A cloud-based energy optimization control system and method

Abstract

This application provides an energy optimization control system and method based on a cloud platform. It extracts the energy distribution fluctuation characteristics of the dispatching unit during energy switching at different time periods, and then determines the energy distribution fluctuation coefficient of the dispatching unit during energy switching based on these characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution conditions. Next, it determines the energy distribution imbalance degree of the photovoltaic-storage capacity configuration of the dispatching unit at different time periods, and then determines the capacity configuration loss of the dispatching unit during the photovoltaic-storage capacity configuration adjustment process based on the energy distribution imbalance degree and the time-varying response characteristics of the photovoltaic-storage capacity configuration. Based on the energy distribution fluctuation coefficient and capacity configuration loss, it optimizes the cost of the photovoltaic-storage capacity configuration during energy switching at different time periods, and then optimizes and controls the photovoltaic-storage energy switching process in the energy management cloud platform based on the optimized photovoltaic-storage capacity configuration. Using the scheme of this application, optimal cost control of the photovoltaic-storage energy switching process can be achieved.

Description

Technical Field

[0001] This application relates to the field of energy optimization control technology, and more specifically, to an energy optimization control system and method based on a cloud platform. Background Technology

[0002] In energy management systems, the coordinated operation of photovoltaic power generation and energy storage systems has become a key means to improve energy utilization efficiency and ensure the stability of power supply. With the continuous increase in the proportion of new energy sources, the dynamic response capability of photovoltaic and energy storage systems under load fluctuations and changes in environmental conditions has an important impact on the overall power dispatch. Rational planning of photovoltaic and energy storage capacity configuration and optimization of energy switching strategies can not only reduce system operating costs, but also effectively alleviate grid pressure and ensure the reliability of power supply during peak load periods.

[0003] Existing energy regulation methods have significant limitations in practical applications, especially during the switching between photovoltaic (PV) and energy storage (ESS) energy sources. These methods struggle to quantify and control operational losses caused by power distribution fluctuations and capacity adjustments. Traditional approaches typically employ fixed configuration parameters or empirical rules for PV and ESS output scheduling, neglecting the characteristics of power distribution fluctuations under different load periods and switching nodes. This leads to insufficient power distribution, delayed response, or capacity overruns during switching, increasing system operational risks and energy costs. Furthermore, these methods lack comparative analysis of steady-state power distribution parameters and actual operational fluctuations, making it impossible to dynamically assess the impact of PV-ESS capacity configuration on system stability and economics. Therefore, achieving optimal cost control during the PV-ESS switching process has become a significant challenge for the industry. Summary of the Invention

[0004] This application provides an energy optimization control system and method based on a cloud platform, which can achieve optimal cost control in the photovoltaic-storage energy switching process.

[0005] In a first aspect, this application provides an energy optimization control method based on a cloud platform, comprising the following steps: Acquire historical operational big data of the dispatching unit in the energy management cloud platform regarding the dispatching of photovoltaic and energy storage energy; Extract the energy distribution fluctuation characteristics of the dispatching unit during energy switching at different time periods from the historical operational big data, and then determine the energy distribution fluctuation coefficient of the dispatching unit during energy switching based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution. Based on the historical operational big data, the energy distribution imbalance of the photovoltaic and energy storage capacity configuration of the allocation unit at different time periods is determined, and then the capacity configuration loss of the allocation unit in the process of adjusting the photovoltaic and energy storage capacity configuration is determined according to the energy distribution imbalance and the time-varying response characteristics of the photovoltaic and energy storage capacity configuration. Based on the energy distribution fluctuation coefficient and the capacity configuration loss, the cost optimization of the photovoltaic and energy storage capacity configuration during the energy switching process at different time periods is carried out, and then the photovoltaic and energy storage energy switching process in the energy management cloud platform is optimized and controlled based on the optimized photovoltaic and energy storage capacity configuration.

[0006] Preferably, the historical operational big data includes power distribution data, photovoltaic and energy storage capacity data, and load demand data.

[0007] Preferably, extracting the energy distribution fluctuation characteristics of the dispatching unit during energy switching at different time periods from the historical operational big data specifically includes: Determine the time period division rules for the dispatching units in the energy management cloud platform, and divide the time period into peak load period, off-peak load period, and low load period according to the time period division rules; Identify energy switching nodes in each time period, including the time points when switching from photovoltaic power supply to energy storage power supply, switching from energy storage power supply to hybrid power supply, and switching from hybrid power supply to grid supplementary power supply. Time windows are set before and after each energy switching node, and power distribution data within the corresponding time window is filtered from historical operational big data. The power distribution data includes the actual energy distribution of photovoltaic, the actual energy distribution of energy storage, and the total energy distribution. Based on power distribution data, determine the energy distribution deviation magnitude and energy distribution volatility at the corresponding energy switching node, and then determine the volatility index of the corresponding energy switching node. The energy distribution fluctuation characteristics of the dispatching unit during the energy switching process at different time periods are determined based on the fluctuation indicators of all energy switching nodes.

[0008] Preferably, determining the energy distribution fluctuation coefficient of the dispatching unit during energy switching based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution conditions specifically includes: Obtain operational data of the steady-state energy distribution status of the allocation unit at different time periods; The steady-state energy distribution parameters are determined based on the operating data for different time periods. The steady-state energy distribution parameters include the steady-state average energy distribution and the upper limit of steady-state energy distribution fluctuation. The energy distribution fluctuation characteristics during the energy switching process in each time period are compared and analyzed with the steady-state energy distribution parameters of the corresponding steady-state energy distribution state. The energy distribution fluctuation coefficient of the dispatching unit during the energy switching process was determined by comparing and analyzing the results.

[0009] Preferably, determining the energy distribution imbalance of the photovoltaic-storage capacity configuration of the allocation unit at different time periods based on the historical operational big data specifically includes: Determine the target energy allocation demand for different time periods, including the target energy allocation for photovoltaics, the target energy allocation for energy storage, and the ratio of photovoltaic-energy storage synergistic energy allocation. The actual energy distribution demand for different time periods is extracted from the historical operational big data. The actual energy distribution demand includes the actual photovoltaic energy distribution, the actual energy storage energy distribution, and the actual photovoltaic-energy storage synergistic energy distribution ratio. The energy distribution demand deviation is determined based on the target energy distribution demand and the actual energy distribution demand. The energy distribution demand deviation includes photovoltaic energy distribution deviation, energy storage energy distribution deviation, and synergy ratio deviation. Based on the preset energy distribution balance weights, the deviations in the energy distribution demand deviations are weighted and summed to obtain the energy distribution imbalance of the photovoltaic storage capacity configuration of the allocation unit at different time periods.

[0010] Preferably, determining the capacity configuration loss of the allocation unit during the photovoltaic-storage capacity configuration adjustment process based on the energy distribution imbalance degree and the time-varying response characteristics of the photovoltaic-storage capacity configuration specifically includes: Extract time-varying response characteristic parameters of photovoltaic and energy storage capacity configuration, including photovoltaic output response delay time, energy storage charge and discharge response speed and photovoltaic and energy storage capacity adjustment rate; Based on the time-varying response characteristic parameters and the energy imbalance of photovoltaic-storage capacity configuration at different time periods, the delay loss and over-limit loss during the capacity adjustment process are determined. The capacity configuration loss of the allocation unit during the photovoltaic-storage capacity configuration adjustment process is determined based on the delay loss and the over-limit loss.

[0011] Preferably, optimizing and controlling the photovoltaic-storage energy switching process in the energy management cloud platform based on the optimized photovoltaic-storage capacity configuration specifically includes: The optimized photovoltaic and energy storage capacity configuration parameters are sent to the allocation unit of the energy management cloud platform; During the photovoltaic-storage energy switching process, the photovoltaic power supply ratio, energy storage charging and discharging power, and grid connection conditions are adjusted according to the photovoltaic-storage capacity configuration parameters. Furthermore, the photovoltaic-storage capacity configuration parameters are updated based on the operation data of the energy management cloud platform.

[0012] Secondly, this application provides a cloud platform-based energy optimization control system, comprising: The acquisition module is used to acquire historical operational big data of the dispatching unit in the energy management cloud platform in the dispatching of photovoltaic and energy storage energy; The processing module is used to extract the energy distribution fluctuation characteristics of the dispatching unit during the energy switching process at different time periods from the historical operation big data, and then determine the energy distribution fluctuation coefficient of the dispatching unit during the energy switching process based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution. The processing module is also used to determine the energy imbalance of the photovoltaic-storage capacity configuration of the allocation unit at different time periods based on the historical operational big data, and then determine the capacity configuration loss of the allocation unit in the process of adjusting the photovoltaic-storage capacity configuration based on the energy imbalance and the time-varying response characteristics of the photovoltaic-storage capacity configuration. The execution module is used to optimize the cost of photovoltaic and energy storage capacity configuration during energy switching at different time periods based on the energy distribution fluctuation coefficient and the capacity configuration loss, and then optimize and control the photovoltaic and energy storage energy switching process in the energy management cloud platform based on the optimized photovoltaic and energy storage capacity configuration.

[0013] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described cloud platform-based energy optimization control method.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned cloud-based energy optimization control method.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: In this embodiment, historical operational big data of the dispatching unit in the energy management cloud platform during photovoltaic-storage energy dispatching is first obtained. Energy distribution fluctuation characteristics of the dispatching unit during energy switching at different time periods are extracted from the historical operational big data. Then, based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution conditions, the energy distribution fluctuation coefficient of the dispatching unit during energy switching is determined. Based on the historical operational big data, the energy distribution imbalance degree of the dispatching unit in photovoltaic-storage capacity configuration at different time periods is determined. Then, based on the energy distribution imbalance degree and the time-varying response characteristics of the photovoltaic-storage capacity configuration, the capacity configuration loss of the dispatching unit during the photovoltaic-storage capacity configuration adjustment process is determined. Based on the energy distribution fluctuation coefficient and the capacity configuration loss, the cost of the photovoltaic-storage capacity configuration during energy switching at different time periods is optimized. Finally, based on the optimized photovoltaic-storage capacity configuration, the photovoltaic-storage energy switching process in the energy management cloud platform is optimized and controlled.

[0016] Therefore, this application optimizes the photovoltaic-storage capacity configuration during energy switching at different time periods based on the energy distribution fluctuation coefficient and the capacity configuration loss, and then optimizes and regulates the photovoltaic-storage energy switching process in the energy management cloud platform based on the optimized photovoltaic-storage capacity configuration. First, by extracting the energy distribution fluctuation characteristics of the energy switching process at different time periods and calculating the energy distribution fluctuation coefficient in combination with steady-state energy distribution parameters, the output fluctuation of the photovoltaic and energy storage systems during the switching process is quantified, providing an accurate and measurable basis for capacity configuration optimization, thereby improving the accuracy and dynamic stability of energy dispatch. Second, by calculating the energy distribution imbalance of the photovoltaic-storage capacity configuration based on historical operating data and determining the capacity configuration loss in combination with the time-varying response characteristics of the photovoltaic-storage capacity configuration, the impact of photovoltaic-storage system response delay and capacity over-limit on system stability can be comprehensively reflected, realizing a quantitative assessment of the loss in the allocation process, providing reliable constraints for cost optimization, and reducing the risk of insufficient energy distribution and over-limit during the switching process. Then, by constructing a cost optimization... The objective function is optimized, and the optimal photovoltaic-storage capacity configuration is searched using a particle swarm optimization algorithm within the adjustable parameter range. This ensures that the real-time photovoltaic energy distribution ratio, energy storage charging and discharging power, and switching trigger threshold are both stable and economical, achieving dynamic optimal scheduling under different load periods. Finally, based on the optimized photovoltaic-storage capacity configuration, the photovoltaic-storage energy switching process of the energy management cloud platform is controlled in real time, and dynamic feedback correction is performed in conjunction with operational data to ensure that the optimization results can adapt to changes in actual operating conditions, improving the reliability and flexibility of system scheduling. In summary, the proposed solution can achieve optimal cost control of the photovoltaic-storage energy switching process, thereby improving the dynamic response accuracy and scheduling stability of the photovoltaic and energy storage systems under different load periods, effectively reducing system losses caused by energy distribution fluctuations and capacity overruns, optimizing energy utilization efficiency, enhancing the reliability of photovoltaic-storage collaborative operation, and achieving intelligent and quantifiable energy regulation while ensuring system economy, providing efficient, safe, and sustainable operation management capabilities for the energy management cloud platform. Attached Figure Description

[0017] Figure 1 This is an exemplary flowchart of a cloud-based energy optimization control method according to some embodiments of this application; Figure 2 This is a schematic flowchart illustrating the process of determining the energy distribution fluctuation coefficient according to some embodiments of this application; Figure 3 This is a schematic flowchart illustrating the process of determining the energy imbalance degree according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of a cloud-based energy optimization control system according to some embodiments of this application; Figure 5This is a schematic diagram of the structure of a computer device that implements a cloud-based energy optimization control method according to some embodiments of this application. Detailed Implementation

[0018] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] refer to Figure 1 The figure is an exemplary flowchart of a cloud-based energy optimization control method according to some embodiments of this application. The cloud-based energy optimization control method mainly includes the following steps: In step 101, historical operational big data of the dispatching unit in the energy management cloud platform in the dispatching of photovoltaic and energy storage is obtained.

[0020] It should be noted that the historical operational big data in this application includes power distribution data, photovoltaic and energy storage capacity data, and load demand data; the dispatching unit in this application refers to the execution unit responsible for the distribution and switching control of photovoltaic, energy storage, and grid energy in the energy management cloud platform; in specific implementation, the operational data of photovoltaic and energy storage energy management process can be collected through the data acquisition module in the energy management cloud platform, and the collected operational data can be stored in the database of the energy management cloud platform. Then, the historical operational big data of the dispatching unit in photovoltaic and energy storage energy dispatching in the energy management cloud platform can be obtained from the database. It should be further noted that the historical operating period in this application can be set to 3 to 5 years, and there is no specific limitation. If the energy management cloud platform is cold-started, the operational big data of the same type of energy management cloud platform can also be used for control optimization.

[0021] In step 102, the energy distribution fluctuation characteristics of the dispatching unit during the energy switching process at different time periods are extracted from the historical operational big data. Then, based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution conditions, the energy distribution fluctuation coefficient of the dispatching unit during the energy switching process is determined.

[0022] In some embodiments, extracting the energy distribution fluctuation characteristics of the dispatching unit during energy switching at different time periods from the historical operational big data can be achieved by the following steps: Determine the time period division rules for the dispatching units in the energy management cloud platform, and divide the time period into peak load period, off-peak load period, and low load period according to the time period division rules; Identify energy switching nodes in each time period, including the time points when switching from photovoltaic power supply to energy storage power supply, switching from energy storage power supply to hybrid power supply, and switching from hybrid power supply to grid supplementary power supply. Time windows are set before and after each energy switching node, and power distribution data within the corresponding time window is filtered from historical operational big data. The power distribution data includes the actual energy distribution of photovoltaic, the actual energy distribution of energy storage, and the total energy distribution. Based on power distribution data, determine the energy distribution deviation magnitude and energy distribution volatility at the corresponding energy switching node, and then determine the volatility index of the corresponding energy switching node. The energy distribution fluctuation characteristics of the dispatching unit during the energy switching process at different time periods are determined based on the fluctuation indicators of all energy switching nodes.

[0023] It should be noted that, in this application, the energy switching node refers to the critical time point at which the energy supply mode between photovoltaic, energy storage and the grid changes; the energy distribution deviation amplitude refers to the difference between the actual energy distribution at the energy switching node and the target energy distribution, used to quantify the degree of instantaneous energy supply deviation; the energy distribution volatility rate refers to the rate of change of energy distribution within a set time window before and after the energy switching node, used to reflect the degree of energy supply instability; and the energy distribution volatility characteristics in this application are used to describe the overall energy supply volatility behavior of the dispatching unit during the energy switching process.

[0024] In specific implementation, the time period division rules for the dispatching units in the energy management cloud platform are determined. Dividing the time periods into peak load periods, off-peak load periods, and low load periods according to these rules can be achieved in the following way: First, historical load data of the dispatching units is retrieved from the energy management cloud platform. This historical load data is preprocessed, including removing outliers, filling in missing values, and smoothing the data using a moving average to obtain a relatively stable load curve. Then, based on the typical daily load curve, the time period boundaries are determined using the statistical quantile threshold method. The quantile thresholds can be set to 75% and 25%, and continuous periods above 75% are defined as peak load periods. A continuous period of less than 25% is defined as a low-load period, and the remaining continuous periods are defined as off-peak periods. Energy switching nodes within each period can be identified as follows: For the real-time output ratio of photovoltaic (PV) and energy storage, a corresponding monitoring sequence is constructed, and a benchmark reference value is set. For example, the reference ratio for PV power supply alone is set to 90%. By calculating the cumulative deviation between the actual sequence and the reference value, when the deviation exceeds the control limit determined based on three standard deviations, it is marked as an energy switching node. When the cumulative deviation of the PV ratio changes abruptly from positive to negative and exceeds the limit, it can be determined as a switch from PV to energy storage. When the cumulative deviation of the energy storage ratio decreases while the deviation of the PV ratio increases... When all exceed the limits, it can be determined as a switch from energy storage to hybrid power supply. In other embodiments, energy switching nodes in each time period can also be read directly from the energy management cloud platform, which will not be elaborated here. Setting time windows before and after each energy switching node and filtering the power distribution data within the corresponding time window from historical operational big data can be achieved in the following way: obtain the timestamp of the switching node, perform a conditional query in InfluxDB, set the time range to five minutes before the switching node to ten minutes after the switching node, i.e., the time window, and batch extract the photovoltaic energy distribution, energy storage energy distribution, and total energy distribution data within the time window, and then use the extracted data as the corresponding Power distribution data within a time window; determining the distribution deviation amplitude and distribution volatility rate at the corresponding energy switching node based on the power distribution data, and then determining the volatility index of the corresponding energy switching node can be achieved in the following way: a steady-state reference value, i.e., the average value, can be obtained by using the power distribution data of the 30 minutes before the switch using the moving average method; then the root mean square error is calculated based on the deviation between the reference value and the actual value, and the obtained root mean square error is used to describe the distribution deviation amplitude; the rate of change of power distribution data before and after the switching node can be used as the distribution volatility rate; further, the distribution deviation amplitude and distribution volatility rate are combined into an array as the volatility index of the corresponding energy switching node;The energy distribution fluctuation characteristics of the dispatching unit during energy switching at different time periods can be determined based on the fluctuation indicators of all energy switching nodes using the following method: The fluctuation indicators of all energy switching nodes can be arranged into a matrix, where the rows represent energy switching nodes and the columns represent fluctuation indicators, including energy distribution deviation amplitude and energy distribution fluctuation rate. The resulting matrix is ​​then used to describe the energy distribution fluctuation characteristics of the dispatching unit during energy switching at different time periods.

[0025] In some embodiments, reference Figure 2 As shown in the figure, this is a flowchart illustrating the process of determining the energy distribution fluctuation coefficient in some embodiments of this application. In this embodiment, the determination of the energy distribution fluctuation coefficient of the dispatching unit during the energy switching process based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution conditions can be achieved through the following steps: In step 1021, the operating data of the steady-state energy distribution state of the allocation unit at different time periods are obtained; In step 1022, steady-state energy distribution parameters for steady-state energy distribution states at different time periods are determined based on the operating data. The steady-state energy distribution parameters include the steady-state average energy distribution and the upper limit of steady-state energy distribution fluctuation. In step 1023, the energy distribution fluctuation characteristics during the energy switching process in each time period and the steady-state energy distribution parameters of the steady-state energy distribution state in the corresponding time period are compared and analyzed. In step 1024, the energy distribution fluctuation coefficient of the distribution unit during the energy switching process is determined by comparing and analyzing the results.

[0026] It should be noted that the steady-state energy distribution parameters in this application refer to the key indicators of the distribution unit when maintaining stable energy supply during non-switching periods, including the steady-state average energy distribution and the upper limit of steady-state energy distribution fluctuation, which are used to characterize the energy supply level and allowable fluctuation range under normal operation; the energy distribution fluctuation coefficient in this application refers to the quantitative characteristics of the actual energy distribution fluctuation relative to the steady-state energy distribution upper limit during energy switching, which is used to measure the amplitude and stability of energy supply fluctuation during switching.

[0027] In practical implementation, obtaining the steady-state energy distribution status of the dispatching unit at different time periods can be achieved in the following way: The steady-state energy distribution status of the dispatching unit at different time periods can be obtained from the database of the energy management cloud platform. Specifically, based on the previously identified energy switching nodes, the time-series data of the switching process can be marked as abnormal, and the data outside the switching process can be marked as steady-state. Then, the data of the steady-state interval can be extracted through data filtering, and grouped according to the pre-defined peak, off-peak, and low-peak periods to ensure the consistency of data with time period characteristics. Determining the steady-state energy distribution parameters for different time periods based on the operational data can be achieved in the following way: The steady-state average energy distribution is calculated using the moving average method for the steady-state data of each time period to reflect the typical energy distribution level. The upper limit of steady-state fluctuation is defined by the three-standard-deviation principle, that is, the range of normal fluctuation is determined by the sum of the steady-state average energy distribution and the standard deviation, thus obtaining the steady-state... The statistical parameters of energy distribution; the comparative analysis of the energy distribution fluctuation characteristics during energy switching in each time period and the steady-state energy distribution parameters of the corresponding time period can be achieved in the following way: the feature mapping and deviation quantification method can be used to map the energy distribution fluctuation characteristics during the switching process to the steady-state parameters of the corresponding time period, the absolute deviation can be obtained by calculating the difference, and the relative deviation can be obtained by the ratio of the difference to the upper limit of steady-state fluctuation. The difference between the switching process and the steady state can be characterized from both absolute and relative dimensions. The energy distribution fluctuation coefficient of the allocation unit during the energy switching process can be determined by the following way: the fluctuation characteristics of the switching process can be ratioed to the upper limit of steady-state fluctuation. The ratio can be used as the energy distribution fluctuation coefficient. When the fluctuation coefficient is less than or equal to 1, it indicates that the fluctuation of the switching process is within the steady-state tolerance range. When the fluctuation coefficient is greater than 1, it indicates that the fluctuation of the switching process exceeds the steady-state tolerance and needs to be focused on in subsequent optimization.

[0028] In step 103, the energy imbalance of the photovoltaic-storage capacity configuration of the allocation unit at different time periods is determined based on the historical operational big data. Then, the capacity configuration loss of the allocation unit in the process of adjusting the photovoltaic-storage capacity configuration is determined based on the energy imbalance and the time-varying response characteristics of the photovoltaic-storage capacity configuration.

[0029] In some embodiments, references Figure 3 As shown in the figure, this is a flowchart illustrating the process of determining the energy distribution imbalance in some embodiments of this application. In this embodiment, the determination of the energy distribution imbalance of the photovoltaic-storage capacity configuration of the allocation unit at different time periods based on the historical operational big data can be achieved by the following steps: In step 1031, the target energy distribution demand for different time periods is determined, and the target energy distribution demand includes the target energy distribution for photovoltaics, the target energy distribution for energy storage, and the photovoltaic-energy storage synergistic energy distribution ratio. In step 1032, the actual energy distribution demand for different time periods is extracted from the historical operational big data. The actual energy distribution demand includes the actual photovoltaic energy distribution, the actual energy storage energy distribution, and the actual photovoltaic-energy storage synergistic energy distribution ratio. In step 1033, the energy distribution demand deviation is determined based on the target energy distribution demand and the actual energy distribution demand. The energy distribution demand deviation includes photovoltaic energy distribution deviation, energy storage energy distribution deviation, and synergy ratio deviation. In step 1034, the deviations in the energy distribution demand deviation are weighted and summed based on the preset energy distribution balance weights to obtain the energy distribution imbalance of the photovoltaic storage capacity configuration of the allocation unit at different time periods.

[0030] It should be noted that the target energy distribution demand in this application is a reference indicator used to guide the dispatching unit to rationally allocate photovoltaic and energy storage resources according to the expected strategy and load demand; the actual energy distribution demand in this application is used to reflect the characteristics of the actual energy distribution situation of the dispatching unit in historical operation; and the energy distribution imbalance degree in this application is an indicator to measure the degree of deviation between the target energy supply and the actual energy supply of the dispatching unit in the process of photovoltaic and energy storage capacity configuration.

[0031] In practical implementation, the target energy allocation demand for different time periods can be determined in the following ways: The target photovoltaic energy allocation can be based on historical irradiance and temperature data, using a long short-term memory network model to predict the theoretical maximum output for each time period. The input is meteorological and photovoltaic output data for several consecutive days, and the output is the target photovoltaic output for the corresponding time period. The target energy allocation for energy storage can be set by combining load forecasting and energy storage state of charge planning. Load forecasting can use an autoregressive moving average model to model historical load data and output future demand. Then, energy storage output is allocated according to the scheduling rules of peak discharge and off-peak charging. The output is the target value that satisfies the load gap; this target value is the target energy allocation for energy storage. The photovoltaic-energy storage co-allocation ratio is determined by an expert system that integrates the prediction results with scheduling rules based on a preset energy strategy threshold to obtain the final target energy allocation demand. Extracting the actual energy allocation demand for different time periods from the historical operational big data can be achieved by: retrieving operational data from the database and obtaining the actual photovoltaic output and actual energy storage charging / discharging output for each time period through statistical analysis; and calculating the actual photovoltaic-energy storage co-allocation ratio based on the actual photovoltaic output and actual energy storage charging / discharging output. Based on the target energy allocation... The deviation between the demand and the actual energy distribution demand can be determined in the following way: a normalized error calculation method can be used to transform the difference between the actual value and the target value into a unified dimensionless index. The deviation between photovoltaic and energy storage is calculated by the ratio of the difference to the target value, and the deviation of the coordination ratio is directly represented by the difference between the target ratio and the actual ratio, so that all deviations are mapped to the same dimension range. It should be further noted that in this application, the deviation between photovoltaic and energy storage is converted into a dimensionless index through a normalization method, which can reduce the calculation deviation caused by the dimension in the subsequent calculation process; based on the preset energy distribution balance The weighted summation of each deviation in the energy distribution demand deviation yields the energy distribution imbalance of the allocation unit at different time periods. This can be achieved by using the analytic hierarchy process (AHP) combined with weighted summation to assign weights to the importance of different deviation factors. For example, energy storage deviations are given higher weights, while photovoltaic and synergistic ratio deviations are given lower weights. After the weights are confirmed to be reasonable through consistency verification, the various deviations are weighted and summed to obtain a comprehensive imbalance index. The higher the value of this index, the more severe the imbalance in the photovoltaic and energy storage capacity allocation, thus providing a quantitative basis for subsequent optimization.

[0032] In some embodiments, determining the capacity configuration loss of the allocation unit during the photovoltaic-storage capacity configuration adjustment process based on the energy allocation imbalance degree and the time-varying response characteristics of the photovoltaic-storage capacity configuration can be achieved through the following steps: Extract time-varying response characteristic parameters of photovoltaic and energy storage capacity configuration, including photovoltaic output response delay time, energy storage charge and discharge response speed and photovoltaic and energy storage capacity adjustment rate; Based on the time-varying response characteristic parameters and the energy imbalance of photovoltaic-storage capacity configuration at different time periods, the delay loss and over-limit loss during the capacity adjustment process are determined. The capacity configuration loss of the allocation unit during the photovoltaic-storage capacity configuration adjustment process is determined based on the delay loss and the over-limit loss.

[0033] It should be noted that the time-varying response characteristics in this application are used to reflect the dynamic response capability of the photovoltaic-storage system as the load changes over time during capacity adjustment; the delay loss in this application is used to measure the insufficient or biased energy distribution caused by the response lag of the photovoltaic-storage system; the over-limit loss in this application is used to measure the utility loss caused by exceeding the equipment safety or rated range during the photovoltaic-storage capacity adjustment process; and the capacity configuration loss in this application is used to measure the total energy deviation loss during the photovoltaic-storage capacity adjustment process.

[0034] In practical implementation, the time-varying response characteristic parameters of photovoltaic and energy storage capacity configuration can be extracted in the following way: By statistically analyzing historical operating data, the delay time of photovoltaic output response is obtained. Specifically, when there is a sudden change in light intensity, the time point of the sudden change in light intensity and the time point of the subsequent change in photovoltaic output are recorded, and the time difference between the two is calculated. The time difference is calculated under multiple identical scenarios, and the average value is taken as the response delay time. The charging and discharging response speed of the energy storage unit is obtained by capturing the power change curve of the energy storage unit during operation, obtaining the time required for it to increase from zero power to rated power or decrease from rated power to zero power, and dividing the rated power by the required time to obtain the response speed value. The capacity adjustment rate is calculated by dividing the difference between the target capacity and the current capacity by the time taken to adjust from the current capacity to the target capacity. The delay loss and over-limit loss during capacity adjustment are determined based on the time-varying response characteristic parameters and the energy imbalance of the photovoltaic-storage capacity configuration at different time periods. This can be achieved by multiplying the response delay time, the corresponding energy imbalance, and a preset coefficient, which can be set based on historical operating losses to reflect the impact of delay on the overall energy configuration. Over-limit loss is determined by identifying portions of the capacity exceeding the rated capacity of the equipment during the capacity adjustment process from historical operating data. The process involves obtaining the over-limit value, multiplying it by the energy distribution imbalance degree and a preset penalty coefficient. The penalty coefficient is a weighting factor reflecting the degree of additional adverse impact of over-limit operation on system stability and equipment reliability, used to amplify the contribution of over-limit behavior to the final loss value in the loss calculation formula. It should be further explained that the over-limit value refers to the numerical difference between the actual operating parameters of the allocation unit and its rated parameters during capacity adjustment. It is used to quantify the degree to which actual operation exceeds the equipment safety or design limits. The method of obtaining this value is as follows: first, extract the actual output curve of the energy storage unit or photovoltaic unit from the operating data and compare it point-by-point with the rated power or rated capacity; when… When the actual value exceeds the rated value, the difference between the actual value and the rated value is taken as the single over-limit value. The over-limit value for the entire period can be accumulated or averaged to reflect the degree of exceeding the rated range. It should be further explained that the preset penalty coefficient is a manually set weight parameter used to reflect the negative impact of over-limit operation on system safety and equipment lifespan during loss calculation. Its implementation methods mainly include: experience-based setting, that is, combining the long-term operational experience and historical fault cases accumulated by maintenance personnel, directly setting corresponding penalty coefficients for different levels of over-limit, for example, setting 0.1 for minor over-limit, 0.2 for moderate over-limit, and 0 for severe over-limit.5. Based on statistical regression, the relationship between over-limit amplitude and equipment lifespan degradation, increased failure rate, or increased maintenance costs in historical operating data is utilized. Linear or logistic regression methods are used to fit the function curve, and the coefficient size is determined based on the curve slope. Based on expert evaluation, experts in the power system and equipment manufacturing fields are organized to use the analytic hierarchy process (AHP) to score indicators such as "safety," "lifespan impact," and "maintenance cost." Reasonable penalty coefficients for different over-limit scenarios are obtained through weighted calculations. The capacity configuration loss of the allocation unit during the photovoltaic-storage capacity configuration adjustment process, based on the aforementioned delay loss and over-limit loss, can be achieved by summing the calculated delay loss and over-limit loss. The result is the total capacity configuration loss, which directly reflects the superimposed effect of different loss factors, providing a basis for subsequent energy configuration optimization.

[0035] It should be noted that this application focuses on delay loss and over-limit loss because these two types of losses directly reflect the impact of the energy allocation process on system stability and equipment safety. Delay loss reflects the mismatch between energy supply and demand caused by untimely response, which directly affects the reliable energy supply on the load side. Over-limit loss reflects the shortened equipment life and potential failure risks caused by operating beyond the rated capacity. By highlighting these two core types of losses, we can grasp the key contradictions affecting the overall efficiency and safety of the system while ensuring the simplicity of calculation, thereby providing a targeted and highly operable evaluation basis for optimizing energy allocation strategies.

[0036] In step 104, the photovoltaic and energy storage capacity configuration during the energy switching process at different time periods is optimized based on the energy distribution fluctuation coefficient and the capacity configuration loss. Then, the photovoltaic and energy storage energy switching process in the energy management cloud platform is optimized and controlled based on the optimized photovoltaic and energy storage capacity configuration.

[0037] In some embodiments, optimizing the photovoltaic-storage capacity configuration during energy switching at different time periods based on the energy distribution fluctuation coefficient and the capacity configuration loss can be achieved through the following steps: The adjustable range of photovoltaic and energy storage capacity configuration for each time period is determined, and the adjustable range is set based on the upper limit of photovoltaic installed capacity, the rated capacity of energy storage, grid access constraints and the lower limit of load demand. A cost optimization objective function is constructed based on the energy distribution fluctuation coefficient and the capacity configuration loss. Within the adjustable range, a particle swarm optimization algorithm is used to search for the optimal photovoltaic-storage capacity configuration parameters that satisfy the cost optimization objective function. The optimal photovoltaic-storage capacity configuration parameters include the real-time photovoltaic energy distribution ratio, the energy storage charging and discharging power setpoint, and the photovoltaic-storage switching trigger threshold. Verify the adaptability of the optimal photovoltaic-storage capacity configuration parameters in historical operating data of the same period, and determine the optimized photovoltaic-storage capacity configuration based on the adaptability results.

[0038] It should be noted that the cost optimization objective function in this application is used to comprehensively evaluate the fluctuations and losses of photovoltaic and energy storage capacity configuration under different scheduling schemes, thereby guiding the search for optimal configuration parameters to achieve optimal control of the energy switching process.

[0039] In practical implementation, the adjustable range of photovoltaic and energy storage capacity configuration for each time period can be determined as follows: the real-time photovoltaic energy allocation ratio range uses the ratio of the internal photovoltaic installed capacity to the system's maximum load as the upper limit and zero as the lower limit; the adjustable range of energy storage charging and discharging power uses the internal rated discharge power as the upper limit and the negative value of the rated charging power as the lower limit, where the negative value represents the charging process; the photovoltaic-energy storage switching trigger threshold range is determined with reference to historical load data, with its lower limit set at 20% of the load demand to avoid frequent switching and its upper limit set at 80% of the load demand to ensure timely energy replenishment during high-demand periods. All of the above parameter ranges are based on equipment... The instruction manual and actual load data are directly set without complex calculations. The cost optimization objective function constructed based on the energy distribution fluctuation coefficient and the capacity configuration loss can be implemented in the following way: the optimization objective is set to minimize the total cost, which is composed of the weighted sum of the energy distribution fluctuation coefficient and the capacity configuration loss. That is, the total cost equals a multiplied by the energy distribution fluctuation coefficient plus b multiplied by the capacity configuration loss, where a and b are preset weight parameters that can be set according to the operational focus. For example, when more attention is paid to system stability, the values ​​of a and b can both be set to 0.5; when more attention is paid to economy, the value of a can be set to 0.4 and the value of b can be set to 0.6. The weight parameters can also be dynamically adjusted based on on-site operational feedback to balance stability and economy. It should be further noted that the capacity configuration loss needs to be dimensionless during the construction of the cost optimization objective function. Existing technologies typically use the extreme value method, mapping the original capacity configuration loss to the [0, 1] interval. The calculation formula is: Dimensionless value = (Original capacity configuration loss - Minimum capacity configuration loss in historical data) / (Maximum capacity configuration loss in historical data - Minimum capacity configuration loss in historical data). Standardization methods, such as the Z-score method, are also used, based on the mean and standard deviation of historical data. The calculation formula is: Dimensionless value = (Original capacity configuration loss - Mean capacity configuration loss in historical data) / (Standard deviation of capacity configuration loss in historical data). Mean normalization is also used, using the mean of historical data as a benchmark. The calculation formula is: Dimensionless value = (Original capacity configuration loss - Mean capacity configuration loss in historical data) / (Maximum capacity configuration loss in historical data - Minimum capacity configuration loss in historical data). It should also be noted that dimensionless... The core function of the optimization process is to eliminate the dimensional differences between capacity configuration loss and energy distribution fluctuation coefficient, allowing them to be weighted within the cost optimization objective function. This avoids physical contradictions in the objective function due to inconsistent units, and unifies their numerical magnitudes to prevent the absolute value of capacity configuration loss from dominating the optimization process. It ensures that both the energy distribution fluctuation coefficient and capacity configuration loss reasonably reflect the impact on the cost of photovoltaic-storage capacity configuration. Searching for the optimal photovoltaic-storage capacity configuration parameters that satisfy the cost optimization objective function within the adjustable range using a particle swarm optimization algorithm can be achieved as follows: First, the particles are encoded, with each particle representing a set of candidate configuration parameters, including the photovoltaic energy distribution ratio, energy storage charging and discharging power, and photovoltaic-storage switching threshold. Then, an initialization operation is performed, randomly generating 50 particles, ensuring that their parameter values ​​are all within the aforementioned adjustable range. During the iterative update process, the particle position is calculated using a basic update formula, where the new position is obtained by superimposing the old position and velocity. The velocity is determined by the inertia weight, the old velocity, the learning factor, and the globally optimal position; in this embodiment, the inertia weight is set to 0.6. The learning factor is set to 2, and the number of iterations is set to 50. After each iteration, the particle with the minimum total cost is selected. The configuration parameters corresponding to the particle with the minimum total cost after iteration are taken as the candidate optimal solution. The adaptability of the optimal photovoltaic-storage capacity configuration parameters in historical operating data of the same period is verified. Based on the adaptability results, the optimized photovoltaic-storage capacity configuration can be implemented in the following way: By extracting sample data consistent with the current optimization period type from historical operating data, for example, when optimizing peak period parameters, extract the load and photovoltaic-storage output data of several peak periods in history, substitute the candidate optimal parameters into the above data for simulation calculation, and obtain the energy distribution fluctuation coefficient, capacity configuration loss and total cost under simulation conditions. If the deviation between the total cost obtained from the simulation calculation and the calculated value of the objective function is less than or equal to 10%, the parameter combination is confirmed to have adaptability and is taken as the final optimization result; if the deviation is greater than 10%, the search is repeated by increasing the number of particle swarm iterations until the deviation meets the requirements, thereby ensuring that the final parameters are not only optimal in the optimization model.

[0040] In some embodiments, optimizing and controlling the switching process between photovoltaic and energy storage in the energy management cloud platform based on the optimized photovoltaic-energy storage capacity configuration can be achieved through the following steps: The optimized photovoltaic and energy storage capacity configuration parameters are sent to the allocation unit of the energy management cloud platform; During the photovoltaic-storage energy switching process, the photovoltaic power supply ratio, energy storage charging and discharging power, and grid connection conditions are adjusted according to the photovoltaic-storage capacity configuration parameters. Furthermore, the photovoltaic-storage capacity configuration parameters are updated based on the operation data of the energy management cloud platform.

[0041] It should be noted that the grid access conditions in this application refer to the parameter settings used to control the proportion of grid participation in energy supply and the timing of grid access during the photovoltaic-storage energy switching process.

[0042] In specific implementation, the optimized photovoltaic-storage capacity configuration parameters can be sent to the dispatching unit of the energy management cloud platform in the following way: The energy management cloud platform will send the optimized photovoltaic ratio, energy storage charging and discharging power, and photovoltaic-storage switching threshold to the dispatching unit through the Internet of Things communication protocol. A confirmation mechanism is used during the sending process. After receiving the parameters, the dispatching unit will immediately return a confirmation signal. If the platform does not receive a confirmation signal within a set time, it will automatically resend the parameters. During the photovoltaic-storage energy switching process, the photovoltaic power supply ratio, energy storage charging and discharging power, and grid access conditions are adjusted according to the photovoltaic-storage capacity configuration parameters. The photovoltaic-storage capacity configuration parameters are further updated based on the operating data of the energy management cloud platform in the following way: During the energy switching process, the dispatching unit directly controls the operation of each energy module according to the sent parameters. The photovoltaic module adjusts its output power according to the proportion parameters issued by the controller, and the energy storage module performs operations according to the set charging and discharging power, and automatically triggers protection measures when the power exceeds the rated value. When the total output of photovoltaic and energy storage is lower than the switching threshold, the dispatching unit automatically triggers grid connection to supplement the system energy. Furthermore, the cloud platform collects the operating data of the dispatching unit in real time through sensors, including the proportion of photovoltaic power, energy storage power and load demand, and stores it in the time series database. The platform compares the actual operating data with the optimized parameters. When the deviation exceeds the preset range, the parameters are slightly corrected and reissued to the dispatching unit for execution. This process does not require rerunning the complete optimization algorithm. It only relies on deviation judgment to realize the dynamic updating of parameters, ensuring that the optimized parameters continuously adapt to the actual working conditions and maintain the stable operation of the system.

[0043] On the other hand, in some embodiments, this application provides a cloud-based energy optimization control system, with reference to... Figure 4 The figure is a schematic diagram of the structure of a cloud-based energy optimization control system according to some embodiments of this application. The cloud-based energy optimization control system 400 includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used to acquire historical operational big data of the dispatching unit in the energy management cloud platform in the dispatching of photovoltaic and energy storage energy. Processing module 402 in this application is used to extract the energy distribution fluctuation characteristics of the dispatching unit during the energy switching process at different time periods from the historical operation big data, and then determine the energy distribution fluctuation coefficient of the dispatching unit during the energy switching process based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution. In this application, the processing module 402 is also used to determine the energy imbalance degree of the photovoltaic-storage capacity configuration of the allocation unit under different time periods based on the historical operating big data, and then determine the capacity configuration loss of the allocation unit in the process of adjusting the photovoltaic-storage capacity configuration according to the energy imbalance degree and the time-varying response characteristics of the photovoltaic-storage capacity configuration. The execution module 403 in this application is mainly used to optimize the cost of photovoltaic and energy storage capacity configuration during energy switching at different time periods based on the energy distribution fluctuation coefficient and the capacity configuration loss, and then optimize and control the photovoltaic and energy storage energy switching process in the energy management cloud platform based on the optimized photovoltaic and energy storage capacity configuration.

[0044] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described cloud platform-based energy optimization control method.

[0045] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device implementing a cloud-based energy optimization control method according to some embodiments of this application. The cloud-based energy optimization control method in the above embodiments can... Figure 5 The computer device shown is used to implement this, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0046] Processor 501 can be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0047] The communication bus 502 can be used to transmit information between the aforementioned components.

[0048] Memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 503 may exist independently and be connected to processor 501 via communication bus 502. Memory 503 may also be integrated with processor 501.

[0049] The memory 503 stores program code for executing the scheme of this application, and its execution is controlled by the processor 501. The processor 501 executes the program code stored in the memory 503. The program code may include one or more software modules. In the above embodiments, the cloud platform-based energy optimization control method can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0050] Communication interface 504 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0051] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0052] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0053] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described cloud-based energy optimization control method.

[0054] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0055] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A cloud-based energy optimization control method, characterized in that, Includes the following steps: Acquire historical operational big data of the dispatching unit in the energy management cloud platform regarding the dispatching of photovoltaic and energy storage energy; Extract the energy distribution fluctuation characteristics of the dispatching unit during energy switching at different time periods from the historical operational big data, and then determine the energy distribution fluctuation coefficient of the dispatching unit during energy switching based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution. Specifically, determining the energy distribution fluctuation coefficient of the dispatching unit during energy switching based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution conditions includes: Obtain operational data of the steady-state energy distribution status of the allocation unit at different time periods; The steady-state energy distribution parameters are determined based on the operating data for different time periods. The steady-state energy distribution parameters include the steady-state average energy distribution and the upper limit of steady-state energy distribution fluctuation. The energy distribution fluctuation characteristics during the energy switching process in each time period are compared and analyzed with the steady-state energy distribution parameters of the corresponding steady-state energy distribution state. The energy distribution fluctuation coefficient of the dispatching unit during the energy switching process was determined by comparing and analyzing the results. Based on the historical operational big data, the energy distribution imbalance of the photovoltaic and energy storage capacity configuration of the allocation unit at different time periods is determined, and then the capacity configuration loss of the allocation unit in the process of adjusting the photovoltaic and energy storage capacity configuration is determined according to the energy distribution imbalance and the time-varying response characteristics of the photovoltaic and energy storage capacity configuration. Specifically, determining the energy distribution imbalance of the photovoltaic-storage capacity configuration of the allocation unit at different time periods based on the historical operational big data includes: Determine the target energy allocation demand for different time periods, including the target energy allocation for photovoltaics, the target energy allocation for energy storage, and the ratio of photovoltaic-energy storage synergistic energy allocation. The actual energy distribution demand for different time periods is extracted from the historical operational big data. The actual energy distribution demand includes the actual photovoltaic energy distribution, the actual energy storage energy distribution, and the actual photovoltaic-energy storage synergistic energy distribution ratio. The energy distribution demand deviation is determined based on the target energy distribution demand and the actual energy distribution demand. The energy distribution demand deviation includes photovoltaic energy distribution deviation, energy storage energy distribution deviation, and synergy ratio deviation. Based on the preset energy distribution balance weight, the deviations in the energy distribution demand deviation are weighted and summed to obtain the energy distribution imbalance degree of the photovoltaic storage capacity configuration of the allocation unit at different time periods. Based on the energy distribution fluctuation coefficient and the capacity configuration loss, the cost optimization of the photovoltaic and energy storage capacity configuration during the energy switching process at different time periods is carried out, and then the photovoltaic and energy storage energy switching process in the energy management cloud platform is optimized and controlled based on the optimized photovoltaic and energy storage capacity configuration.

2. The method as described in claim 1, characterized in that, The historical operational big data includes power distribution data, photovoltaic and energy storage capacity data, and load demand data.

3. The method as described in claim 1, characterized in that, Extracting the energy distribution fluctuation characteristics of the dispatching unit during energy switching at different time periods from the historical operational big data specifically includes: Determine the time period division rules for the dispatching units in the energy management cloud platform, and divide the time period into peak load period, off-peak load period, and low load period according to the time period division rules; Identify energy switching nodes in each time period, including the time points when switching from photovoltaic power supply to energy storage power supply, switching from energy storage power supply to hybrid power supply, and switching from hybrid power supply to grid supplementary power supply. Time windows are set before and after each energy switching node, and power distribution data within the corresponding time window is filtered from historical operational big data. The power distribution data includes the actual energy distribution of photovoltaic, the actual energy distribution of energy storage, and the total energy distribution. Based on power distribution data, determine the energy distribution deviation magnitude and energy distribution volatility at the corresponding energy switching node, and then determine the volatility index of the corresponding energy switching node. The energy distribution fluctuation characteristics of the dispatching unit during the energy switching process at different time periods are determined based on the fluctuation indicators of all energy switching nodes.

4. The method as described in claim 1, characterized in that, Based on the aforementioned energy distribution imbalance and the time-varying response characteristics of the photovoltaic-storage capacity configuration, the capacity configuration loss of the allocation unit during the photovoltaic-storage capacity configuration adjustment process is determined to specifically include: Extract time-varying response characteristic parameters of photovoltaic and energy storage capacity configuration, including photovoltaic output response delay time, energy storage charge and discharge response speed and photovoltaic and energy storage capacity adjustment rate; Based on the time-varying response characteristic parameters and the energy imbalance of photovoltaic-storage capacity configuration at different time periods, the delay loss and over-limit loss during the capacity adjustment process are determined. The capacity configuration loss of the allocation unit during the photovoltaic-storage capacity configuration adjustment process is determined based on the delay loss and the over-limit loss.

5. The method as described in claim 1, characterized in that, Based on the optimized photovoltaic-storage capacity configuration, the energy management cloud platform optimizes and regulates the photovoltaic-storage energy switching process, specifically including: The optimized photovoltaic and energy storage capacity configuration parameters are sent to the allocation unit of the energy management cloud platform; During the photovoltaic-storage energy switching process, the photovoltaic power supply ratio, energy storage charging and discharging power, and grid connection conditions are adjusted according to the photovoltaic-storage capacity configuration parameters. Furthermore, the photovoltaic-storage capacity configuration parameters are updated based on the operation data of the energy management cloud platform.

6. A cloud-based energy optimization control system, which employs the method described in any one of claims 1 to 5 for energy optimization control, characterized in that, The system includes: The acquisition module is used to acquire historical operational big data of the dispatching unit in the energy management cloud platform in the dispatching of photovoltaic and energy storage energy; The processing module is used to extract the energy distribution fluctuation characteristics of the dispatching unit during the energy switching process at different time periods from the historical operation big data, and then determine the energy distribution fluctuation coefficient of the dispatching unit during the energy switching process based on the energy distribution fluctuation characteristics and the steady-state energy distribution parameters of the energy management cloud platform under steady-state energy distribution. The processing module is also used to determine the energy imbalance of the photovoltaic-storage capacity configuration of the allocation unit at different time periods based on the historical operational big data, and then determine the capacity configuration loss of the allocation unit in the process of adjusting the photovoltaic-storage capacity configuration based on the energy imbalance and the time-varying response characteristics of the photovoltaic-storage capacity configuration. The execution module is used to optimize the cost of photovoltaic and energy storage capacity configuration during energy switching at different time periods based on the energy distribution fluctuation coefficient and the capacity configuration loss, and then optimize and control the photovoltaic and energy storage energy switching process in the energy management cloud platform based on the optimized photovoltaic and energy storage capacity configuration.

7. A computer device comprising a memory and a processor, the memory storing code, characterized in that, The processor is configured to acquire the code and execute the cloud-based energy optimization control method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the cloud-based energy optimization control method as described in any one of claims 1 to 5.

Images