction generation module to optimize subsequent strategies.

[0031] Embodiment 2 Please refer to Figure 2 As shown, the present invention provides an energy dispatch control method based on demand-side response, including the following steps: S1: Collect user-side data, S2: User demand prediction analysis, S3: Energy supply and demand matching analysis, S4: Generate energy dispatch instructions, S5: Edge collaborative dispatch control, and S6: Energy dispatch effect evaluation; S1: Collect user-side data: Real-time collect the electricity consumption behavior data, device status data, and environmental parameters on the user side through a distributed sensing network, and generate a dynamic demand-side response model in combination with the historical electricity consumption behavior pattern; S2: User demand prediction analysis: Based on the collected electricity consumption behavior data and the dynamic demand-side response model, analyze the electricity consumption behavior data to obtain a user demand prediction index; S3: Energy supply and demand matching analysis: Receive the power system grid status data, combine the user demand prediction index, perform matching analysis of energy supply and demand, and generate an energy supply and demand matching result; S4: Generate energy dispatch instructions: Based on the energy supply and demand matching result, generate energy dispatch instructions for different user groups and different time periods, and perform real-time correction of the energy dispatch instructions according to the real-time status of the power grid and the user response behavior; S5: Edge collaborative dispatch control: Receive the energy dispatch instructions, and through an edge computing node or a cloud server, send the energy dispatch instructions to the user-side devices in real time to regulate the operation mode of the user-side electrical equipment in real time; S6: Energy dispatch effect evaluation: Real-time monitor the energy dispatch execution result, evaluate the energy dispatch effect based on the actual energy dispatch result, and feedback the evaluation result to the dispatch instruction generation module to optimize subsequent strategies.

[0032] Finally, the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

[0033] As described above, this is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or replacements, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claimed rights.

Claims

1. An energy scheduling and control system based on demand response, characterized in that, Including: User-side data acquisition module: It is used to collect the electricity consumption behavior data, device status data and environmental parameters on the user side in real time through a distributed sensing network, and generate a dynamic demand-side response model in combination with historical electricity consumption behavior patterns; User demand prediction and analysis module: Based on the collected electricity consumption behavior data and the dynamic demand-side response model, analyze the electricity consumption behavior data to obtain the user demand prediction index; Energy supply-demand matching analysis module: It is used to receive the grid status data of the power system, combine the user demand prediction index, conduct matching analysis of energy supply and demand, and generate an energy supply-demand matching result; Energy scheduling instruction generation module: Based on the energy supply-demand matching result, generate energy scheduling instructions for different user groups and different time periods, and make real-time corrections to the energy scheduling instructions according to the real-time status of the power grid and the user response behavior; Edge collaborative scheduling and control module: It is used to receive the energy scheduling instructions, and through edge computing nodes or cloud servers, send the energy scheduling instructions to the user-side devices in real time to regulate the operation mode of the user-side electrical equipment in real time; Energy scheduling effect evaluation module: It is used to monitor the execution result of energy scheduling in real time, evaluate the energy scheduling effect based on the actual energy scheduling result, and feedback the evaluation result to the scheduling instruction generation module to optimize subsequent strategies.

2. The energy scheduling and control system based on demand-side response according to claim 1, wherein: The execution method of the user-side data acquisition module is specifically as follows: Deploy a multi-level distributed sensing network, including an electricity consumption behavior data acquisition layer, a device status data monitoring layer, and an environmental parameter perception layer, to collect comprehensive data on the user side in real time. The comprehensive data includes electricity consumption behavior data, device status data, and environmental parameters; Preprocess the collected comprehensive data, read the preprocessed comprehensive data, extract historical electricity consumption behavior pattern data from the local database or cloud storage, integrate the comprehensive data and historical electricity consumption behavior patterns using a weighted fusion algorithm, and use a deep learning algorithm to train the integrated data to generate a dynamic demand-side response model.

3. The energy scheduling and control system based on demand-side response according to claim 1, wherein: The execution method of the user demand prediction and analysis module is specifically as follows: Extract the characteristics of the electricity consumption behavior data, including electric power, electricity consumption, electricity price, and electricity consumption time, and extract the characteristic values of the electricity consumption behavior data. The characteristic values of the electricity consumption behavior data include the peak-valley difference rate of electricity consumption, price sensitivity index, electricity consumption fluctuation coefficient, and electricity consumption time distribution coefficient; Based on four characteristic values, namely the peak-valley difference rate of electricity consumption, the price sensitivity index, the electricity consumption fluctuation coefficient, and the electricity consumption time distribution coefficient, the user demand prediction index is calculated by taking the fourth root of the product of the four characteristic values Tu .

4. The energy dispatching and control system based on demand side response according to claim 3, wherein: The extraction method of the peak-valley difference rate of electricity consumption is specifically as follows: Extract all the power consumption data points within the statistical time period from the database, arrange them in chronological order, traverse the extracted power consumption data, and find the maximum value as the peak power consumption , and find the minimum value as the valley power consumption , and obtain the average power consumption , subtract the valley power consumption from the peak power consumption , and then divide the result by the average power consumption to calculate the peak-to-valley difference rate of power consumption ; The extraction method of the price sensitivity index is specifically as follows: Determine the time point when the electricity price changes based on the electricity price adjustment records of the power company. Taking the electricity price change node as the boundary, divide the statistical time period into two sub-time periods before and after the electricity price change, and respectively count the electricity consumption E before the electricity price change and the total electricity consumption after the change , and calculate the change in electricity consumption . At the same time, record the electricity price P before the electricity price change and the electricity price after the change , and calculate the change in electricity price . Import them into the price sensitivity index model respectively to calculate the price sensitivity index Sp ; The extraction method of the electricity consumption fluctuation coefficient is specifically as follows: Obtain the number of electricity consumption data points \(n\) within the statistical time period, and extract the electricity consumption at each time point within the statistical time period from the database and the average electricity consumption , respectively import them into the electricity consumption fluctuation coefficient model, and calculate the electricity consumption fluctuation coefficient Ce ; The extraction method of the electricity consumption time distribution coefficient is specifically as follows: Divide the statistical time period into m time intervals. For each time interval j, count the duration of this time interval , and calculate the average power consumption within this time interval . Sum up the durations of all time intervals to determine the total duration of the statistical time period T . Calculate the power consumption time distribution coefficient through the power consumption time distribution coefficient formula Ct .

5. The energy scheduling and control system based on demand side response according to claim 1, characterized in that: The execution method of the energy supply-demand matching analysis module is specifically as follows: Obtain the grid status data of the current power system. The grid status data includes the power supply capacity, grid load level, electricity price information, and predicted data of various renewable energy outputs in the target area within a continuous time period. At the same time, receive the user demand prediction index from the user demand prediction and analysis module; According to the preset time granularity, align the grid status data and the user demand prediction index in time and perform normalization processing; Construct an energy supply-demand matching matrix with the time slice as the horizontal axis and the user group as the vertical axis , where the value of each unit in the matrix represents the energy supply-demand difference of the h-th user group at the g-th time slice; Set adjustment weight factors for each user group and import the adjustment weight factors into the energy supply-demand matching matrix to generate a comprehensive matching index matrix and analyze and judge the comprehensive matching index matrix to generate the energy supply-demand matching result.

6. The energy scheduling and control system based on demand response according to claim 5, wherein: The specific content of analyzing and judging the comprehensive matching index matrix to generate the energy supply - demand matching result is as follows: Traverse and analyze the comprehensive matching index matrix to judge the supply and demand status of each user group in each time slice. If the comprehensive matching index matrix is less than the preset threshold, it is marked as energy supply-demand tension. If the comprehensive matching index matrix is greater than or equal to the preset threshold, it is marked as normal energy supply and demand. According to the classification results of different states, generate the energy supply-demand matching results.

7. The energy dispatching control system based on demand side response according to claim 1, characterized in that: The execution mode of the edge collaborative scheduling control module is specifically as follows: Receive the energy scheduling instruction from the energy scheduling instruction generation module. According to the user group identifier in the energy scheduling instruction, decompose the energy scheduling instruction into multiple sub - instructions, and distribute the sub - instructions to the corresponding edge computing nodes or cloud servers; Receive the sub - instruction, and convert the sub - instruction into a device - level control command according to the user device information library stored locally; Establish a secure communication connection with the user - side device, and send the device - level control command to the user - side device through a wired network, a wireless network or a power line carrier channel; According to the issued control command, adjust the operation mode of the user - side electrical equipment, including the switch state, power level, operation cycle and temperature set value.

8. The energy scheduling and control system based on demand-side response according to claim 1, wherein: The execution mode of the energy scheduling effect evaluation module is specifically as follows: Obtain the expected target values set in the energy scheduling instruction, including the load response target value Lt, the frequency target value Ft and the cost target value Ct; Collect the actual execution data in the real - time monitoring system, including the actual load response value La, the actual frequency value Fa and the actual cost value Ca; Take the difference between the corresponding parameter values in the expected target value and the corresponding parameter values in the actual execution data and take the absolute value respectively, and calculate the absolute deviation of load response, absolute deviation of frequency, and absolute deviation of cost; Based on the absolute deviation of load response, absolute deviation of frequency, and absolute deviation of cost, calculate the load response deviation rate Ldr, frequency deviation rate Fdr, and cost deviation rate Cdr; Construct an energy scheduling effect evaluation index model, import the load response deviation rate Ldr, frequency deviation rate Fdr, and cost deviation rate Cdr into the energy scheduling effect evaluation index model respectively, and calculate the energy scheduling effect evaluation index.

9. A method for energy scheduling control based on demand response, which is used for an energy scheduling control system based on demand response described in any one of the above claims 1-8, characterized in that, It includes the following steps: S1: Collect user - side data: Real - time collect the electricity consumption behavior data, device status data and environmental parameters on the user side through a distributed sensing network, and generate a dynamic demand - side response model in combination with the historical electricity consumption behavior pattern; S2: User demand prediction and analysis: Based on the collected electricity consumption behavior data and the dynamic demand - side response model, analyze the electricity consumption behavior data to obtain the user demand prediction index; S3: Energy supply - demand matching analysis: Receive the power system grid status data, and combine with the user demand prediction index to conduct the matching analysis of energy supply and demand, and generate the energy supply - demand matching result; S4: Generate energy scheduling instructions: Based on the energy supply - demand matching result, generate energy scheduling instructions for different user groups and different time periods, and make real - time corrections to the energy scheduling instructions according to the real - time status of the power grid and the user response behavior; S5: Edge collaborative scheduling control: Receive the energy scheduling instruction, and through the edge computing node or cloud server, send the energy scheduling instruction to the user - side device in real - time, and regulate the operation mode of the user - side electrical equipment in real - time; S6: Evaluation of energy scheduling effect: Monitor the execution result of energy scheduling in real time, evaluate the energy scheduling effect based on the actual energy scheduling result, and feedback the evaluation result to the scheduling instruction generation module to optimize subsequent strategies.

Images