Fusion modeling method, device and equipment for power Internet of Things energy management

Abstract

The present application relates to a fusion modeling method, device and equipment for energy management of electric power Internet of Things, the method includes: configuring communication channels, synchronous clocks, exception handling links and model elements according to preset optimization requirements of electric power Internet of Things; using depth-first search method to divide at least one autonomous sub-area and determine its dominant power supply; based on the above-configured parameters and dominant power supply, respectively establish an analytical-data-driven fusion optimization model and solution function for the control center and autonomous sub-area, and perform cyclic iterative solution; after each round of solution, update the system status and check the convergence until the convergence termination condition is reached, and then generate the energy management plan of electric power Internet of Things. The proposed method, device and equipment significantly improve the energy management efficiency and optimized operation quality of electric power Internet of Things, and have broad prospects for industrial application.

Description

Technical Field

[0001] The present application relates to the technical field of power system optimization operation, and in particular to a fusion modeling method, device and equipment for power Internet of Things energy management. Background Art

[0002] Driven by the energy revolution and the digital revolution, the power system is accelerating its evolution towards the power Internet of Things. The so-called power Internet of Things is to apply the Internet of Things technology to the power system, thereby comprehensively improving the digitalization and intelligence level of the power system, realizing the interconnection of all things and human-machine interaction within the system, and providing solid and reliable technical support for different links and different application scenarios of the power system, such as power generation, transmission, transformation, distribution, and power consumption.

[0003] The power Internet of Things has new features such as comprehensive system perception, ubiquitous interconnection, and information fusion. At present, the technology is not mature enough and is still in the initial development stage. Taking the typical function of the power Internet of Things energy management as an example, the traditional method of power system optimization is difficult to directly migrate to the power Internet of Things, and there are still many technical challenges to be overcome.

[0004] First, the computational complexity of centralized optimization methods usually increases exponentially with the growth of the number of devices. In the power Internet of Things with a large number of smart devices, centralized optimization faces the curse of dimensionality and cannot meet the computing performance requirements of practical applications. If we further consider factors such as privacy protection, data distortion, and noise interference, centralized optimization methods may even fail completely due to the difficulty in modeling.

[0005] Second, distributed optimization methods have more application prospects in the power Internet of Things. Such methods usually divide the system into central nodes and sub-nodes. Each sub-node performs local calculations in rounds and responds to coordination instructions issued by the central node, thereby ultimately achieving iterative optimization of the entire system. Low iteration efficiency is the core bottleneck of such methods. In the power Internet of Things with massive smart devices, the efficiency problem of distributed optimization is particularly prominent.

[0006] In addition to the above-mentioned centralized / distributed classification criteria, existing modeling and analysis technologies can also be divided into pure analytical methods and pure data-driven methods according to model type.

[0007] First, pure analytical methods are generally based on physical mechanisms or operating equations for modeling, requiring the acquisition of all technical parameters of the entire system. In distributed optimization, pure analytical methods are often rough in the design of coordination instructions, and the problem of iteration efficiency is still prominent. In addition, a large number of applications in the power Internet of Things have obvious randomness and irrationality, which seriously damages the modeling accuracy of pure analytical methods.

[0008] Secondly, data-driven methods do not rely on specific mechanisms. They start from data and conduct modeling analysis by mining empirical correlations. Data-driven methods have the potential to handle more complex application scenarios, but are currently still mainly used in the field of prediction. Data-driven distributed optimization methods are relatively rare and usually cannot guarantee the convergence of iterations and the quality of converged solutions, and are still far from practical applications. Summary of the invention

[0009] The present application provides a fusion modeling method, device and equipment for energy management of the power Internet of Things to solve the problem that traditional methods for power system optimization are difficult to directly migrate to the power Internet of Things.

[0010] The first aspect of the present application provides a fusion modeling method for energy management of the power Internet of Things, comprising the following steps:

[0011] Configure communication channels, synchronous clocks, exception handling links, and model elements according to the preset power Internet of Things optimization requirements;

[0012] Using a depth-first search method to divide at least one autonomous sub-region, and determining the dominant power supply in each autonomous sub-region;

[0013] Based on the configured communication channels, synchronous clocks, exception handling links, model elements and the dominant power supply, respectively establish an analytical-data-driven fusion optimization model and a solution function for the control center and the autonomous sub-area, and perform a cyclic iterative solution; and

[0014] After each round of solution, the system status is updated and the convergence is checked until the convergence termination condition is reached, and the energy management plan of the power Internet of Things is generated.

[0015] According to an embodiment of the present application, configuring communication channels, synchronous clocks, exception handling links, and model elements according to preset power Internet of Things optimization requirements includes:

[0016] Determining the dominant power supply of all communicably connected sources, and configuring the communication channels based on the transmission rate and reliability of multiple connection channels of the dominant power supply;

[0017] Configuring the synchronization clock based on a preset clock zero point, a preset common frequency, and a preset synchronization state periodic refresh interval;

[0018] Configuring the exception handling link based on preset communication verification rules, exception types and exception handling strategies;

[0019] The model elements are configured based on the system control objective function, system control constraint function, system coupling constraint function of the control center, and the power supply objective function and power supply constraint conditions of the dominant power supply.

[0020] According to an embodiment of the present application, the autonomous sub-region is a control region including one or more power supply sources, and the method of dividing at least one autonomous sub-region by a depth-first search method includes:

[0021] Determine a search order, and use a depth-first method to perform a traversal search according to the search order;

[0022] Specifying the dominant power supply source in each autonomous sub-area;

[0023] Generate a coordination strategy between the energy supply sources in each autonomous sub-area.

[0024] According to an embodiment of the present application, establishing an analytical-data-driven fusion optimization model and a solution function for the control center and the autonomous sub-region respectively includes:

[0025] Constructing an optimization model expression for each autonomous sub-region according to the modeling elements;

[0026] Initialize and construct the coordinated variables and adjustment term function expressions, and determine the optimization solver;

[0027] The convergence termination condition and the upper limit of the iterative correction amount of the coordination variable are determined.

[0028] According to one embodiment of the present application, updating the system status and checking convergence includes:

[0029] Collecting the optimal value of the power supply state variable reported by each autonomous sub-area;

[0030] Based on the optimal value, an analytical-data driven model is used to update the coordination variable, and an adjustment item function is updated according to the system state, wherein the adjustment item function is an auxiliary function sent by the control center to each autonomous sub-area.

[0031] According to an embodiment of the present application, performing a loop iterative solution includes:

[0032] Establishing a corresponding autonomous sub-region optimization model according to the modeling elements, the coordination variables, and the adjustment term function, and solving the corresponding autonomous sub-region optimization model using the solver to obtain an optimal power generation capacity;

[0033] Based on the optimal power generation, the system control constraints are updated, and the control center optimization model is established, wherein the values ​​of the system control constraints are determined by the decision results between the autonomous sub-regions;

[0034] The solver is used to solve the control center optimization model to obtain the optimal value of the system control variable.

[0035] According to the fusion modeling method of the power Internet of Things energy management in the embodiment of the present application, the communication channels, synchronous clocks, exception handling links, and model elements are configured according to the preset power Internet of Things optimization requirements, and at least one autonomous sub-area is divided by the depth-first search method, and its dominant power supply is determined. Based on the above-configured parameters and the dominant power supply, an analytical-data-driven fusion optimization model and solution function are established for the control center and the autonomous sub-area, respectively, and a cyclic iterative solution is performed; after each round of solution, the system status is updated and the convergence is checked until the convergence termination condition is reached, and the power Internet of Things energy management plan is generated. Therefore, this method improves the energy management efficiency and optimized operation quality of the power Internet of Things, and has broad prospects for industrial application.

[0036] The second aspect of the present application provides a fusion modeling device for energy management of electric power Internet of Things, including:

[0037] Configuration module, used to configure communication channels, synchronous clocks, exception handling links, and model elements according to preset power Internet of Things optimization requirements;

[0038] A partitioning module, used to partition at least one autonomous sub-region by using a depth-first search method, and determine a dominant power supply in each autonomous sub-region;

[0039] An optimization module, for establishing an optimization model and a solution function of analytical-data-driven fusion for the control center and the autonomous sub-area based on the configured communication channels, synchronous clocks, exception handling links, model elements and the dominant power supply, and performing cyclic iterative solutions;

[0040] The output module is used to update the system status and check the convergence after each round of solution until the convergence termination condition is reached, and then generate the energy management plan of the power Internet of Things.

[0041] According to one embodiment of the present application, the configuration module is specifically used to:

[0042] Determining the dominant power supply of all communicably connected sources, and configuring the communication channels based on the transmission rate and reliability of multiple connection channels of the dominant power supply;

[0043] Configuring the synchronization clock based on a preset clock zero point, a preset common frequency, and a preset synchronization state periodic refresh interval;

[0044] Configuring the exception handling link based on preset communication verification rules, exception types and exception handling strategies;

[0045] The model elements are configured based on the system control objective function, system control constraint function, system coupling constraint function of the control center, and the power supply objective function and power supply constraint conditions of the dominant power supply.

[0046] According to an embodiment of the present application, the autonomous sub-area is a control area including one or more power supply sources, and the division module is specifically used to:

[0047] Determine a search order, and use a depth-first method to perform a traversal search according to the search order;

[0048] Specifying the dominant power supply source in each autonomous sub-area;

[0049] Generate a coordination strategy between the energy supply sources in each autonomous sub-area.

[0050] According to one embodiment of the present application, the optimization module is specifically used to:

[0051] Constructing an optimization model expression for each autonomous sub-region according to the modeling elements;

[0052] Initialize and construct the coordinated variables and adjustment term function expressions, and determine the optimization solver;

[0053] The convergence termination condition and the upper limit of the iterative correction amount of the coordination variable are determined.

[0054] According to one embodiment of the present application, the output module is specifically used for:

[0055] Collecting the optimal value of the power supply state variable reported by each autonomous sub-area;

[0056] Based on the optimal value, an analytical-data driven model is used to update the coordination variable, and an adjustment item function is updated according to the system state, wherein the adjustment item function is an auxiliary function sent by the control center to each autonomous sub-area.

[0057] According to one embodiment of the present application, the optimization module is specifically used to:

[0058] Establishing a corresponding autonomous sub-region optimization model according to the modeling elements, the coordination variables, and the adjustment term function, and solving the corresponding autonomous sub-region optimization model using the solver to obtain an optimal power generation capacity;

[0059] Based on the optimal power generation, the system control constraints are updated, and the control center optimization model is established, wherein the values ​​of the system control constraints are determined by the decision results between the autonomous sub-regions;

[0060] The solver is used to solve the control center optimization model to obtain the optimal value of the system control variable.

[0061] According to the fusion modeling device of the power Internet of Things energy management in the embodiment of the present application, the communication channels, synchronous clocks, exception handling links, and model elements are configured according to the preset power Internet of Things optimization requirements, and at least one autonomous sub-area is divided by the depth-first search method, and its dominant power supply is determined; based on the above-configured parameters and the dominant power supply, an analytical-data-driven fusion optimization model and solution function are established for the control center and the autonomous sub-area respectively, and a cyclic iterative solution is performed; after each round of solution, the system status is updated and the convergence is checked until the convergence termination condition is reached to generate the power Internet of Things energy management plan. As a result, the device improves the energy management efficiency and optimized operation quality of the power Internet of Things, and has broad prospects for industrial application.

[0062] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the fusion modeling method for energy management of the electric power Internet of Things as described in the above embodiment.

[0063] The fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the fusion modeling method for energy management of the electric power Internet of Things as described in the above embodiments.

[0064] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0066] Figure 1 A flowchart of a fusion modeling method for energy management of the power Internet of Things provided according to an embodiment of the present application;

[0067] Figure 2 A schematic diagram of a power Internet of Things information transmission process according to an embodiment of the present application;

[0068] Figure 3 A typical communication topology diagram of an electric power Internet of Things system provided according to an embodiment of the present application;

[0069] Figure 4 A schematic diagram of the division of autonomous sub-areas of the power Internet of Things provided according to an embodiment of the present application;

[0070] Figure 5 A schematic diagram of information interaction and calculation between a control center and an autonomous sub-region according to an embodiment of the present application;

[0071] Figure 6 This is an example diagram of a fusion modeling device for energy management of the electric power Internet of Things according to an embodiment of the present application;

[0072] Figure 7 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0073] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0074] The following describes the fusion modeling method, device and equipment of the power Internet of Things energy management of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that the traditional method of power system optimization mentioned in the above background technology center is difficult to directly migrate to the power Internet of Things, the present application provides a fusion modeling method of the power Internet of Things energy management. In this method, the communication channel, synchronous clock, exception handling link, and model elements are configured according to the preset power Internet of Things optimization requirements, and at least one autonomous sub-area is divided by a depth-first search method, and its dominant power supply is determined; based on the above-configured parameters and the dominant power supply, an analytical-data-driven fusion optimization model and solution function are established for the control center and the autonomous sub-area, respectively, and a cyclic iterative solution is performed; after each round of solution, the system state is updated and the convergence is checked until the convergence termination condition is reached to generate the power Internet of Things energy management plan. As a result, the proposed method, device and equipment significantly improve the energy management efficiency and optimized operation quality of the power Internet of Things, and have broad prospects for industrial application.

[0075] Specifically, Figure 1 A flow chart of a fusion modeling method for energy management of the electric power Internet of Things provided in an embodiment of the present application.

[0076] like Figure 1 As shown, the fusion modeling method of the power Internet of Things energy management includes the following steps:

[0077] In step S101, communication channels, synchronous clocks, exception handling links, and model elements are configured according to preset power Internet of Things optimization requirements.

[0078] Furthermore, in some embodiments, communication channels, synchronous clocks, exception handling links, and model elements are configured according to preset power Internet of Things optimization requirements, including: determining the dominant energy supply sources of all communicative connections, and configuring communication channels based on the transmission rate and reliability of multiple connection channels of the dominant energy supply source; configuring the synchronous clock based on a preset clock zero point, a preset common frequency, and a preset synchronization state periodic refresh interval; configuring the exception handling link based on preset communication verification rules, exception types, and exception handling strategies; configuring the model elements based on the system control objective function, system control constraint function, and system coupling constraint function of the control center, as well as the power objective function and power constraint conditions of the dominant energy supply source.

[0079] Specifically, combined Figure 2 As shown, the embodiment of the present application can carry out the system configuration work before optimization to ensure that all entities in the power Internet of Things can work together normally. This step specifically includes the following four sub-steps:

[0080] (1) Check the communication channels. The control center needs to determine all power sources that can be connected for communication. For nodes with multiple connection channels, the main channel and backup channel should be determined based on factors such as transmission rate and reliability. The upper limit of the number of relay nodes can be further limited to determine the legal communication channels. Figure 3 As shown, the control center O determines the connectable nodes in the energy supply AF, where for a node F with at least two connection modes, if the upper limit of the number of relay nodes is set to 0 (i.e., it cannot include relay nodes), it is considered that F cannot be connected to O. In addition, the control center organizes all connectable energy supplies and their communication channels, and suspends maintenance or grid expansion requirements for energy supplies that cannot be connected.

[0081] (2) Set up tolerance and exception handling mechanisms and agree on communication verification rules. In order to avoid the impact of external interference factors on the operation of the power Internet of Things, it is necessary to formulate tolerance and exception handling plans. Among them, at the communication level, it is necessary to agree on communication verification rules to ensure that the communication content between the control center, relay nodes, and power supply is accurate and reliable; at the operation level, it is necessary to agree on common exception types (such as accidental disconnection of the power supply, relay node failure, etc.) and corresponding exception handling strategies (such as removing the fault and continuing to operate, enabling backup communication channels, etc.); the control center will establish a log system to record all abnormal events and abnormal handling situations in the power Internet of Things in chronological order.

[0082] (3) Synchronous clock. The normal operation of the power Internet of Things depends on the coordinated timing between the control center and the power supply. Here, it is necessary to agree on the clock zero point, common frequency, and the time interval for regularly refreshing the synchronization status.

[0083] (4) Prepare optimization modeling elements. The control center and the power supply configure their own modeling elements, namely the parameters and model forms used in the optimization model. These elements only need to be saved locally and do not need to be published externally. Specifically, the control center needs to specify specific system control variables, as well as the system control objective function, system control constraint function, and system coupling constraint function; the power supply uses power generation as the optimization variable and needs to determine the power supply objective function and power supply constraint conditions.

[0084] It should be noted that the energy sources can be optimized independently, but in the absence of coordination, the overall behavior of all sources may violate the system coupling constraints (for example, the total power generation exceeds the transmission capacity of the distribution network). Therefore, the important responsibility of the control center is to introduce a coordination mechanism to guide the power generation behavior of each energy source.

[0085] In step S102, at least one autonomous sub-region is divided using a depth-first search method, and a dominant power supply source in each autonomous sub-region is determined.

[0086] Furthermore, in some embodiments, the autonomous sub-region is a control region including one or more power supplies, and at least one autonomous sub-region is divided using a depth-first search method, including: determining a search order, and using a depth-first method to perform a traversal search according to the search order; specifying a dominant power supply within each autonomous sub-region; and generating a coordination strategy between the power supplies within each autonomous sub-region.

[0087] Specifically, the autonomous sub-region refers to a collection of one or several dominant energy sources, and ensures that the objective functions or constraints of each energy source in the region are coupled, but the energy sources within and outside the region are independent of each other. This division step is led by the control center and can support the establishment of a dynamic hierarchical structure of the power Internet of Things to ensure the efficient execution of optimization tasks. This step specifically includes the following three sub-steps:

[0088] (1) Determine the search order and use the depth-first method to traverse the search. The control center gradually generates autonomous subintervals by traversing all connectable power supplies. First, determine the search order of a group of power supplies (which can be determined by serial number, communication speed or random order), and then the control center will notify the power supply one by one to report other power supplies that are coupled with it, and then continue to query these coupled power supplies according to the depth-first rule. The control center will eventually assign an autonomous subinterval number to this group of power supplies, and then search for the next power supply that is not included in the autonomous subinterval. The above process will continue to cycle until all allocations are completed.

[0089] like Figure 4As shown, the process of dividing autonomous sub-area 1 is as follows: the control center O first communicates with power supply A and learns that there is coupling between the optimization models of A and B, that is, there is coupling in the power optimization target or power constraint; then communicates with power supply B and finds no more coupled power supplies; based on this, A and B are allocated to autonomous sub-area 1. Similarly, autonomous sub-areas 2-4 are divided.

[0090] (2) Specify the dominant power supply in the autonomous sub-area. After the autonomous sub-area is determined, the control center will only communicate with the dominant power supply in it. The dominant power supply can be determined by comprehensively considering factors such as communication speed and communication reliability. Figure 4 As shown, the dominant power supply of autonomous sub-area 1 is A, the dominant power supply of autonomous sub-area 4 is E, and since autonomous sub-areas 2 and 3 only have one power supply, that power supply automatically becomes the dominant power supply.

[0091] (3) Formulate a coordination strategy between the energy sources in the autonomous sub-region. Each autonomous sub-region will handle the coupling relationship between different energy sources by establishing a joint optimization model. The model can be a large optimization model that includes all energy source state variables, objective functions and constraints. This sub-step is led by the dominant energy source and does not need to be reported to the control center.

[0092] In step S103, based on the configured communication channels, synchronous clocks, exception handling links, model elements and dominant power supply, analytical-data-driven fusion optimization models and solution functions are established for the control center and the autonomous sub-areas respectively, and cyclic iterative solutions are performed.

[0093] Furthermore, in some embodiments, analytical-data-driven fusion optimization models and solution functions are established for the control center and the autonomous sub-regions respectively, including: constructing an optimization model expression for each autonomous sub-region based on modeling elements; initializing the construction of coordination variables and adjustment term function expressions, and determining the optimization solver; determining the convergence termination conditions and the upper limit of the iterative correction amount of the coordination variables.

[0094] Specifically, the optimization operation model and solution function of the power Internet of Things are established, including various configuration tasks before executing the optimization task, including the following steps:

[0095] (1) The control center and the autonomous sub-region construct their own optimization model expressions based on the modeling elements collected in the above step of preparing the optimization modeling elements. The optimization model is generally a type that is easy to solve, such as linear programming, quadratic programming, second-order cone programming, and semi-positive definite programming. If the optimization model is a type that is difficult to solve, such as nonlinear programming, the sequential linearization method can be used to perform model approximate conversion.

[0096] (2) The control center initializes and constructs the expressions of coordination variables and adjustment function. The coordination variables and adjustment function are the information released by the control center to the autonomous sub-regions during the optimization process, which are used to coordinate the optimization behaviors among different regions.

[0097] (3) The control center and the autonomous sub-region determine the optimization solver respectively. It can be a mature commercial solver or a free open source solver. In addition, if the optimization model is relatively simple and the closed-form solution can be directly listed according to the optimality condition method, the solution function can be directly constructed.

[0098] (4) The control center determines the termination conditions for iterative convergence and the upper limit of the iterative correction amount of the coordination variable. Often, multiple termination conditions can be set, including when the number of iterations reaches the set upper limit, when the difference between the optimal solutions of the two rounds is less than the set range, etc. The upper limit of the iterative correction amount should not be too large and can be reasonably set based on historical experience.

[0099] In step S104, after each round of solving, the system status is updated and the convergence is checked until the convergence termination condition is reached, and then an energy management plan for the power Internet of Things is generated.

[0100] Furthermore, in some embodiments, updating the system state and checking convergence include: collecting the optimal values ​​of the power supply state variables reported by each autonomous sub-region; based on the optimal values, updating the coordination variables using an analytical-data driven model, and updating the adjustment item function according to the system state, wherein the adjustment item function is an auxiliary function sent by the control center to each autonomous sub-region.

[0101] Specifically, this step can be called in the first round of iteration or other rounds. When called in the first round, it is only necessary to initialize the system state and interaction information, and then proceed to the next step, that is, the control center and the autonomous sub-region mentioned below independently carry out local optimization. Among them, the system state refers to the value of the system control variables and the power generation of the power source, which can generally be initialized to the rated operating point or the historical average operating point; the interaction information refers to the coordination variables and the adjustment item function. The coordination variables can be set to zero or historical experience values ​​for initial value setting, and the adjustment item function can be set to zero or initialized to a linear function.

[0102] Furthermore, when this step is called in other rounds (iterative loops), the following three sub-steps need to be further executed:

[0103] (1) The control center collects the optimal values ​​of the power supply state variables reported by each autonomous sub-region;

[0104] (2) The control center uses the analytical-data driven fusion method to update the coordination variables. The formula is as follows:

[0105] Updated coordination variable = coordination variable before update + coordination variable correction;

[0106] Therefore, the coordinated variable correction can be solved by the fusion modeling method, and the following solution model needs to be constructed:

[0107] min estimated violation of system coupling constraints;

[0108] st coordination variable correction amount ≤ correction amount upper limit;

[0109] Among them, the variable to be optimized is the coordinated variable correction, the constraint condition parameter adopts the above-mentioned termination condition of iterative convergence, and belongs to the analytical model; and the objective function is the estimated system coupling constraint violation, which can be modeled using a data-driven model.

[0110] Furthermore, in a non-limiting example, combined with the data accumulated in the relevant technology (the response changes of the power generation of each power source under different coordination variables), a deep learning neural network model can be trained to fit the mapping relationship in the data, that is, the expected power generation of each power supply when the coordination variable takes different values ​​can be predicted in advance, and the violation of the system coupling constraint can be estimated by substituting it into the system coupling constraint expression. This estimation method belongs to a form of adaptive configuration, and its accuracy is higher than the traditional method of directly presetting parameters, which is conducive to greatly improving the iteration efficiency, reducing iterative oscillations, and promoting the control center and the autonomous sub-region to quickly approach the convergence state.

[0111] It should be noted that the above-mentioned solution model is relatively complex, but the model scale is often small, and heuristic methods such as random search or grid search can be used for approximate solutions.

[0112] (3) The control center updates the adjustment function according to the system status. The adjustment function is an auxiliary function issued by the control center to the autonomous sub-region. The adjustment functions of different autonomous regions may be completely different. The adjustment function can include two options: one is to directly extract the function term related to the autonomous sub-region from the system coupling constraints, and the other is to find the first-order Taylor expansion of this function term at the current operating point.

[0113] Further, in some embodiments, a loop iterative solution is performed, including: establishing a corresponding autonomous sub-region optimization model according to modeling elements, coordination variables, and adjustment term functions, and using a solver to solve the corresponding autonomous sub-region optimization model to obtain the optimal power generation; based on the optimal power generation, updating the system control constraints, and establishing a control center optimization model, wherein the value of the system control constraints is determined by the decision results between the autonomous sub-regions; using a solver to solve the control center optimization model to obtain the optimal value of the system control variable. The solver is a generalized solution software.

[0114] Specifically, Figure 5 As shown, the control center and the autonomous sub-region independently carry out local optimization, corresponding to the optimization calculation details of the autonomous sub-region and the control center respectively:

[0115] (1) Autonomous sub-region optimization calculation details. Based on the prepared optimization modeling elements and the obtained coordination variables and adjustment term functions, the following autonomous sub-region optimization model can be established:

[0116] min power objective function + coordination variable × adjustment term function;

[0117] st power supply constraint condition is established;

[0118] The variable to be optimized is the power generation of all power sources in the autonomous sub-region. The control center and the autonomous sub-region determine the optimization solver (mature commercial solver or free open source solver) to solve the above optimization model, obtain the optimal power generation and upload the optimal solution to the control center.

[0119] (2) Control center optimization calculation details. After receiving the optimization calculation results of all autonomous subintervals, the control center first updates the system control constraints (in some applications, the value boundaries of the system control constraints are affected by the decision results of the autonomous subintervals), and then establishes the following control center optimization model:

[0120] min system control objective function;

[0121] st system control constraints are established;

[0122] The variables to be optimized are system control variables. The control center and the autonomous sub-regions are respectively used to determine the optimization solver (a mature commercial solver or a free open source solver) to solve the above optimization model to obtain the optimal value of the system control variable.

[0123] like Figure 5 As shown in the figure, in one cycle, the control center will first initialize the coordination variables and adjustment item functions, and publish them to the autonomous sub-intervals; the autonomous sub-intervals will calculate the optimal power generation and upload it to the control center; the control center will then establish and solve the system optimization control model, and configure efficient coordination variables based on historical data, and finally publish the updated coordination variables and adjustment item functions again; the autonomous sub-regions will update the local energy management optimization model accordingly, and repeat the above cycle.

[0124] Furthermore, the control center determines whether the convergence termination condition is met. The iterative convergence termination condition determined in the above steps usually includes a variety of different conditions: when (any) convergence termination condition is met, the loop is jumped out and the optimization result is output, otherwise the loop is returned to iterative solution and the next round of optimization calculation is entered.

[0125] In order to facilitate those skilled in the art to further understand the fusion modeling method of power Internet of Things energy management in the embodiment of the present application, the following is further described according to its specific steps:

[0126] S1, carry out system configuration work before optimization:

[0127] S11, check communication channels;

[0128] S12, setting tolerance and exception handling mechanism, and agreeing on communication verification rules;

[0129] S13, synchronous clock;

[0130] S14, prepare to optimize modeling elements.

[0131] S2, divide the power Internet of Things autonomous sub-areas:

[0132] S21, determine the search order and use the depth-first method to perform traversal search;

[0133] S22, the dominant power source in the designated autonomous sub-region;

[0134] S23, formulate a coordination strategy among the energy sources in the autonomous sub-area.

[0135] S3, establish the power Internet of Things optimization operation model and solution function:

[0136] S31, the control center and the autonomous sub-region respectively construct their own optimization model expressions according to the modeling elements collected in sub-step S14;

[0137] S32, the control center initializes and constructs the coordination variables and adjustment item function expressions;

[0138] S33, the control center and the autonomous sub-region respectively determine the optimization solver;

[0139] S34, the control center determines the termination condition of iterative convergence and the upper limit of iterative correction amount of the coordination variable.

[0140] S4, update system status and interaction information:

[0141] S41, the control center collects the optimal values ​​of the power supply state variables reported by each autonomous sub-region;

[0142] S42, the control center updates the coordination variables using the analytical-data driven fusion method;

[0143] S43, the control center updates the adjustment item function according to the system status.

[0144] S5, the control center and autonomous sub-regions independently perform local optimization:

[0145] S51, autonomous sub-region optimization calculation details;

[0146] S52, the control center optimizes the calculation details.

[0147] S6, the control center determines whether the convergence termination condition is met. If so, execute S7, otherwise, execute S4.

[0148] S7, output optimization results, record system status and optimal solution information.

[0149] The specific contents of the above steps have been described in detail in the embodiments and will not be described in detail here. It should be noted that when multiple optimization tasks need to be completed continuously, the above steps S2-S7 need to be repeated; if the autonomous sub-region does not need to be dynamically adjusted, only steps S3-S7 need to be repeated.

[0150] According to the fusion modeling method of the power Internet of Things energy management in the embodiment of the present application, the communication channels, synchronous clocks, exception handling links, and model elements are configured according to the preset power Internet of Things optimization requirements, and the depth-first search method is used to divide at least one autonomous sub-area of ​​the power Internet of Things, and its dominant power supply is determined; based on the above-configured parameters and the dominant power supply, the optimization model and solution function of the analytical-data-driven fusion are established for the control center and the autonomous sub-area respectively, and the cyclic iterative solution is performed; after each round of solution, the system status is updated and the convergence is checked until the convergence termination condition is reached to generate the power Internet of Things energy management plan. Therefore, the proposed method improves the energy management efficiency and optimized operation quality of the power Internet of Things, and has broad prospects for industrial application.

[0151] Secondly, the fusion modeling device for energy management of the power Internet of Things proposed in accordance with the embodiment of the present application is described with reference to the accompanying drawings.

[0152] Figure 6 It is a block diagram of a fusion modeling device for energy management of the electric power Internet of Things according to an embodiment of the present application.

[0153] like Figure 6 As shown, the fusion modeling device 10 for power Internet of Things energy management includes: a configuration module 100, a division module 200, an optimization module 300 and an output module 400.

[0154] Among them, the configuration module 100 is used to configure the communication channel, synchronous clock, abnormal processing link, and model elements according to the preset power Internet of Things optimization requirements;

[0155] The partitioning module 200 is used to partition at least one autonomous sub-region by using a depth-first search method, and determine the dominant power supply in each autonomous sub-region;

[0156] The optimization module 300 is used to establish an optimization model and a solution function of analytical-data-driven fusion for the control center and the autonomous sub-area based on the configured communication channels, synchronous clocks, exception handling links, model elements and dominant power supply, and perform cyclic iterative solutions;

[0157] The output module 400 is used to update the system status and check the convergence after each round of solution, and generate an energy management plan for the power Internet of Things after the convergence termination condition is reached.

[0158] Furthermore, in some embodiments, the configuration module 100 is specifically configured to:

[0159] Determine the dominant energy source of all communicative connections, and configure communication channels based on the transmission rate and reliability of multiple connection channels of the dominant energy source;

[0160] Configure the synchronization clock based on a preset clock zero point, a preset common frequency, and a preset synchronization state periodic refresh interval;

[0161] Configure exception handling based on preset communication verification rules, exception types and exception handling strategies;

[0162] Model elements are configured based on the system control objective function, system control constraint function, system coupling constraint function of the control center, as well as the power objective function and power constraint condition of the dominant energy source.

[0163] Further, in some embodiments, the autonomous sub-area is a control area including one or more power supply sources, and the division module 200 is specifically used for:

[0164] Determine the search order and use the depth-first method to traverse the search order;

[0165] Specify the dominant power source in each autonomous sub-region;

[0166] Generate a coordination strategy between the energy sources in each autonomous sub-area.

[0167] Furthermore, in some embodiments, the optimization module 300 is specifically configured to:

[0168] Constructing the optimization model expression for each autonomous sub-region based on the modeling elements;

[0169] Initialize and construct the coordinated variables and adjustment term function expressions, and determine the optimization solver;

[0170] Determine the convergence termination condition and the upper limit of the iterative correction amount of the coordination variable.

[0171] Further, in some embodiments, the output module 400 is specifically configured to:

[0172] Collect the optimal values of the power supply status variables reported by each autonomous sub-region;

[0173] Based on the optimal values, update the coordination variables using an analytical-data-driven model and update the adjustment term function according to the system state, where the adjustment term function is an auxiliary function sent by the control center to each autonomous sub-region.

[0174] Further, in some embodiments, the optimization module 300 is specifically configured to:

[0175] Establish a corresponding autonomous sub-region optimization model according to the modeling elements, coordination variables, and adjustment term function, and use a solver to solve the corresponding autonomous sub-region optimization model to obtain the optimal power generation;

[0176] Based on the optimal power generation, update the system control constraints and establish a control center optimization model, where the adjustment term function is an auxiliary function sent by the control center to each autonomous sub-region;

[0177] Use a solver to solve the control center optimization model to obtain the optimal values of the system control variables.

[0178] According to the fusion modeling device for power Internet of Things energy management in the embodiments of the present application, configure communication channels, synchronous clocks, exception handling links, and model elements according to the preset power Internet of Things optimization requirements; divide at least one autonomous sub-region using the depth-first search method and determine its dominant power supply; based on the above-configured parameters and the dominant power supply, establish an analytical-data-driven fusion optimization model and a solution function for the control center and autonomous sub-regions respectively, and perform iterative solution; after each round of solution, update the system state and check the convergence until the convergence termination condition is reached, and then generate a power Internet of Things energy management solution. Thus, the proposed device improves the efficiency of power Internet of Things energy management and the quality of optimized operation, and has broad industrial application prospects.

[0179] Figure 7 The structural schematic diagram of the electronic device provided by the embodiment of the present application. The electronic device may include:

[0180] A memory 701, a processor 702, and a computer program stored on the memory 701 and executable on the processor 702.

[0181] When the processor 702 executes the program, it implements the fusion modeling method for power Internet of Things energy management provided in the above embodiments.

[0182] Furthermore, the electronic device further comprises:

[0183] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0184] The memory 701 is used to store computer programs that can be executed on the processor 702 .

[0185] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0186] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0187] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0188] The processor 702 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0189] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the above-mentioned fusion modeling method for energy management of the power Internet of Things is implemented.

[0190] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0191] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0192] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0193] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0194] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0195] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0196] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0197] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A fusion modeling method for energy management of power Internet of Things, It is characterized in that The following steps are involved: Configure communication channels, synchronous clocks, exception handling links, and model elements according to the preset power Internet of Things optimization requirements; Using a depth-first search method to divide at least one autonomous sub-region, and determining the dominant power supply in each autonomous sub-region; Based on the configured communication channels, synchronous clocks, exception handling links, model elements and the dominant power supply, respectively establish an analytical-data-driven fusion optimization model and a solution function for the control center and the autonomous sub-area, and perform cyclic iterative solutions; and After each round of solving, the system status is updated and the convergence is checked until the convergence termination condition is reached, and the power Internet of Things energy management plan is generated; The configuration of communication channels, synchronous clocks, exception handling links, and model elements according to the preset power Internet of Things optimization requirements includes: Determining the dominant power supply of all communicably connected sources, and configuring the communication channels based on the transmission rate and reliability of multiple connection channels of the dominant power supply; Configuring the synchronization clock based on a preset clock zero point, a preset common frequency, and a preset synchronization state periodic refresh interval; Configuring the exception handling link based on preset communication verification rules, exception types and exception handling strategies; The model elements are configured based on the system control objective function, system control constraint function, system coupling constraint function of the control center, and the power supply objective function and power supply constraint conditions of the dominant power supply.

2. The method according to claim 1, It is characterized in that The autonomous sub-region is a control region including one or more power supply sources, and the depth-first search method is used to divide at least one autonomous sub-region, including: Determine a search order, and use a depth-first method to perform a traversal search according to the search order; Specifying the dominant power supply source in each autonomous sub-area; Generate a coordination strategy between the energy supply sources in each autonomous sub-area.

3. The method according to claim 1, It is characterized in that The establishing of an analytical-data driven fusion optimization model and a solution function for the control center and the autonomous sub-region respectively includes: Constructing an optimization model expression for each autonomous sub-region according to the modeling elements; Initialize and construct the coordinated variables and adjustment term function expressions, and determine the optimization solver; The convergence termination condition and the upper limit of the iterative correction amount of the coordination variable are determined.

4. The method according to claim 3, It is characterized in that The updating of the system status and checking of convergence include: Collecting the optimal value of the power supply state variable reported by each autonomous sub-area; Based on the optimal value, an analytical-data driven model is used to update the coordination variable, and an adjustment item function is updated according to the system state, wherein the adjustment item function is an auxiliary function sent by the control center to each autonomous sub-area.

5. The method according to claim 4, It is characterized in that The loop iterative solution comprises: Establishing a corresponding autonomous sub-region optimization model according to the modeling elements, the coordination variables, and the adjustment term function, and solving the corresponding autonomous sub-region optimization model using the solver to obtain an optimal power generation capacity; Based on the optimal power generation, the system control constraints are updated, and the control center optimization model is established, wherein the values ​​of the system control constraints are determined by the decision results between the autonomous sub-regions; The solver is used to solve the control center optimization model to obtain the optimal value of the system control variable.

6. A fusion modeling device for power Internet of Things energy management, It is characterized in that include: Configuration module, used to configure communication channels, synchronous clocks, exception handling links, and model elements according to preset power Internet of Things optimization requirements; A partitioning module, used to partition at least one autonomous sub-region by using a depth-first search method, and determine a dominant power supply in each autonomous sub-region; An optimization module is used to establish an optimization model and a solution function of analytical-data-driven fusion for the control center and the autonomous sub-area based on the configured communication channels, synchronous clocks, exception handling links, model elements and the dominant power supply, and perform cyclic iterative solutions; as well as The output module is used to update the system status and check the convergence after each round of solution, until the convergence termination condition is reached, and then generate the energy management plan of the power Internet of Things; The configuration module is specifically used for: Determining the dominant power supply of all communicably connected sources, and configuring the communication channels based on the transmission rate and reliability of multiple connection channels of the dominant power supply; Configuring the synchronization clock based on a preset clock zero point, a preset common frequency, and a preset synchronization state periodic refresh interval; Configuring the exception handling link based on preset communication verification rules, exception types and exception handling strategies; The model elements are configured based on the system control objective function, system control constraint function, system coupling constraint function of the control center, and the power supply objective function and power supply constraint conditions of the dominant power supply.

7. An electronic device, It is characterized in that include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the fusion modeling method for energy management of the electric power Internet of Things as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that The program is executed by a processor to implement the fusion modeling method for energy management of the electric power Internet of Things as described in any one of claims 1-5.

Images