An energy management method, device and equipment based on micro-grid division, a storage medium and a program product

Abstract

The application discloses an energy management method and device based on micro-grid division, equipment, a storage medium and a program product, relates to the technical field of data processing, and avoids single point failure and expansion difficulty of centralized architecture by dividing a micro-grid into multiple node regions and acquiring output prediction data (average, upper limit, lower limit) and load prediction data (average, upper limit, lower limit) of each region in a future period. The average net load is calculated according to the average output and the average load, the uncertainty index is calculated according to the predicted upper and lower limit values of the load and the output, and the cost function of the exchange power of the node region is constructed based on the average net load and the uncertainty index, so that the uncertainty is embedded, the decision-making has risk perception ability, and the energy management is realized.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to an energy management method, device, equipment, storage medium and program product based on microgrid partitioning. Background Technology

[0002] Microgrid-based energy management systems are the core platform for achieving coordinated optimization of distributed power sources, energy storage, and flexible loads. Existing systems generally adopt a centralized deterministic optimization architecture: the central controller collects network-wide operational data along with meteorological and electricity price information, solves the global optimization model based on single numerical predictions (such as expected values) of renewable energy output and load, generates scheduling plans, and uniformly distributes them for execution.

[0003] The forecasting module of this technical approach typically outputs expected values ​​for renewable energy output and load in future periods. The optimization module treats these expected values ​​as rigid constraints or fixed input parameters, without considering the uncertainty of the forecast values ​​themselves. When the forecast deviation is large, the scheduling plan becomes mismatched, and the system can only make up for it retrospectively through rolling corrections in the next cycle, leading to increased operating costs and reduced energy consumption rate. Summary of the Invention

[0004] The main objective of this application is to provide an energy management method, device, equipment, storage medium, and program product based on microgrid partitioning, which aims to solve the technical problem that existing energy management schemes are prone to scheduling mismatch when the prediction deviation is large, resulting in increased operating costs.

[0005] To achieve the above objectives, this application proposes an energy management method based on microgrid partitioning, wherein the energy management method based on microgrid partitioning includes: The microgrid is divided into several node regions, and the power output forecast data and load forecast data of the node regions in future time periods are obtained; wherein, the power output forecast data includes at least the average power output forecast, the upper limit of the power output forecast, and the lower limit of the power output forecast, and the load forecast data includes at least the average load forecast, the upper limit of the load forecast, and the lower limit of the load forecast. The average net load of the node region in the future period is determined based on the average output forecast and the average load forecast, and the uncertainty index of the node region in the future period is determined based on the upper limit of output forecast, the lower limit of output forecast, the upper limit of load forecast, and the lower limit of load forecast. Based on the net load average and the uncertainty index, a cost function for the power exchange between the node region and its neighboring node regions is constructed, and the cost function is optimized to obtain the target value of the power exchange of the node region. The energy management scheme for each node region in the microgrid is determined based on the target exchange power value.

[0006] In one embodiment, the step of constructing a cost function for power exchange between the node region and its neighboring node regions based on the net load mean and the uncertainty index includes: The coefficients of the linear term of the cost function are determined based on the net load average; and, The coefficients of the quadratic term of the cost function are determined based on the uncertainty index. The cost function for exchanging power between the node region and its neighboring node regions is constructed based on the coefficients of the first term and the coefficients of the second term.

[0007] In one embodiment, the step of optimizing according to the cost function to obtain the target value of the switching power of the node region includes: The historical neighbor consistency variables and historical marginal costs of the neighbor node region are obtained, and the exchange power is updated based on the historical neighbor consistency variables, the historical marginal costs, the first-order coefficients, and the second-order coefficients to obtain the current exchange power for the current iteration; wherein, the current exchange power is used to exchange with each of the neighbor nodes; The average current neighbor exchange power is determined based on the current neighbor exchange power of each neighbor node, and the consistency variable is updated based on the current exchange power and the average current neighbor exchange power to obtain the current consistency variable for the current round of iteration. If the current switching power and the current consistency variable of each node region satisfy the preset convergence condition, then the current switching power is taken as the target value of the switching power of the node region.

[0008] In one embodiment, after the step of updating the consistency variable based on the current switching power and the average current neighbor switching power to obtain the current consistency variable for the current round of iteration, the method further includes: If the current exchange power and the current consistency variable of a node region do not meet the preset convergence condition, then the current marginal cost of the current iteration is determined based on the current consistency variable, the current exchange power, and the historical marginal cost. Return to the step of obtaining the historical neighbor consistency variables and historical marginal costs of the neighbor node region to proceed to the next iteration.

[0009] In one embodiment, the step of determining the energy management scheme for each node region in the microgrid based on the target switching power value includes: Obtain the load priority information of each load in the node region; Power is allocated to the node region based on the load priority information and the target switching power value, and load control instructions are generated based on the power allocation results. An energy management scheme for the node region is generated based on the load control command.

[0010] In one embodiment, the step of obtaining the power output forecast data and load forecast data of the node region in future time periods includes: Acquire historical data, real-time operational data, and external meteorological data for the node region; Based on the historical data, the real-time operational data, and the external meteorological data, multi-timescale rolling forecasts are performed to obtain the power output forecast data and load forecast data for the node area in future periods.

[0011] Furthermore, to achieve the above objectives, this application also proposes an energy management device based on microgrid partitioning, the energy management device based on microgrid partitioning comprising: The data prediction module is used to divide the microgrid into several node regions and obtain the output prediction data and load prediction data of the node regions in future time periods; wherein, the output prediction data includes at least the average output prediction value, the upper limit of the output prediction value, and the lower limit of the output prediction value, and the load prediction data includes at least the average load prediction value, the upper limit of the load prediction value, and the lower limit of the load prediction value. The indicator determination module is used to determine the average net load of the node area in the future period based on the average output forecast and the average load forecast, and to determine the uncertainty index of the node area in the future period based on the upper limit of output forecast, the lower limit of output forecast, the upper limit of load forecast, and the lower limit of load forecast. The power management module is used to construct a cost function for exchanging power between the node region and its neighboring node regions based on the net load average and the uncertainty index, and to optimize the cost function to obtain the target value of the exchange power of the node region. The load scheduling module is used to determine the energy management scheme for each node area in the microgrid based on the target switching power value.

[0012] In addition, to achieve the above objectives, this application also proposes an energy management device based on microgrid partitioning, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the energy management method based on microgrid partitioning as described above.

[0013] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the energy management method based on microgrid partitioning as described above.

[0014] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the energy management method based on microgrid partitioning as described above.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: This application divides a microgrid into several node regions and obtains power output and load forecast data for these regions in future time periods. Based on the average power output and load forecasts, it determines the average net load for each node region in future time periods. It also determines the uncertainty index for each node region in future time periods based on the upper and lower limits of the power output and load forecasts. A cost function for power exchange between a node region and its neighboring node regions is constructed based on the average net load and uncertainty index, and optimized to obtain the target power exchange value for each node region. Finally, an energy management scheme for each node region is determined based on the target power exchange value. By dividing the microgrid into multiple node regions and obtaining power output (average, upper, and lower limits) and load forecast data (average, upper, and lower limits) for each region in future time periods, the single point of failure and expansion difficulties of centralized architectures are avoided. The uncertainty index is calculated based on the upper and lower limits of the source and load forecasts, and a cost function for power exchange between node regions is constructed based on the average net load and uncertainty index. This embeds uncertainty, enabling risk perception in decision-making and achieving proactive risk mitigation in energy management. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating an embodiment of the energy management method based on microgrid partitioning in this application. Figure 2This is a flowchart illustrating Embodiment 2 of the energy management method based on microgrid partitioning in this application; Figure 3 This is a flowchart illustrating Embodiment 3 of the energy management method based on microgrid partitioning in this application; Figure 4 This is a schematic diagram of the module structure of an energy management device based on microgrid partitioning, as described in an embodiment of this application. Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the energy management method based on microgrid partitioning in the embodiments of this application.

[0019] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0021] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0022] The main solution of this application embodiment is as follows: The microgrid is divided into several node regions, and the power output forecast data and load forecast data of the node regions for future periods are obtained. The power output forecast data includes at least the average power output forecast, the upper limit of the power output forecast, and the lower limit of the power output forecast; the load forecast data includes at least the average load forecast, the upper limit of the load forecast, and the lower limit of the load forecast. The net load average of the node region for future periods is determined based on the average power output forecast and the average load forecast; the uncertainty index of the node region for future periods is determined based on the upper limit of the power output forecast, the lower limit of the power output forecast, the upper limit of the load forecast, and the lower limit of the load forecast. A cost function for power exchange between the node region and its neighboring node regions is constructed based on the net load average and the uncertainty index, and optimized according to the cost function to obtain the target value of the exchange power for the node region. The energy management scheme for the node region is determined based on the target value of the exchange power.

[0023] This application provides a solution that avoids the single point of failure and expansion difficulties of centralized architecture by dividing the microgrid into multiple node regions and obtaining the power output forecast data (mean, upper limit, lower limit) and load forecast data (mean, upper limit, lower limit) for each region in future time periods. The solution calculates the net load average based on the power output average and load average; calculates the uncertainty index based on the forecast upper and lower limits of both the source and load sides; and constructs the cost function of the power exchange of the node region based on the net load average and uncertainty index. This embeds uncertainty, enabling decision-making to have risk perception capabilities and achieving ex-ante risk avoidance in energy management.

[0024] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer or personal computer, or an electronic device or virtual device capable of performing the above functions. The following description uses an energy management device based on microgrid partitioning (hereinafter referred to as the management device) as an example to illustrate this embodiment and the subsequent embodiments.

[0025] Based on this, embodiments of this application provide an energy management method based on microgrid partitioning, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the energy management method based on microgrid partitioning in this application.

[0026] In this embodiment, the energy management method based on microgrid partitioning includes steps S10 to S40: Step S10: Divide the microgrid into several node regions and obtain the power output forecast data and load forecast data of the node regions in future time periods. The power output forecast data includes at least the average power output forecast, the upper limit of the power output forecast, and the lower limit of the power output forecast, and the load forecast data includes at least the average load forecast, the upper limit of the load forecast, and the lower limit of the load forecast.

[0027] It should be noted that in a microgrid, the number of devices may be in the hundreds or thousands (photovoltaic inverters, energy storage converters, smart sockets, air conditioners, charging piles, etc.). In this embodiment, electrical connection points can be selected as the basis for dividing node areas, thus dividing the microgrid into several node areas. For example, each feeder can be used as a boundary, with all devices downstream of the feeder forming a node area; another example is using the distribution transformer as a boundary, with its power supply range forming a node area; yet another example is using the busbar sectionalizing switch as a boundary, with each busbar section and its load forming a node area; or, using the main incoming switch of a building or workshop as a boundary, with the internal equipment forming a node area. This embodiment does not limit the specific method of dividing node areas and can be selected according to the needs of actual applications.

[0028] It should also be noted that at least one regional agent can be set up in each node area for regional management. Within the node area, communication with the regional agent can be achieved through a low-cost industrial bus, which reduces the number of smart nodes from the device level to the region level. New devices only need to connect to the regional agent in their respective node areas, avoiding communication explosion caused by each device having to exchange information with its neighbors, and reducing the overall computing burden of the system.

[0029] It should be understood that the aforementioned power output forecast data refers to the predicted power generation of power generation devices (such as photovoltaic power generation, wind power generation, etc.) within the node region in future time periods. Specifically, it can include the average power output forecast, the upper limit of the power output forecast, and the lower limit of the power output forecast. Among them, the average power output forecast is used to represent the expected average power output value in future time periods, such as "the average photovoltaic power output in the next 15 minutes is 100kW"; the upper limit of the power output forecast is used to represent the upper limit that the average power output in future time periods may reach under a given confidence level (such as 90%), such as "there is a 90% probability that the power output will not exceed 140kW"; the lower limit of the power output forecast can represent the lower limit that the average power output in future time periods may reach under a given confidence level (such as 90%), such as "there is a 90% probability that the power output will not be less than 60kW".

[0030] It is understood that the aforementioned load forecast data refers to the predicted total power consumption of all loads within the node area over future periods. Similarly, load forecast data can include the load forecast average, load forecast upper limit, and load forecast lower limit. The load forecast average represents the expected power consumption over future periods, such as "average load of 350kW over the next 15 minutes." The load forecast upper limit represents the upper limit of the average load that may be reached over future periods at a given confidence level, such as "there is a 90% probability that the load will not exceed 400kW." The load forecast lower limit represents the lower limit of the average load that may be reached over future periods at a given confidence level, such as "there is a 90% probability that the load will not be less than 300kW."

[0031] It should be noted that by determining the upper and lower limits of output forecast and load forecast, the uncertainty of forecasting is quantified. The wider the range between the upper and lower limits, the greater the deviation of the actual value from the expected value, and the greater the risk. This range width can be used to adjust the aggressiveness of optimization decisions.

[0032] It should be understood that the length of the aforementioned future period can be determined based on the predicted needs, such as 15 minutes, 1 to 4 hours, 24 hours, etc., and the embodiments of this application do not impose any restrictions on this.

[0033] In some embodiments of this application, the future time period may include multiple levels, such as ultra-short-term forecasting, short-term forecasting, and medium-term forecasting.

[0034] For example, the future time period of ultra-short-term forecasts can be 15 minutes in the future, with a resolution of 1 minute, for real-time scheduling and energy storage charging and discharging control; the future time period of short-term forecasts can be 1 hour in the future, with a resolution of 15 minutes, for coordinating energy storage and interruptible load plans; and the future time period of medium-term forecasts can be 24 hours in the future, with a resolution of 1 hour, for day-ahead planning and trading arrangements with the grid.

[0035] In some embodiments of this application, ultra-short-term forecasting can be used to achieve real-time energy management. For example, data for the next 15 time steps can be predicted at 1-minute intervals (resolution), where each time step can correspond to an independent average output value, upper and lower limits, and average load value, upper and lower limits.

[0036] In its specific implementation, this application's embodiment divides the microgrid into several node regions and uses regional agents set within these node regions to realize the output and load forecast data for each node region in future time periods, thereby quantifying uncertainty. When uncertainty is high, a smoothing strategy can be automatically adopted, achieving proactive risk avoidance; when uncertainty is low, flexible adjustments can be made, fundamentally avoiding the emergency remediation and increased operating costs caused by forecast deviations in traditional methods.

[0037] Step S20: Determine the average net load of the node region in the future period based on the average output forecast and the average load forecast, and determine the uncertainty index of the node region in the future period based on the upper limit of output forecast, the lower limit of output forecast, the upper limit of load forecast, and the lower limit of load forecast.

[0038] It is understandable that the net load average is the net power value of the nodal region in the future period, which can be specifically represented as follows: ; in, This represents the average net load. This represents the average load forecast. This represents the predicted average output.

[0039] Understandably, by determining the net load average, the power exchanged between each node region in energy management and the external power grid can be determined. If the output is greater than the load, i.e., the net load average is negative, the node region can transmit power to the outside; if the output is less than the load, i.e., the net load average is positive, the node region can receive power from the outside.

[0040] It should be noted that the aforementioned uncertainty index can be a parameter that reflects the overall fluctuation range of net load forecasting, and can be determined by the interval width on both the output and load sides. In this application embodiment, the uncertainty index can be determined by linear superposition, weighted superposition, or other methods, and this application embodiment does not limit this. In this application embodiment, linear superposition is taken as an example, which can be specifically as follows: ; in, Indicators representing uncertainty This indicates the upper limit of the predicted output. This indicates the lower limit of the power output prediction. This indicates the width of the power generation forecast range, representing the potential deviation of photovoltaic power from expectations. This represents the upper limit of load forecasting. This represents the lower limit of load forecasting. This indicates the width of the load forecast interval, representing the potential deviation of the load from the expected range.

[0041] In its implementation, the regional agent determines the average net load of the node region in the future time period, thereby determining the power exchange value between the node region and the outside world in the future time period. By combining the uncertainties on the load side and the generation side, an uncertainty index is obtained, which can reflect the overall risk faced by the node region, enabling the optimizer to automatically adopt a more conservative strategy when the risk is high.

[0042] Step S30: Construct a cost function for the power exchange between the node region and its neighboring node regions based on the net load average and the uncertainty index, and optimize the cost function to obtain the target value of the power exchange of the node region. Step S40: Determine the energy management scheme for each node area in the microgrid based on the target exchange power value.

[0043] Understandably, in a microgrid topology, two node regions connected by direct electrical links can be considered neighboring node regions. Communication links can be established between adjacent neighboring node regions to exchange information such as marginal costs and consistency variables in distributed collaborative optimization. Through information exchange between node regions and their neighboring node regions, and after multiple iterations, the microgrid's decision-making can converge to the global optimum, achieving cost function-based optimization.

[0044] It should be noted that the cost function mentioned above can be a function used to quantify the operating cost of a node region. An exemplary function expression is shown below: ; in, This represents the decision variable, namely the exchange power between the node region and its neighboring node regions; This is the coefficient of the quadratic term, which is positively correlated with the uncertainty index and is used to reflect risk sensitivity; This is the coefficient for the first term, which is related to the net load average and is used to reflect the fundamental value of the exchange power.

[0045] It is understood that the target exchange power value is the optimized power value planned for exchange with neighboring node regions. The optimization of the cost function in this application embodiment can be achieved through distributed collaborative optimization, consensus algorithms, distributed gradient descent, etc., and this application embodiment does not impose any limitations on this approach.

[0046] It should be understood that an energy management scheme is a set of operating instructions for controllable resources such as power sources, energy storage systems, and interruptible and uninterruptible loads within each node area. This is used to control the power or operating status of each load in future time periods to ensure that the overall exchange power target value of each node area is met, thus achieving economical and reliable operation of internal resources. In this application's embodiments, the specific method of determining the energy management scheme is not limited; it can be determined based on greedy allocation, convex optimization models, etc.

[0047] This application embodiment divides the microgrid into several node regions and obtains the power output forecast data and load forecast data of the node regions for future periods. Based on the average power output forecast and the average load forecast, the net load average of the node regions for future periods is determined. Furthermore, based on the upper limit of power output forecast, the lower limit of power output forecast, the upper limit of load forecast, and the lower limit of load forecast, the uncertainty index of the node regions for future periods is determined. Based on the net load average and the uncertainty index, a cost function for power exchange between the node regions and their neighboring node regions is constructed, and this cost function is optimized to obtain the target power exchange value for the node regions. Finally, an energy management scheme for the node regions is determined based on the target power exchange value. By dividing the microgrid into multiple node regions and acquiring power output forecast data (mean, upper limit, lower limit) and load forecast data (mean, upper limit, lower limit) for each region in future time periods, the single point of failure and expansion difficulties of centralized architecture are avoided. The net load average is calculated based on the power output average and load average; uncertainty indicators are calculated based on the upper and lower limits of the forecasts on both the source and load sides; and a cost function for the power exchange of node regions is constructed based on the net load average and uncertainty indicators. This embeds uncertainty, enabling decision-making to have risk perception capabilities and achieving ex-ante risk avoidance in energy management.

[0048] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 In this embodiment of the application, the step of constructing a cost function for the power exchange between the node region and its neighboring node regions based on the net load average and the uncertainty index includes: Step S31: Determine the coefficients of the linear term of the cost function based on the net load average; and, Step S32: Determine the coefficient of the quadratic term of the cost function based on the uncertainty index; Step S33: Construct a cost function for the power exchange between the node region and its neighboring node regions based on the first-order coefficients and the second-order coefficients.

[0049] It should be noted that the aforementioned linear term coefficients can be used to determine the optimizer's basic preference for the direction of switching power, and the magnitude of the linear term coefficients determines the strength of this preference. In this embodiment, the relationship for determining the linear term coefficients can be as follows: ; in, The electricity price coefficient is used to represent the electricity price level. Its value can be determined according to actual application, and the embodiments of this application do not limit it.

[0050] Understandably, when the net load average is positive, nodal regions are willing to pay the cost to obtain external power; the larger the absolute value of the net load, the larger the linear coefficient, meaning more power needs to be received. When the net load average is negative, nodal regions can gain benefits by sending power to external sources; the larger the absolute value of the net load, the larger the negative value of the linear coefficient, meaning more power can be fed back.

[0051] It should be noted that the aforementioned quadratic term coefficients can be used to determine the steepness of the cost function. In this embodiment, the relationship for determining the quadratic term coefficients can be as follows: ; in, Used to represent the risk sensitivity coefficient The base curvature can be set according to the actual application.

[0052] Understandably, when the prediction range for the future period of a node region is wide, the corresponding uncertainty index is large. At this time, the coefficient of the quadratic term increases significantly. The optimizer will automatically avoid assigning power commands with drastic fluctuations to the node region, thereby reducing the deviation of the actual operation of each load in the node region and reducing the frequency of emergency adjustments afterward.

[0053] In some embodiments of this application, to determine the target value of the exchange power, the step of optimizing according to the cost function to obtain the target value of the exchange power of the node region includes: obtaining the historical neighbor consistency variable mean and historical marginal cost of the neighbor node region, and updating the exchange power according to the historical neighbor consistency variable, the historical marginal cost, the linear term coefficient and the quadratic term coefficient to obtain the current exchange power of the current iteration; wherein, the current exchange power is used to exchange with each of the neighbor nodes; determining the current neighbor exchange power mean according to the current neighbor exchange power of each of the neighbor nodes, and updating the consistency variable according to the current exchange power and the current neighbor exchange power mean to obtain the current consistency variable of the current iteration; if the current exchange power and the current consistency variable of each node region satisfy a preset convergence condition, then the current exchange power is used as the target value of the exchange power of the node region.

[0054] It should be noted that during the iteration process, each node's node region maintains a value used for exchange among neighbors to coordinate the power exchange decisions of each node region; this value is the consistency variable. Through mutual exchange and updates among neighbors, the power exchange of each node region can gradually converge to the microgrid power balance, thereby achieving distributed collaborative optimization.

[0055] Understandably, neighbor consistency variables are the consistency variables corresponding to the neighboring node regions of a node region. Historical neighbor consistency variables are the neighbor consistency variables that this node region received from all its neighboring node regions before the start of the current iteration round, representing the consistency variables of each neighboring node during the previous iteration. At the end of each iteration round, each node region can send its updated consistency variables for that round to all its neighboring node regions.

[0056] It should be noted that marginal cost refers to the signal exchanged between a node region and its corresponding neighboring node regions, used to coordinate the microgrid to achieve optimal performance. The aforementioned historical marginal cost refers to the historical marginal cost received by the current node region from all its neighboring node regions during the previous iteration, prior to the start of the current iteration. At the end of each iteration, each node region can send its updated marginal cost for the current iteration to all its neighboring node regions.

[0057] In this embodiment of the application, in the first... In the next iteration, the regional agent can construct the mean of the neighbor combination as shown below based on the received historical neighbor consistency variables and historical marginal costs: ; in, For the number of neighbors, This represents the set of neighboring node regions of a node region. This is the penalty coefficient, which can be set according to the actual application. Represents the neighbor node region Historical neighbor consistency variable, Represents the neighbor node region The historical marginal cost.

[0058] It should be noted that when determining the mean of the neighbor combination of a node region, the exchange power can be updated based on the coefficients of the first and second terms to obtain the current iteration round. Exchange power: ; in, The coefficient of the quadratic term, The coefficient of the linear term.

[0059] It is understandable that the aforementioned current exchange power is the exchange power of the current iteration round. When each node region determines the exchange power of the current iteration round, it can send its own exchange power to all neighboring node regions and receive the current neighbor exchange power sent by the neighboring node regions.

[0060] It should be noted that, based on the received current exchange power of each neighboring node, the average exchange power of the current neighbors can be determined. Then, the consistency variables of the node region are updated according to the current exchange power of the node region and the average exchange power of the current neighbors, resulting in the current consistency variables for the current iteration round. The specific steps for updating the consistency variables are as follows: ; in, Indicates the current consistency variable. This represents the average switching power of the current neighbors. Represents historical marginal cost. This represents the penalty coefficient.

[0061] In some embodiments of this application, the preset convergence condition may be that the number of iterations reaches a preset number, or it may be that the change value between the current consistency variable and the historical neighbor consistency variable of the previous iteration and / or that the change value between the current exchange power of the current iteration round and the historical exchange power of the previous iteration meets certain conditions. This application does not limit this.

[0062] In some embodiments of this application, a first change value of the consistency variable of a node region can be determined based on the current consistency variable of the current iteration round and the historical neighbor consistency variable of the previous iteration. A second change value of the exchange power of a node region can be determined based on the current exchange power of the current iteration round and the historical exchange power of the previous iteration. When the first change value of all node regions is less than a first preset threshold and the second change value is less than a second preset threshold, a preset convergence condition can be considered satisfied. When the preset convergence condition is satisfied, the current exchange power of each node region can be used as the corresponding target exchange power value.

[0063] It is understood that the first preset threshold and the second preset threshold mentioned above can be set according to the needs of actual applications, and the embodiments of this application do not impose any restrictions on them.

[0064] In some embodiments of this application, after the step of updating the consistency variable based on the current exchange power and the average current neighbor exchange power to obtain the current consistency variable for the current iteration, the method further includes: if the current exchange power and the current consistency variable of a node region do not meet a preset convergence condition, then the current marginal cost of the current iteration is determined based on the current consistency variable, the current exchange power, and the historical marginal cost; and the method returns to the step of obtaining the historical neighbor consistency variable and the historical marginal cost of the neighbor node region to enter the next iteration.

[0065] Understandably, if the preset convergence conditions are not met, the next iteration can proceed. Specifically, a node region can send its current consistency variables, current exchange power, and current marginal cost to its neighboring node regions, and receive the current neighbor consistency variables, current neighbor exchange power, and current neighbor marginal cost from its neighboring node regions to enable the next iteration.

[0066] In some embodiments of this application, the marginal cost update method can be as follows: ; in, This represents the historical marginal cost of the previous iteration. This represents the current marginal cost. The penalty coefficient is... This represents the current switching power. This is the current consistency variable.

[0067] This application's embodiments determine the coefficients of the first term of the cost function based on the net load average; and determine the coefficients of the second term of the cost function based on the uncertainty index; and construct a cost function for the power exchange between neighboring node regions based on the first and second term coefficients. Because the verified average is mapped to the first term coefficients and the uncertainty index is mapped to the second term coefficients, the cost function simultaneously possesses value perception and risk perception capabilities. This allows for a balance between expectations and risks during subsequent optimization, avoiding scheduling mismatches and increased costs caused by ignoring prediction uncertainties.

[0068] Based on the first and / or second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to the first and / or second embodiments described above can be referred to the above description and will not be repeated hereafter. Based on this, please refer to... Figure 3 In this embodiment of the application, the step of determining the energy management scheme for each node region in the microgrid based on the target switching power value includes: Step S41: Obtain the load priority information of each load in the node region; Step S42: Perform power allocation on the node area according to the load priority information and the target switching power value, and generate load control instructions based on the power allocation results; Step S43: Generate an energy management scheme for the node region according to the load control command.

[0069] It should be noted that the aforementioned load priority data is a type of data that can be used to describe the importance and interruptibility of each electrical load. In this embodiment of the application, loads can be divided into several priorities according to their importance, such as three levels, five levels, ten levels, etc., and this embodiment of the application does not impose any limitations on this.

[0070] In this embodiment of the application, the solution is illustrated by dividing the load into three priorities. The first-level load priority is uninterruptible, such as data centers; the second-level load priority is interruptible for short periods, such as important workshops and office lighting; and the third-level load priority is flexibly interruptible, such as air conditioners and charging stations.

[0071] It should be noted that in this embodiment, power allocation can be achieved using a priority-based greedy allocation method. Specifically, the load power requirements of all uninterruptible loads can be satisfied first, and the total uninterruptible load power of these loads can be set as... Based on the total power of this uninterruptible load. Current charging and discharging power of energy storage (Discharging is positive, charging is negative), actual photovoltaic power output and each set of interruptible loads Current power Determine the current net power of the node region. : ; Understandably, in When the value is positive, the node region is transmitting power outwards; in When the value is negative, the node region is receiving power from the outside. Based on the current net power and the target switching power value, the power difference that needs to be adjusted can be determined. This power difference is the difference between the target switching power value and the current net power. When the power difference is greater than zero, the net power needs to be increased. Conversely, the net power needs to be decreased.

[0072] It should be understood that the above-mentioned current energy storage charging and discharging power and actual photovoltaic output power are the charging and discharging power and photovoltaic output power of the system during actual operation.

[0073] It should be noted that when the power difference is greater than zero, interruptible loads can be sorted by priority from low to high, and load reduction can be performed according to this sorting. For example, loads with lower priority can be shut down, or the reduction amount for each load can be determined based on its power level, and the load power level can be adjusted based on the reduction amount (e.g., adjusting the air conditioner from 21°C to 26°C). Similarly, when the power difference is less than zero, interruptible loads can be sorted by priority from high to low, and load increase can be performed according to this sorting.

[0074] It is understandable that by allocating power in the above manner, the load control instructions for each load can be determined, and an energy management scheme for the entire node area can be generated based on these load control instructions.

[0075] In some embodiments of this application, in order to achieve the prediction of power output data and load data, the step of obtaining the predicted power output data and load data of the node area in the future period includes: obtaining historical data, real-time operating data and external meteorological data of the node area; performing multi-timescale rolling prediction based on the historical data, the real-time operating data and the external meteorological data to obtain the predicted power output data and load data of the node area in the future period.

[0076] It should be noted that the historical data for the aforementioned node region can be data stored in the local database of the node region over a period of time, and may include power output sequences and load sequences. The aforementioned real-time operational data refers to the photovoltaic power output and load power collected during forecasting. The aforementioned external meteorological data may include weather forecast data, calendar data, electricity price data, etc., and this application embodiment does not impose any limitations on this.

[0077] In some embodiments of this application, the application can perform multi-timescale rolling forecasts at a fixed period (e.g., every minute), and each forecast can generate forecast results for multiple future time periods (e.g., the next 15 minutes, 1 hour, 4 hours). Specifically, embodiments of this application can construct initial load forecasting models and initial photovoltaic output forecasting models at different time scales, respectively. By inputting the above data into different models for training, a model for realizing multi-timescale rolling forecasts can be obtained.

[0078] It should be noted that the model in the embodiments of this application can be built based on long short-term memory networks, gated recurrent units, or other machine learning models, time series models, etc., and the embodiments of this application do not limit this.

[0079] This application embodiment obtains the load priority information of each load in the node region; allocates power to the node region according to the load priority information and the target switching power value, and generates load control instructions based on the power allocation results; and generates an energy management scheme for the node region based on the load control instructions. Because it uses load priority information as the basis for power value allocation and combines it with the target switching power value to generate executable load control instructions, it avoids the problem of daily scheduling being disconnected from load value in traditional energy management.

[0080] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the energy management method based on microgrid partitioning in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0081] This application also provides an energy management device based on microgrid partitioning, please refer to... Figure 4 The energy management device based on microgrid partitioning includes: The data prediction module 10 is used to divide the microgrid into several node regions and obtain the output prediction data and load prediction data of the node regions in future time periods; wherein, the output prediction data includes at least the average output prediction value, the upper limit of the output prediction value, and the lower limit of the output prediction value, and the load prediction data includes at least the average load prediction value, the upper limit of the load prediction value, and the lower limit of the load prediction value. The indicator determination module 20 is used to determine the average net load of the node area in the future period based on the average output forecast and the average load forecast, and to determine the uncertainty index of the node area in the future period based on the upper limit of output forecast, the lower limit of output forecast, the upper limit of load forecast, and the lower limit of load forecast. The power management module 30 is used to construct a cost function for exchanging power between the node region and its neighboring node regions based on the net load average and the uncertainty index, and to optimize the cost function to obtain a target value for the exchange power of the node region. The load scheduling module 40 is used to determine the energy management scheme for each node area in the microgrid based on the target value of the switching power.

[0082] The microgrid-based energy management device provided in this application, employing the microgrid-based energy management method described in the above embodiments, can solve the technical problem that existing energy management schemes are prone to scheduling mismatch when prediction deviations are large, leading to increased operating costs. Compared with the prior art, the beneficial effects of the microgrid-based energy management device provided in this application are the same as those of the microgrid-based energy management method provided in the above embodiments, and other technical features in the microgrid-based energy management device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0083] This application provides an energy management device based on microgrid partitioning. The energy management device based on microgrid partitioning includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the energy management method based on microgrid partitioning in Embodiment 1 above.

[0084] The following is for reference. Figure 5 This document illustrates a structural schematic diagram of a microgrid-based energy management device suitable for implementing embodiments of this application. The microgrid-based energy management device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The energy management device based on microgrid partitioning shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0085] like Figure 5As shown, the microgrid-based energy management device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the microgrid-based energy management device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the microgrid-based energy management device to exchange data with other devices wirelessly or via wired communication. Although the figure shows a microgrid-based energy management device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0086] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0087] The microgrid-based energy management device provided in this application, employing the microgrid-based energy management method described in the above embodiments, can solve the technical problem that existing energy management schemes are prone to scheduling mismatch when prediction deviations are large, leading to increased operating costs. Compared with the prior art, the beneficial effects of the microgrid-based energy management device provided in this application are the same as those of the microgrid-based energy management method provided in the above embodiments, and other technical features of this microgrid-based energy management device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0088] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0089] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0090] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the energy management method based on microgrid partitioning in the above embodiments.

[0091] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0092] The aforementioned computer-readable storage medium may be included in a microgrid-based energy management device; or it may exist independently and not be incorporated into a microgrid-based energy management device.

[0093] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a microgrid-based energy management device, cause the microgrid-based energy management device to: The microgrid is divided into several node regions, and the power output forecast data and load forecast data of the node regions in future time periods are obtained; wherein, the power output forecast data includes at least the average power output forecast, the upper limit of the power output forecast, and the lower limit of the power output forecast, and the load forecast data includes at least the average load forecast, the upper limit of the load forecast, and the lower limit of the load forecast. The average net load of the node region in the future period is determined based on the average output forecast and the average load forecast, and the uncertainty index of the node region in the future period is determined based on the upper limit of output forecast, the lower limit of output forecast, the upper limit of load forecast, and the lower limit of load forecast. Based on the net load average and the uncertainty index, a cost function for the power exchange between the node region and its neighboring node regions is constructed, and the cost function is optimized to obtain the target value of the power exchange of the node region. The energy management scheme for each node region in the microgrid is determined based on the target exchange power value.

[0094] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0095] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0096] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0097] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described energy management method based on microgrid partitioning. This addresses the technical problem that existing energy management schemes often suffer from scheduling mismatches when prediction deviations are large, leading to increased operating costs. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the energy management method based on microgrid partitioning provided in the above embodiments, and will not be elaborated upon here.

[0098] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the energy management method based on microgrid partitioning as described above.

[0099] The computer program product provided in this application can solve the technical problem that existing energy management schemes are prone to scheduling mismatch when the prediction deviation is large, leading to increased operating costs. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the microgrid-based energy management method provided in the above embodiments, and will not be repeated here.

[0100] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. An energy management method based on microgrid partitioning, characterized in that, The method includes: The microgrid is divided into several node regions, and the power output forecast data and load forecast data of the node regions in future time periods are obtained; wherein, the power output forecast data includes at least the average power output forecast, the upper limit of the power output forecast, and the lower limit of the power output forecast, and the load forecast data includes at least the average load forecast, the upper limit of the load forecast, and the lower limit of the load forecast. The average net load of the node region in the future period is determined based on the average output forecast and the average load forecast, and the uncertainty index of the node region in the future period is determined based on the upper limit of output forecast, the lower limit of output forecast, the upper limit of load forecast, and the lower limit of load forecast. Based on the net load average and the uncertainty index, a cost function for the power exchange between the node region and its neighboring node regions is constructed, and the cost function is optimized to obtain the target value of the power exchange of the node region. The energy management scheme for each node region in the microgrid is determined based on the target exchange power value.

2. The energy management method based on microgrid partitioning as described in claim 1, characterized in that, The step of constructing a cost function for power exchange between the node region and its neighboring node regions based on the net load average and the uncertainty index includes: The coefficients of the linear term of the cost function are determined based on the net load average; and, The coefficients of the quadratic term of the cost function are determined based on the uncertainty index. The cost function for exchanging power between the node region and its neighboring node regions is constructed based on the coefficients of the first term and the coefficients of the second term.

3. The energy management method based on microgrid partitioning as described in claim 2, characterized in that, The step of optimizing according to the cost function to obtain the target value of the switching power of the node region includes: The historical neighbor consistency variables and historical marginal costs of the neighbor node region are obtained, and the exchange power is updated based on the historical neighbor consistency variables, the historical marginal costs, the first-order coefficients, and the second-order coefficients to obtain the current exchange power for the current iteration; wherein, the current exchange power is used to exchange with each of the neighbor nodes; The average current neighbor exchange power is determined based on the current neighbor exchange power of each neighbor node, and the consistency variable is updated based on the current exchange power and the average current neighbor exchange power to obtain the current consistency variable for the current round of iteration. If the current switching power and the current consistency variable of each node region satisfy the preset convergence condition, then the current switching power is taken as the target value of the switching power of the node region.

4. The energy management method based on microgrid partitioning as described in claim 3, characterized in that, After the step of updating the consistency variable based on the current switching power and the average current neighbor switching power to obtain the current consistency variable for the current round of iteration, the method further includes: If the current exchange power and the current consistency variable of a node region do not meet the preset convergence condition, then the current marginal cost of the current iteration is determined based on the current consistency variable, the current exchange power, and the historical marginal cost. Return to the step of obtaining the historical neighbor consistency variables and historical marginal costs of the neighbor node region to proceed to the next iteration.

5. The energy management method based on microgrid partitioning as described in claim 1, characterized in that, The step of determining the energy management scheme for each node region in the microgrid based on the target switching power value includes: Obtain the load priority information of each load in the node region; Power is allocated to the node region based on the load priority information and the target switching power value, and load control instructions are generated based on the power allocation results. An energy management scheme for the node region is generated based on the load control command.

6. The energy management method based on microgrid partitioning as described in claim 1, characterized in that, The step of obtaining the power output forecast data and load forecast data of the node region for future time periods includes: Acquire historical data, real-time operational data, and external meteorological data for the node region; Based on the historical data, the real-time operational data, and the external meteorological data, multi-timescale rolling forecasts are performed to obtain the power output forecast data and load forecast data for the node area in future periods.

7. An energy management device based on microgrid partitioning, characterized in that, The energy management device based on microgrid partitioning includes: The data prediction module is used to divide the microgrid into several node regions and obtain the output prediction data and load prediction data of the node regions in future time periods; wherein, the output prediction data includes at least the average output prediction value, the upper limit of the output prediction value, and the lower limit of the output prediction value, and the load prediction data includes at least the average load prediction value, the upper limit of the load prediction value, and the lower limit of the load prediction value. The indicator determination module is used to determine the average net load of the node area in the future period based on the average output forecast and the average load forecast, and to determine the uncertainty index of the node area in the future period based on the upper limit of output forecast, the lower limit of output forecast, the upper limit of load forecast, and the lower limit of load forecast. The power management module is used to construct a cost function for exchanging power between the node region and its neighboring node regions based on the net load average and the uncertainty index, and to optimize the cost function to obtain the target value of the exchange power of the node region. The load scheduling module is used to determine the energy management scheme for each node area in the microgrid based on the target switching power value.

8. An energy management device based on microgrid partitioning, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the energy management method based on microgrid partitioning as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the energy management method based on microgrid partitioning as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the energy management method based on microgrid partitioning as described in any one of claims 1 to 6.

Images