Cloud edge collaboration-based multi-micronet group optimization scheduling method, device and system

Abstract

The application provides a kind of based on cloud edge coordination's multi-micronet group optimization scheduling method, device and system, cloud server receives each edge server through micro-grid scheduling model and sends local scheduling parameter;Cloud server obtains initial global scheduling parameter based on each local scheduling parameter and distribution network scheduling model;For each edge server, based on initial global scheduling parameter and distributed optimization algorithm, interactive iteration process is executed until the optimal global scheduling parameter is obtained.In this scheme, through the hierarchical structure of cloud edge coordination, the data transmission amount is effectively reduced, and the overall scheduling efficiency of the system is improved, and only the scheduling parameters are transmitted between the cloud layer and the edge layer, so that the sensitive information of the micro-grid cannot be obtained by the cloud layer, thereby ensuring the data isolation and privacy security between the subjects, and the global optimal scheduling result is obtained by using the distributed optimization algorithm for multiple interactive iterations, which ensures the overall economy and operation efficiency of the system.

Description

Technical Field

[0001] This invention relates to the field of multi-microgrid group optimization scheduling technology in power systems, specifically to a multi-microgrid group optimization scheduling method, device, and system based on cloud-edge collaboration. Background Technology

[0002] With the transformation of the global energy structure and the continuous development of distributed energy technologies, microgrid technology has become an important component of future power systems. Microgrids can flexibly integrate various renewable energy sources, such as solar photovoltaic power generation and wind power generation, and can also include energy storage systems and fuel cell power generation equipment, thereby providing electricity users with efficient and low-carbon power supply. This distributed energy system not only improves the stability and reliability of local power supply, but also reduces electricity costs and brings economic benefits to users through participation in electricity market transactions.

[0003] However, with the expansion of microgrid scale and the widespread application of microgrids, the concept of multi-microgrid cluster systems has gradually emerged. A multi-microgrid cluster refers to multiple independently operating microgrids interconnected through a common active distribution network to form an energy system with stronger coupling capabilities. In this system, each microgrid can not only operate independently to meet its local load demand, but also participate in the scheduling and optimization of the distribution network to collaboratively improve the overall system's economy and reliability.

[0004] Despite the broad application prospects of multi-microgrid systems, their economic dispatch optimization faces numerous challenges. First, traditional centralized dispatch methods require collecting detailed operational data from each microgrid (such as power generation and load conditions) and performing centralized optimization through a unified dispatch center. However, this method carries the risk of data privacy breaches, as individual microgrids, as independent stakeholders, are unwilling to share their detailed operational data. Furthermore, as the scale of multi-microgrid systems expands, centralized dispatch also incurs a significant communication burden, leading to reduced system operating efficiency. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method, apparatus and system for optimizing scheduling of multi-micro network groups based on cloud-edge collaboration, so as to ensure data isolation and privacy security among various subjects, as well as the overall economy and operating efficiency of the system.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] The first aspect of this invention discloses a multi-microgrid group optimization scheduling method based on cloud-edge collaboration, applied to a cloud server in a multi-microgrid group optimization scheduling system based on cloud-edge collaboration. The cloud server is communicatively connected to multiple edge servers in the multi-microgrid group optimization scheduling system. The cloud server is deployed in a power distribution network, and each edge server is deployed in a corresponding microgrid. The method includes:

[0008] The system receives local scheduling parameters sent by each of the edge servers; the local scheduling parameters are obtained by the edge servers based on a pre-configured microgrid scheduling model, which is established based on an objective function aimed at minimizing the total operating cost of the microgrid.

[0009] Based on the local scheduling parameters and the pre-configured distribution network scheduling model, the initial global scheduling parameters are obtained; the distribution network scheduling model is established based on an objective function aimed at minimizing the total operating cost of the distribution network.

[0010] For each of the aforementioned edge servers, an interactive iterative process is performed based on the initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0011] Preferably, for each of the edge servers, the interactive iterative process based on initial global scheduling parameters and a distributed optimization algorithm is performed until the optimal global scheduling parameters are obtained, including:

[0012] The initial global scheduling parameters are sent to each of the edge servers;

[0013] Receive the local optimization results obtained by each of the edge servers performing local optimization tasks based on the initial global scheduling parameters;

[0014] Based on the local optimization results, a global optimization task is performed to obtain new global scheduling parameters;

[0015] If the new global scheduling parameters do not meet the convergence condition, the new global scheduling parameters are used as the initial global scheduling parameters, and the process of sending the initial global scheduling parameters to each edge server is returned until the new global scheduling parameters meet the convergence condition and the optimal global scheduling parameters are obtained.

[0016] Preferably, receiving the local optimization results obtained by each of the edge servers performing local optimization tasks based on initial global scheduling parameters includes:

[0017] For each edge server that supports the execution of a local optimization task based on initial global scheduling parameters using its remaining computing resources, the local optimization result obtained from the execution of the local optimization task is received from the edge server.

[0018] For a target edge server whose remaining computing resources do not support executing a local optimization task based on initial global scheduling parameters, the system receives a local optimization result sent by an outsourced computing object specified by the target edge server. The outsourced computing object obtains the local optimization result by receiving and executing the outsourced task sent by the target edge server. The outsourced task is encrypted and packaged by the target edge server using outsourced encryption technology. The outsourced object includes the cloud server and the edge server whose remaining computing resources support executing the local optimization task.

[0019] Preferably, before performing the interactive iterative process based on initial global scheduling parameters and a distributed optimization algorithm for each of the edge servers, the method further includes:

[0020] Get the initial condition parameters;

[0021] The initial condition parameters are input into the distributed optimization algorithm for initialization settings.

[0022] A second aspect of this invention discloses a multi-microgrid group optimization scheduling method based on cloud-edge collaboration, applied to any edge server in a multi-microgrid group optimization scheduling system based on cloud-edge collaboration. Each edge server is communicatively connected to a cloud server in the multi-microgrid group optimization scheduling system. Each edge server is deployed in a corresponding microgrid, and the cloud server is deployed in a distribution network. The method includes:

[0023] Local scheduling parameters are obtained based on a pre-configured microgrid scheduling model, and these local scheduling parameters are sent to the cloud server. The cloud server then obtains initial global scheduling parameters based on the local scheduling parameters sent by each edge server and the pre-configured distribution network scheduling model. The microgrid scheduling model is established based on an objective function that minimizes the total operating cost of the microgrid; the distribution network scheduling model is also established based on an objective function that minimizes the total operating cost of the distribution network.

[0024] An interactive iterative process is performed based on the initial global scheduling parameters and the distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0025] Preferably, the step of performing an interactive iterative process based on initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained includes:

[0026] Receive the initial global scheduling parameters sent by the cloud server;

[0027] The local optimization task is performed based on the initial global scheduling parameters to obtain the local optimization result;

[0028] The local optimization results are sent to the cloud server, so that the cloud server performs a global optimization task based on the local optimization results sent by each edge server to obtain new global scheduling parameters. If the new global scheduling parameters do not meet the convergence condition, the new global scheduling parameters are used as the initial global scheduling parameters.

[0029] Return to the step of receiving the initial global scheduling parameters sent by the cloud server, until the cloud server determines that the new global scheduling parameters satisfy the convergence condition and obtains the optimal global scheduling parameters.

[0030] Preferably, the step of performing a local optimization task based on initial global scheduling parameters to obtain a local optimization result includes:

[0031] If the remaining computing resources support the execution of a local optimization task based on the initial global scheduling parameters, then the local optimization task is executed to obtain the local optimization result;

[0032] If the remaining computing resources do not support the execution of local optimization tasks based on the initial global scheduling parameters, the local optimization tasks are encrypted and packaged using outsourcing encryption technology to obtain outsourcing tasks.

[0033] The outsourced task is sent to any outsourced computing object, so that the outsourced computing object executes the outsourced task to obtain the local optimization result, and sends the local optimization result to the cloud server; the outsourced object includes: the cloud server and the edge server whose remaining computing resources support the execution of the local optimization task.

[0034] A third aspect of this invention discloses a cloud-edge collaborative multi-microgrid group optimization scheduling device, applied to a cloud server in a cloud-edge collaborative multi-microgrid group optimization scheduling system. The cloud server is communicatively connected to multiple edge servers in the multi-microgrid group optimization scheduling system. The cloud server is deployed in a power distribution network, and each edge server is deployed in a corresponding microgrid. The device includes:

[0035] The receiving unit is used to receive local scheduling parameters sent by each of the edge servers; the local scheduling parameters are obtained by the edge servers based on a pre-configured microgrid scheduling model, and the microgrid scheduling model is established based on an objective function aimed at minimizing the total operating cost of the microgrid;

[0036] The first initial scheduling unit is used to obtain initial global scheduling parameters based on the various local scheduling parameters and the pre-configured distribution network scheduling model; the distribution network scheduling model is established based on an objective function aimed at minimizing the total operating cost of the distribution network.

[0037] The first iteration unit is used to perform an interactive iterative process for each of the edge servers based on the initial global scheduling parameters and the distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0038] A fourth aspect of this invention discloses a multi-microgrid group optimization scheduling device based on cloud-edge collaboration, applied to any edge server in a multi-microgrid group optimization scheduling system based on cloud-edge collaboration. Each edge server is communicatively connected to a cloud server in the multi-microgrid group optimization scheduling system. Each edge server is deployed in a corresponding microgrid, and the cloud server is deployed in a distribution network. The device includes:

[0039] The second initial scheduling unit is used to obtain local scheduling parameters based on a pre-configured microgrid scheduling model and send the local scheduling parameters to the cloud server, so that the cloud server obtains initial global scheduling parameters based on the local scheduling parameters sent by each of the edge servers and the pre-configured distribution network scheduling model; the microgrid scheduling model is established based on an objective function that minimizes the total operating cost of the microgrid; the distribution network scheduling model is established based on an objective function that minimizes the total operating cost of the distribution network.

[0040] The second iterative unit is used to perform an interactive iterative process based on the initial global scheduling parameters and the distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0041] The fifth aspect of this invention discloses a multi-microgrid group optimization scheduling system based on cloud-edge collaboration. The system includes a cloud server and multiple edge servers. The cloud server is communicatively connected to the multiple edge servers in the multi-microgrid group optimization scheduling system. The cloud server is deployed in a power distribution network, and each edge server is deployed in a corresponding microgrid.

[0042] The cloud server is used to receive local scheduling parameters sent by each of the edge servers; based on each of the local scheduling parameters and a pre-configured distribution network scheduling model, initial global scheduling parameters are obtained; the distribution network scheduling model is established based on an objective function aimed at minimizing the total operating cost of the distribution network; for each of the edge servers, an interactive iterative process is performed based on the initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0043] The edge server is used to obtain local scheduling parameters based on a pre-configured microgrid scheduling model and send the local scheduling parameters to the cloud server; the microgrid scheduling model is established based on an objective function aimed at minimizing the total operating cost of the microgrid; an interactive iterative process is performed based on the initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0044] Based on the above embodiments of the present invention, a method, apparatus, and system for optimizing the scheduling of multiple microgrids based on cloud-edge collaboration are provided. These are applied to a cloud server in a cloud-edge collaborative multi-microgrid optimization scheduling system. The cloud server is communicatively connected to multiple edge servers in the system. The cloud server is deployed in a distribution network, and each edge server is deployed in a corresponding microgrid. The method includes: receiving local scheduling parameters sent by each edge server; the local scheduling parameters are obtained by the edge server based on a pre-configured microgrid scheduling model, which is established based on an objective function aimed at minimizing the total operating cost of the microgrid; obtaining initial global scheduling parameters based on the local scheduling parameters and the pre-configured distribution network scheduling model; the distribution network scheduling model is established based on an objective function aimed at minimizing the total operating cost of the distribution network; and for each edge server, performing an interactive iterative process based on the initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained. In this scheme, the layered structure of cloud-edge collaboration effectively reduces the amount of data transmission and improves the overall scheduling efficiency of the system. Furthermore, only scheduling parameters are transmitted between the cloud layer and the edge layer, and the sensitive information of the microgrid will not be obtained by the cloud layer, thereby ensuring data isolation and privacy security among the various entities. In addition, the distributed optimization algorithm is used to obtain the globally optimal scheduling result through multiple interactive iterations, ensuring the overall economy and operating efficiency of the system. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0046] Figure 1 This is an architecture diagram of a multi-micro-network group optimization scheduling system based on cloud-edge collaboration disclosed in an embodiment of the present invention;

[0047] Figure 2 This is a technical schematic diagram of a cloud-edge collaborative multi-micro-network group optimization scheduling system disclosed in an embodiment of the present invention;

[0048] Figure 3 This is a flowchart of a multi-micro-network group optimization scheduling method based on cloud-edge collaboration disclosed in an embodiment of the present invention;

[0049] Figure 4 This is a schematic diagram of an encrypted outsourced computing strategy disclosed in an embodiment of the present invention;

[0050] Figure 5This is a flowchart of another cloud-edge collaborative multi-micro network group optimization scheduling method disclosed in an embodiment of the present invention;

[0051] Figure 6 This is a structural diagram of a multi-micro-network group optimization scheduling device based on cloud-edge collaboration disclosed in an embodiment of the present invention;

[0052] Figure 7 This is a structural diagram of another cloud-edge collaborative multi-micro-network group optimization scheduling device disclosed in an embodiment of the present invention. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0055] As the background technology indicates, traditional centralized scheduling methods require collecting detailed operational data (such as power generation and load status) from each microgrid and performing centralized optimization through a unified dispatch center. However, this method carries the risk of data privacy breaches, as each microgrid, as an independent entity with its own interests, is unwilling to share its detailed operational data. Furthermore, as the scale of multi-microgrid systems expands, centralized scheduling also incurs a significant communication burden, leading to reduced system operating efficiency.

[0056] Therefore, this invention discloses a method, apparatus, and system for optimized scheduling of multiple microgrids based on cloud-edge collaboration. In this solution, the hierarchical structure of cloud-edge collaboration effectively reduces data transmission volume and improves the overall scheduling efficiency of the system. Furthermore, only scheduling parameters are transmitted between the cloud layer and the edge layer; sensitive information of the microgrid is not acquired by the cloud layer, thus ensuring data isolation and privacy security among the various entities. Additionally, the use of a distributed optimization algorithm for multiple interactive iterations to obtain the globally optimal scheduling result ensures the overall economic efficiency and operational efficiency of the system.

[0057] like Figure 1The diagram shown is an architecture diagram of a cloud-edge collaborative multi-micro-network group optimization scheduling system disclosed in an embodiment of the present invention. The system includes a computing layer and a physical layer.

[0058] The computing layer includes cloud servers and multiple edge servers, while the physical layer includes power distribution networks and multiple microgrids.

[0059] The cloud server communicates with each edge server. The cloud server is deployed on the power distribution network, and each edge server is deployed on its corresponding microgrid.

[0060] The distribution network and multiple microgrids operate independently, and are physically connected to each other for power exchange.

[0061] The method for constructing a multi-microgrid group optimized scheduling system with a two-layer architecture of physical and computational layers is as follows:

[0062] To meet the needs of joint operation and real-time control between distribution networks and microgrids, a microgrid is used as an edge node and an edge server is deployed there, providing computing, local optimization scheduling, and data storage capabilities. Cloud servers, deployed on the distribution network, possess abundant computing resources and are primarily responsible for global optimization scheduling, handling complex scheduling problems.

[0063] like Figure 2 The diagram shown is a technical principle diagram of a multi-micro-network group optimization scheduling system based on cloud-edge collaboration disclosed in an embodiment of the present invention.

[0064] Each microgrid has a distributed architecture and includes power generation equipment (such as wind power, photovoltaic power, and energy storage systems) and load equipment. The distribution network includes generator sets and load equipment.

[0065] Specifically, the cloud server receives local scheduling parameters sent by each edge server; based on the local scheduling parameters and the pre-configured distribution network scheduling model, it obtains the initial global scheduling parameters; for each edge server, it performs an interactive iterative process based on the initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0066] The distribution network scheduling model is based on an objective function aimed at minimizing the total operating cost of the distribution network.

[0067] Edge servers are used to obtain local scheduling parameters based on a pre-configured microgrid scheduling model and send the local scheduling parameters to the cloud server; an interactive iterative process is performed based on the initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0068] The microgrid scheduling model is based on an objective function aimed at minimizing the total operating cost of the microgrid.

[0069] It should be noted that local scheduling parameters refer to the trading power given within the initial microgrid with the goal of minimizing the total operating cost of the microgrid, while global scheduling parameters are the set of trading power transferred between the cloud server and each edge server.

[0070] Based on the above embodiments of the present invention, a multi-microgrid group optimization scheduling system based on cloud-edge collaboration is disclosed. Each microgrid can independently generate electricity, store energy, and meet local load demands. Simultaneously, through collaborative cooperation with other microgrids and distribution networks, it achieves higher economic efficiency, reliability, and flexibility. The multi-microgrid group system not only optimizes the utilization of energy resources within the region but also improves the overall system's operational efficiency through distributed scheduling, adapting to the modern power system's requirements for clean energy consumption and multi-entity optimized operation. Furthermore, by distributing computing tasks to cloud servers and edge servers, distributed economic scheduling optimization is achieved without sharing sensitive data. This layered architecture not only reduces communication burden but also ensures the data privacy and security of each microgrid.

[0071] like Figure 3 The diagram shows a flowchart of a cloud-edge collaborative multi-micro network group optimization scheduling method disclosed in an embodiment of the present invention. Applied to a cloud server in the cloud-edge collaborative multi-micro network group optimization scheduling system disclosed in the above embodiment of the present invention, the method includes the following steps:

[0072] Step S301: Receive local scheduling parameters sent by each edge server.

[0073] In step S301, the local scheduling parameters are obtained by the edge server based on a pre-configured microgrid scheduling model, which is established based on an objective function aimed at minimizing the total operating cost of the microgrid.

[0074] Specifically, the local scheduling parameters are calculated by the edge server based on the pre-configured microgrid scheduling model and the microgrid's local load, generation capacity, and energy storage status.

[0075] It should be noted that the microgrid dispatch model obtains not only local dispatch parameters but also internal dispatch parameters that are retained only on the edge servers, such as the output of controllable units within the microgrid. These internal dispatch parameters, stored on the edge servers, are continuously optimized and updated during subsequent interactive iterations until the optimal global dispatch parameters are obtained. At this point, the edge servers perform power dispatching outwards based on the global dispatch parameters and implement internal dispatching within the microgrid based on the current internal dispatch parameters.

[0076] Step S302: Based on the local scheduling parameters and the pre-configured distribution network scheduling model, obtain the initial global scheduling parameters.

[0077] In step S302, the distribution network scheduling model is established based on an objective function aimed at minimizing the total operating cost of the distribution network.

[0078] It should be noted that while the distribution network dispatching model obtains global dispatching parameters, it also obtains internal dispatching parameters that are only retained in the cloud server, such as the output of controllable units within the distribution network. The internal dispatching parameters retained in the cloud server will also be optimized and updated in subsequent interactive iterations until the optimal global dispatching parameters are obtained. At this point, the cloud server performs power dispatching externally based on the global dispatching parameters and implements internal dispatching within the distribution network based on the current internal dispatching parameters.

[0079] In the specific implementation of step S302, the global scheduling parameters and the internal scheduling parameters of the distribution network are calculated based on each local scheduling parameter, the pre-configured distribution network scheduling model, and the state parameters of the distribution network.

[0080] The status parameters of the distribution network include: local load, generation capacity, energy storage status, etc.

[0081] The objective function that aims to minimize the total operating cost of the distribution network is, in other words, the objective function that aims to minimize the sum of the total generation cost of the distribution network units and the interaction cost with multiple microgrids:

[0082] minC=min{C DG +C MG}

[0083] Where C is the total operating cost of the distribution network, C DG C represents the total power generation cost of the distribution network units. MG This refers to the interaction cost between the distribution network and each microgrid.

[0084]

[0085] Where N is the total number of generator sets in the distribution network, P DG,i Let a be the power generation of generator set i. i b i and c i Let be the cost coefficient of generator set i.

[0086]

[0087] Where M is the total number of microgrids, P buy,j and P sell,j These represent the electricity purchased and sold from the distribution network to microgrid j, respectively. buy,j and c sell,j These are the electricity purchase price and electricity sales price for microgrid j, respectively.

[0088] The distribution network dispatching model includes the following constraints:

[0089] Active power balance constraints, system reserve constraints, upper and lower limits of active power of controllable fuel units, ramping speed constraints of controllable fuel units, minimum start-up and shutdown time constraints, power purchase constraints of large power grid, load shelving constraints, and PCC (Point of Common Coupling) trading power constraints.

[0090] Step S303: For each edge server, perform an interactive iterative process based on the initial global scheduling parameters and the distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0091] In step S303, the distributed optimization algorithm can handle multi-objective and multi-dimensional scheduling optimization problems, reducing system costs while ensuring the overall economy and operating efficiency of the system.

[0092] In one embodiment, after obtaining the optimal global scheduling parameters, the optimal global scheduling parameters are sent to each edge server.

[0093] It should be noted that the interactive iteration process involves not only iterative updates of global scheduling parameters, but also iterative updates of internal scheduling parameters that do not need to be transmitted within the cloud server. This process yields both the optimal global scheduling parameters and the optimal internal scheduling parameters for the distribution network. Furthermore, iterative updates are also performed on internal scheduling parameters that do not need to be transmitted within the edge server, resulting in the optimal internal scheduling parameters for the microgrid.

[0094] The optimal internal dispatch parameters and optimal global dispatch parameters corresponding to the distribution network and microgrid constitute the day-ahead dispatch scheme. Since the microgrid and distribution network directly know the parts of the day-ahead dispatch scheme that are relevant to them, they can achieve global dispatch by directly adjusting the output of their internal units based on these parts.

[0095] Day-ahead scheduling is a planned dispatch scheme developed in the electricity market or grid dispatching to ensure the balance of electricity supply and demand the following day. Essentially, it involves optimizing the generation, transmission, and distribution of electricity one day in advance based on electricity market demand forecasts, generator availability, and other system constraints.

[0096] In one embodiment, prior to step S303, the method further includes:

[0097] Obtain the initial condition parameters; input the initial condition parameters into the distributed optimization algorithm for initialization settings.

[0098] Initial condition parameters include: load demand, environmental information, and predicted power generation from new energy units.

[0099] It should be noted that the initial condition parameters are obtained from historical data and the prediction model. In distributed optimization algorithms, other variables besides the decision variables need to be given in advance for the solution of the decision variables. The decision variables are the internal scheduling parameters of the microgrid and the distribution network, as well as the scheduling parameters between the distribution network and the microgrids.

[0100] The specific implementation of step S303 includes:

[0101] Step S3031: Send the initial global scheduling parameters to each edge server.

[0102] Step S3032: Receive the local optimization results obtained by each edge server performing local optimization tasks based on the initial global scheduling parameters.

[0103] In step S3032, when the local optimization task is executed, the edge server performs local optimization on the internal scheduling parameters and the transaction power transmitted to the cloud server based on status parameters such as local load, power generation capacity, and energy storage status. The local optimization result refers to the transaction power transmitted to the cloud server.

[0104] For a detailed explanation of the specific implementation process of step S3032, please refer to [link / reference]. Figure 4 This is a schematic diagram of an encrypted outsourcing computing strategy disclosed in an embodiment of the present invention. The specific implementation process is as follows:

[0105] For each edge server with remaining computing resources, local optimization tasks are performed based on initial global scheduling parameters, and the local optimization results obtained from the execution of local optimization tasks are received from the edge server.

[0106] For target edge servers whose remaining computing resources do not support performing local optimization tasks based on initial global scheduling parameters, the local optimization results sent by the outsourced computing object specified by the target edge server are received.

[0107] The outsourced computing object receives outsourced tasks sent by the target edge server and executes the outsourced tasks to obtain local optimization results; the outsourced tasks are obtained by the target edge server using outsourced encryption technology to encrypt and package the local optimization tasks; the outsourced objects include: cloud servers and edge servers with remaining computing resources that support the execution of local optimization tasks.

[0108] In this embodiment of the invention, when the computing resources of each edge server can support its completion of its respective local optimization task within the allowed time, the edge servers solve the problem in parallel, and the distribution network and microgrid interact with non-sensitive information through cloud-edge collaboration, achieving coordinated solution between the distribution network and the microgrid. However, when the computing resources of the edge nodes are insufficient to support the execution of local optimization tasks, the cumulative lag effect of a certain edge server will significantly reduce the overall cloud-edge collaborative solution time. In this case, edge servers with limited computing resources can outsource computing tasks to cloud servers or other edge servers to effectively improve computing efficiency.

[0109] It should be noted that when an outsourced task is executed by an outsourced computing object, it is equivalent to executing a local optimization task based on the initial global scheduling parameters. Since the local optimization task contains state parameters of the edge server, such as local load, power generation capacity, and energy storage status, which are sensitive power data, encrypted outsourced computing technology is used. This ensures that regardless of whether the outsourced computing object is a cloud server or another edge server, it cannot obtain the true privacy information, thus avoiding the risk of information leakage due to potential hacker attacks.

[0110] Preferably, if the outsourced computing object is a cloud server, the cloud server receives the outsourced task sent by the edge server and executes the outsourced task to obtain local optimization results.

[0111] Step S3033: Execute a global optimization task based on the results of each local optimization to obtain new global scheduling parameters.

[0112] In step S3033, the cloud server performs a global optimization task, calculates the global power balance and economic benefits, and provides new global scheduling parameters.

[0113] It should be noted that the global optimization task can also update the internal scheduling parameters of the cloud server.

[0114] Step S3034: If the new global scheduling parameters do not meet the convergence condition, then use the new global scheduling parameters as the initial global scheduling parameters and return to step S3031 until the new global scheduling parameters meet the convergence condition and the optimal global scheduling parameters are obtained.

[0115] Among them, the new global scheduling parameters satisfy the convergence condition, that is, the global economic benefits and system power balance reach the optimal state.

[0116] Based on the cloud-edge collaborative multi-microgrid group optimization scheduling method disclosed in this invention, this scheme divides the entire system into two main parts—cloud servers and edge servers—through a hierarchical structure, thereby achieving an organic combination of global and local scheduling. The cloud server, as the core of global scheduling, is responsible for collecting and processing power data and economic scheduling requirements at the distribution network level, comprehensively considering factors such as system operating costs, power generation capacity, and load demand to formulate a global optimization scheduling strategy. Simultaneously, the cloud server and edge servers interact by transmitting traded power, without transmitting the specific operating data of each microgrid, ensuring data privacy. The edge servers of each microgrid focus on handling local optimization tasks within the microgrid. The edge servers utilize local load, power generation, and energy storage data to perform independent optimization calculations to meet local power demands, and then transmit the optimized traded power to the cloud server, achieving cloud-edge collaborative scheduling. This distributed computing model not only significantly reduces the system's communication burden and the need for large-scale data transmission, but also ensures the overall system's operating efficiency and response speed. Meanwhile, by using encrypted outsourced computing technology, this invention can outsource local optimization tasks to cloud servers or other edge servers with sufficient computing resources when edge server computing resources are insufficient, thereby further improving the system's flexibility and computing efficiency.

[0117] like Figure 5 The diagram shows another cloud-edge collaborative multi-micro network group optimization scheduling method disclosed in this embodiment of the invention. Applied to the edge server in the cloud-edge collaborative multi-micro network group optimization scheduling system disclosed in the above embodiment of the invention, the method includes the following steps:

[0118] Step S501: Obtain local scheduling parameters based on the pre-configured microgrid scheduling model, and send the local scheduling parameters to the cloud server, so that the cloud server can obtain the initial global scheduling parameters based on the local scheduling parameters sent by each edge server and the pre-configured distribution network scheduling model.

[0119] Among them, the microgrid scheduling model is established based on an objective function that aims to minimize the total operating cost of the microgrid; the distribution network scheduling model is established based on an objective function that aims to minimize the total operating cost of the distribution network.

[0120] The objective function that aims to minimize the total operating cost of the microgrid is, in other words, the objective function that aims to minimize the sum of the total generation cost of the microgrid units and the interaction cost with the distribution network:

[0121] minf = f DG +f oper +f PD

[0122] Where f is the sum of the operating costs of a single microgrid, f DG For the unit's power generation cost, considering only traditional generator sets such as diesel engines and steam turbines, f oper For the operation and maintenance costs of new energy units, f PD For transaction costs between microgrids and distribution networks.

[0123] The constraints of the microgrid dispatch model include: power balance constraints, distributed generation power constraints, and PCC trading power constraints.

[0124] Step S502: Execute an interactive iterative process based on the initial global scheduling parameters and the distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0125] The specific implementation of step S502 includes the following steps:

[0126] Step S5021: Receive the initial global scheduling parameters sent by the cloud server.

[0127] Step S5022: Execute a local optimization task based on the initial global scheduling parameters to obtain the local optimization results.

[0128] The specific implementation process of step S5022 is as follows:

[0129] If the remaining computing resources support the execution of a local optimization task based on the initial global scheduling parameters, then the local optimization task will be executed to obtain the local optimization result.

[0130] If the remaining computing resources do not support the execution of local optimization tasks based on the initial global scheduling parameters, then the local optimization tasks are encrypted and packaged using outsourcing encryption technology to obtain outsourcing tasks.

[0131] The outsourced task is sent to any outsourced computing object, which then executes the outsourced task to obtain a local optimization result and sends the local optimization result to the cloud server. The outsourced objects include: cloud servers and edge servers with remaining computing resources that support the execution of local optimization tasks.

[0132] Step S5023: Send the local optimization results to the cloud server, so that the cloud server can perform a global optimization task based on the local optimization results sent by each edge server to obtain new global scheduling parameters. If the new global scheduling parameters do not meet the convergence condition, the new global scheduling parameters are used as the initial global scheduling parameters.

[0133] Step S5024: Return to step S5021 until the cloud server determines that the new global scheduling parameters meet the convergence condition and obtains the optimal global scheduling parameters.

[0134] It should be noted that for explanations of the embodiments of the present invention, please refer to the above-described cloud-edge collaborative multi-micro network group optimization scheduling method disclosed in the embodiments of the present invention, which will not be repeated here.

[0135] Based on the cloud-edge collaborative multi-microgrid group optimization scheduling method disclosed in this invention, this scheme effectively reduces data transmission volume and improves the overall scheduling efficiency of the system through the hierarchical structure of cloud-edge collaboration. Furthermore, only scheduling parameters are transmitted between the cloud server and each edge server; sensitive information such as the microgrid's specific load data and power generation data is not obtained by the cloud layer, thus ensuring data isolation and privacy security among the various entities. Utilizing encrypted outsourced computing technology, the problem of insufficient computing resources on edge servers is solved while ensuring data privacy, achieving optimized allocation of computing resources. Using a distributed optimization algorithm, parallel solving between the cloud server and each edge server is achieved. Through multiple iterations and interactions, the optimal global scheduling parameters are finally obtained, reducing system costs while ensuring the overall economy and operational efficiency of the system.

[0136] like Figure 6 The diagram shown is a structural diagram of a cloud-edge collaborative multi-micro network group optimization scheduling device disclosed in an embodiment of the present invention. It is applied to a cloud server in a cloud-edge collaborative multi-micro network group optimization scheduling system disclosed in the above embodiment of the present invention. The device includes: a receiving unit 601, a first initial scheduling unit 602, and a first iteration unit 603.

[0137] The receiving unit 601 is used to receive local scheduling parameters sent by each edge server. The local scheduling parameters are obtained by the edge server based on a pre-configured microgrid scheduling model, which is established based on an objective function aimed at minimizing the total operating cost of the microgrid.

[0138] The first initial scheduling unit 602 is used to obtain initial global scheduling parameters based on various local scheduling parameters and a pre-configured distribution network scheduling model; the distribution network scheduling model is established based on an objective function aimed at minimizing the total operating cost of the distribution network.

[0139] The first iteration unit 603 is used to perform an interactive iterative process for each edge server based on the initial global scheduling parameters and the distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0140] In one embodiment, the first iteration unit 603 is specifically used for:

[0141] The process involves sending initial global scheduling parameters to each edge server; receiving local optimization results from each edge server based on the initial global scheduling parameters; performing a global optimization task based on the local optimization results to obtain new global scheduling parameters; and if the new global scheduling parameters do not meet the convergence condition, using the new global scheduling parameters as the initial global scheduling parameters and returning to the step of sending the initial global scheduling parameters to each edge server until the new global scheduling parameters meet the convergence condition and the optimal global scheduling parameters are obtained.

[0142] In one embodiment, the first iteration unit 603, used to receive the local optimization results obtained by each edge server performing a local optimization task based on initial global scheduling parameters, is specifically used for:

[0143] For each edge server whose remaining computing resources support the execution of local optimization tasks based on initial global scheduling parameters, the local optimization results obtained from the execution of local optimization tasks are received from the edge server. For target edge servers whose remaining computing resources do not support the execution of local optimization tasks based on initial global scheduling parameters, the local optimization results sent by the outsourced computing object specified by the target edge server are received. The outsourced computing object obtains local optimization results by receiving and executing the outsourced task sent by the target edge server. The outsourced task is obtained by the target edge server using outsourced encryption technology to encrypt and package the local optimization task. The outsourced objects include: cloud servers and edge servers whose remaining computing resources support the execution of local optimization tasks.

[0144] In one embodiment, the device further includes:

[0145] The initialization unit is used to obtain initial condition parameters for each edge server before performing the interactive iterative process based on the initial global scheduling parameters and the distributed optimization algorithm; and input the initial condition parameters into the distributed optimization algorithm for initialization settings.

[0146] Based on the cloud-edge collaborative multi-microgrid group optimization scheduling device disclosed in this invention, this solution effectively reduces data transmission volume and improves the overall scheduling efficiency of the system through a hierarchical structure of cloud-edge collaboration. Furthermore, only scheduling parameters are transmitted between the cloud server and each edge server; sensitive information such as specific load data and power generation data of the microgrid is not obtained by the cloud layer, thus ensuring data isolation and privacy security among the various entities. Utilizing encrypted outsourced computing technology, the problem of insufficient computing resources on edge servers is solved while ensuring data privacy, achieving optimized allocation of computing resources. Using a distributed optimization algorithm, parallel solving between the cloud server and each edge server is achieved. Through multiple iterations and interactions, the optimal global scheduling parameters are finally obtained, reducing system costs while ensuring the overall economy and operational efficiency of the system.

[0147] like Figure 7 The diagram shown is a structural diagram of another cloud-edge collaborative multi-micro network group optimization scheduling device disclosed in an embodiment of the present invention. It is applied to the edge server in the cloud-edge collaborative multi-micro network group optimization scheduling system disclosed in the above embodiment of the present invention. The device includes: a second initial scheduling unit 701 and a second iteration unit 702.

[0148] The second initial scheduling unit 701 is used to obtain local scheduling parameters based on a pre-configured microgrid scheduling model and send the local scheduling parameters to the cloud server, so that the cloud server obtains the initial global scheduling parameters based on the local scheduling parameters sent by each edge server and the pre-configured distribution network scheduling model; the microgrid scheduling model is established based on an objective function that aims to minimize the total operating cost of the microgrid; the distribution network scheduling model is established based on an objective function that aims to minimize the total operating cost of the distribution network.

[0149] The second iteration unit 702 is used to perform an interactive iterative process based on the initial global scheduling parameters and the distributed optimization algorithm until the optimal global scheduling parameters are obtained.

[0150] In one embodiment, the second iteration unit 702 is specifically used for:

[0151] Receive the initial global scheduling parameters sent by the cloud server; perform a local optimization task based on the initial global scheduling parameters to obtain the local optimization result; send the local optimization result back to the cloud server, so that the cloud server performs a global optimization task based on the local optimization results sent by each edge server to obtain a new global scheduling parameter. If the new global scheduling parameter does not meet the convergence condition, the new global scheduling parameter is used as the initial global scheduling parameter; return to the step of receiving the initial global scheduling parameter sent by the cloud server until the cloud server determines that the new global scheduling parameter meets the convergence condition and obtains the optimal global scheduling parameter.

[0152] In one embodiment, the second iteration unit 702, used to perform a local optimization task based on initial global scheduling parameters to obtain local optimization results, is specifically used for:

[0153] If the remaining computing resources support the execution of a local optimization task based on the initial global scheduling parameters, the local optimization task is executed to obtain the local optimization result. If the remaining computing resources do not support the execution of a local optimization task based on the initial global scheduling parameters, the local optimization task is encrypted and packaged using outsourcing encryption technology to obtain an outsourced task. The outsourced task is sent to any outsourced computing object, so that the outsourced computing object executes the outsourced task to obtain the local optimization result, and sends the local optimization result to the cloud server. The outsourced objects include: the cloud server and the edge server whose remaining computing resources support the execution of the local optimization task.

[0154] Based on the cloud-edge collaborative multi-microgrid group optimization scheduling device disclosed in this invention, this solution effectively reduces data transmission volume and improves the overall scheduling efficiency of the system through a hierarchical structure of cloud-edge collaboration. Furthermore, only scheduling parameters are transmitted between the cloud server and each edge server; sensitive information such as specific load data and power generation data of the microgrid is not obtained by the cloud layer, thus ensuring data isolation and privacy security among the various entities. Utilizing encrypted outsourced computing technology, the problem of insufficient computing resources on edge servers is solved while ensuring data privacy, achieving optimized allocation of computing resources. Using a distributed optimization algorithm, parallel solving between the cloud server and each edge server is achieved. Through multiple iterations and interactions, the optimal global scheduling parameters are finally obtained, reducing system costs while ensuring the overall economy and operational efficiency of the system.

[0155] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0156] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0157] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-microgrid group optimization scheduling method based on cloud-edge collaboration, characterized in that, A cloud server is applied to a cloud-edge collaborative multi-microgrid group optimization scheduling system, wherein the cloud server is communicatively connected to multiple edge servers in the multi-microgrid group optimization scheduling system, the cloud server is deployed in a power distribution network, and each edge server is deployed in a corresponding microgrid. The method includes: The system receives local scheduling parameters sent by each of the edge servers; the local scheduling parameters are obtained by the edge servers based on a pre-configured microgrid scheduling model, which is established based on an objective function aimed at minimizing the total operating cost of the microgrid. Based on the local scheduling parameters and the pre-configured distribution network scheduling model, the initial global scheduling parameters are obtained; the distribution network scheduling model is established based on an objective function aimed at minimizing the total operating cost of the distribution network. For each of the aforementioned edge servers, an interactive iterative process is performed based on initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained, including: receiving the local optimization results obtained by each of the aforementioned edge servers performing local optimization tasks based on the initial global scheduling parameters; The step of receiving the local optimization results obtained by each of the edge servers performing local optimization tasks based on initial global scheduling parameters includes: For a target edge server whose remaining computing resources do not support executing a local optimization task based on initial global scheduling parameters, the system receives a local optimization result sent by an outsourced computing object specified by the target edge server. The outsourced computing object obtains the local optimization result by receiving and executing the outsourced task sent by the target edge server. The outsourced task is encrypted and packaged by the target edge server using outsourced encryption technology. The outsourced computing object includes the cloud server and the edge server whose remaining computing resources support executing the local optimization task.

2. The method according to claim 1, characterized in that, For each of the edge servers, an interactive iterative process is performed based on initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained, including: The initial global scheduling parameters are sent to each of the edge servers; Receive the local optimization results obtained by each of the edge servers performing local optimization tasks based on the initial global scheduling parameters; Based on the local optimization results, a global optimization task is performed to obtain new global scheduling parameters; If the new global scheduling parameters do not meet the convergence condition, the new global scheduling parameters are used as the initial global scheduling parameters, and the process of sending the initial global scheduling parameters to each edge server is returned until the new global scheduling parameters meet the convergence condition and the optimal global scheduling parameters are obtained.

3. The method according to claim 2, characterized in that, The step of receiving the local optimization results obtained by each of the edge servers performing local optimization tasks based on initial global scheduling parameters includes: For each edge server that supports the execution of a local optimization task based on initial global scheduling parameters using its remaining computing resources, the local optimization results obtained from executing the local optimization task are received from the edge server.

4. The method according to claim 2, characterized in that, Before performing the interactive iterative process for each of the edge servers based on initial global scheduling parameters and a distributed optimization algorithm, the method further includes: Get the initial condition parameters; The initial condition parameters are input into the distributed optimization algorithm for initialization settings.

5. A multi-microgrid group optimization scheduling method based on cloud-edge collaboration, characterized in that, The method applies to any edge server in a cloud-edge collaborative multi-microgrid group optimization scheduling system, wherein each edge server is communicatively connected to a cloud server in the multi-microgrid group optimization scheduling system, each edge server is deployed in a corresponding microgrid, and the cloud server is deployed in a distribution network. The method includes: Local scheduling parameters are obtained based on a pre-configured microgrid scheduling model, and these local scheduling parameters are sent to the cloud server. The cloud server then obtains initial global scheduling parameters based on the local scheduling parameters sent by each edge server and the pre-configured distribution network scheduling model. The microgrid scheduling model is established based on an objective function that minimizes the total operating cost of the microgrid; the distribution network scheduling model is also established based on an objective function that minimizes the total operating cost of the distribution network. An interactive iterative process is performed based on the initial global scheduling parameters and the distributed optimization algorithm until the optimal global scheduling parameters are obtained, including: performing local optimization tasks based on the initial global scheduling parameters to obtain local optimization results; The process of performing a local optimization task based on initial global scheduling parameters to obtain local optimization results includes: If the remaining computing resources do not support the execution of the local optimization task based on the initial global scheduling parameters, the local optimization task is encrypted and packaged using outsourcing encryption technology to obtain an outsourced task; the outsourced task is sent to any outsourced computing object, so that the outsourced computing object executes the outsourced task to obtain the local optimization result, and sends the local optimization result to the cloud server; the outsourced computing object includes: the cloud server and the edge server whose remaining computing resources support the execution of the local optimization task.

6. The method according to claim 5, characterized in that, The interactive iterative process based on the initial global scheduling parameters and the distributed optimization algorithm, until the optimal global scheduling parameters are obtained, includes: Receive the initial global scheduling parameters sent by the cloud server; The local optimization task is performed based on the initial global scheduling parameters to obtain the local optimization result; The local optimization results are sent to the cloud server, so that the cloud server performs a global optimization task based on the local optimization results sent by each edge server to obtain new global scheduling parameters. If the new global scheduling parameters do not meet the convergence condition, the new global scheduling parameters are used as the initial global scheduling parameters. Return to the step of receiving the initial global scheduling parameters sent by the cloud server, until the cloud server determines that the new global scheduling parameters satisfy the convergence condition and obtains the optimal global scheduling parameters.

7. The method according to claim 6, characterized in that, The process of performing a local optimization task based on initial global scheduling parameters to obtain local optimization results includes: If the remaining computing resources support the execution of a local optimization task based on the initial global scheduling parameters, then the local optimization task is executed to obtain the local optimization result.

8. A multi-micro-network group optimization scheduling device based on cloud-edge collaboration, characterized in that, A cloud server is applied to a cloud-edge collaborative multi-microgrid group optimization scheduling system. The cloud server is communicatively connected to multiple edge servers in the multi-microgrid group optimization scheduling system. The cloud server is deployed in a power distribution network, and each edge server is deployed in a corresponding microgrid. The device includes: The receiving unit is used to receive local scheduling parameters sent by each of the edge servers; the local scheduling parameters are obtained by the edge servers based on a pre-configured microgrid scheduling model, and the microgrid scheduling model is established based on an objective function aimed at minimizing the total operating cost of the microgrid; The first initial scheduling unit is used to obtain initial global scheduling parameters based on the various local scheduling parameters and the pre-configured distribution network scheduling model; the distribution network scheduling model is established based on an objective function aimed at minimizing the total operating cost of the distribution network. The first iteration unit is used to perform an interactive iterative process for each of the edge servers based on initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained, including: receiving the local optimization results obtained by each of the edge servers performing local optimization tasks based on the initial global scheduling parameters; The step of receiving the local optimization results obtained by each of the edge servers performing local optimization tasks based on initial global scheduling parameters includes: For a target edge server whose remaining computing resources do not support executing a local optimization task based on initial global scheduling parameters, the system receives a local optimization result sent by an outsourced computing object specified by the target edge server. The outsourced computing object obtains the local optimization result by receiving and executing the outsourced task sent by the target edge server. The outsourced task is encrypted and packaged by the target edge server using outsourced encryption technology. The outsourced computing object includes the cloud server and the edge server whose remaining computing resources support executing the local optimization task.

9. A multi-micro-network group optimization scheduling device based on cloud-edge collaboration, characterized in that, An edge server is applied to any edge server in a cloud-edge collaborative multi-microgrid group optimization scheduling system. Each edge server is communicatively connected to a cloud server in the multi-microgrid group optimization scheduling system. Each edge server is deployed in a corresponding microgrid, and the cloud server is deployed in a distribution network. The device includes: The second initial scheduling unit is used to obtain local scheduling parameters based on a pre-configured microgrid scheduling model and send the local scheduling parameters to the cloud server, so that the cloud server obtains initial global scheduling parameters based on the local scheduling parameters sent by each of the edge servers and the pre-configured distribution network scheduling model; the microgrid scheduling model is established based on an objective function that minimizes the total operating cost of the microgrid; the distribution network scheduling model is established based on an objective function that minimizes the total operating cost of the distribution network. The second iteration unit is used to perform an interactive iterative process based on the initial global scheduling parameters and the distributed optimization algorithm until the optimal global scheduling parameters are obtained, including: performing local optimization tasks based on the initial global scheduling parameters to obtain local optimization results; The process of performing a local optimization task based on initial global scheduling parameters to obtain local optimization results includes: If the remaining computing resources do not support the execution of the local optimization task based on the initial global scheduling parameters, the local optimization task is encrypted and packaged using outsourcing encryption technology to obtain an outsourced task; the outsourced task is sent to any outsourced computing object, so that the outsourced computing object executes the outsourced task to obtain the local optimization result, and sends the local optimization result to the cloud server; the outsourced computing object includes: the cloud server and the edge server whose remaining computing resources support the execution of the local optimization task.

10. A multi-micro-network group optimization scheduling system based on cloud-edge collaboration, characterized in that, The system includes: a cloud server and multiple edge servers. The cloud server is communicatively connected to the multiple edge servers in the multi-microgrid group optimization scheduling system. The cloud server is deployed in the power distribution network, and each edge server is deployed in a corresponding microgrid. The cloud server is used to receive local scheduling parameters sent by each of the edge servers; based on each of the local scheduling parameters and a pre-configured distribution network scheduling model, it obtains initial global scheduling parameters; the distribution network scheduling model is established based on an objective function aimed at minimizing the total operating cost of the distribution network; for each of the edge servers, it performs an interactive iterative process based on the initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained, including: receiving the local optimization results obtained by each of the edge servers performing local optimization tasks based on the initial global scheduling parameters; The step of receiving the local optimization results obtained by each of the edge servers performing local optimization tasks based on initial global scheduling parameters includes: For a target edge server whose remaining computing resources do not support executing a local optimization task based on initial global scheduling parameters, the system receives a local optimization result sent by an outsourced computing object specified by the target edge server. The outsourced computing object obtains the local optimization result by receiving and executing the outsourced task sent by the target edge server. The outsourced task is encrypted and packaged by the target edge server using outsourced encryption technology. The outsourced computing object includes the cloud server and the edge server whose remaining computing resources support executing the local optimization task. The edge server is used to obtain local scheduling parameters based on a pre-configured microgrid scheduling model and send the local scheduling parameters to the cloud server; the microgrid scheduling model is established based on an objective function aimed at minimizing the total operating cost of the microgrid; an interactive iterative process is performed based on initial global scheduling parameters and a distributed optimization algorithm until the optimal global scheduling parameters are obtained, including: performing local optimization tasks based on the initial global scheduling parameters to obtain local optimization results; The process of performing a local optimization task based on initial global scheduling parameters to obtain local optimization results includes: If the remaining computing resources do not support the execution of the local optimization task based on the initial global scheduling parameters, the local optimization task is encrypted and packaged using outsourcing encryption technology to obtain an outsourced task; the outsourced task is sent to any outsourced computing object, so that the outsourced computing object executes the outsourced task to obtain the local optimization result, and sends the local optimization result to the cloud server; the outsourced computing object includes: the cloud server and the edge server whose remaining computing resources support the execution of the local optimization task.

Images