Thermal power plant SIS multi-agent scheduling method based on gravity model and related device

Abstract

The invention discloses a thermal power plant SIS multi-agent scheduling method based on a gravity model and a related device. The method comprises the steps of obtaining multi-dimensional vector index data of each agent in a thermal power plant SIS system; inputting the multi-dimensional vector index data of each agent into a trained agent dynamic gravitation scheduling model to screen out an agent group which can be executed and called; according to the method and the related device, dynamic coordination of multiple agents and tool calling optimization can be realized, and the problem solving efficiency in a complex industrial environment is improved.

Description

Technical Field

[0001] This invention belongs to the interdisciplinary field of artificial intelligence technology and power generation technology, and relates to a multi-agent scheduling method and related device for thermal power plants based on a gravity model. Background Technology

[0002] With the rapid development of the power industry, thermal power plants, as important energy supply facilities, have received widespread attention for their operational efficiency, safety, and economy. A modern thermal power plant is a complex, large-scale, multi-unit integrated system involving multiple key equipment such as boilers, steam turbines, generators, and desulfurization and denitrification devices. These subsystems must operate in coordination to achieve efficient and stable power production. Plant-level monitoring information systems (SIS) play a crucial role in equipment monitoring and economic analysis.

[0003] SIS systems can monitor equipment operating status and perform economic analysis based on historical data. However, traditional SIS systems have the following problems: 1) They lack flexible dynamic adjustment capabilities. Data analysis is mostly based on static models or fixed rules, making it difficult to adapt to dynamic changes in equipment operating conditions. This often leads to lag in optimization strategies and an inability to respond in real time to complex conditions such as load fluctuations and fuel quality changes; 2) They rely heavily on expert experience. Current analysis and decision-making processes heavily depend on the experience and knowledge of experts in specific fields. They lack intelligent and self-learning analysis iteration methods, making it difficult to achieve automated accumulation and transfer of knowledge, which limits the universality and scalability of the system; 3) They are difficult to integrate heterogeneous data from multiple sources. Thermal power plants have diverse data sources, including real-time sensor data, equipment logs, maintenance records, environmental parameters, etc., and the data formats and sampling frequencies vary. Traditional systems lack efficient data fusion mechanisms, making it difficult to achieve unified analysis and mining of multi-dimensional data, resulting in serious information silos; 4) Intelligent decision support is weak. Existing systems are mainly focused on monitoring and report generation, lacking in-depth optimization capabilities based on big data analysis and artificial intelligence, and are unable to provide operators with accurate fault warnings, energy efficiency optimization and scheduling decision support. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a multi-agent scheduling method and related device for thermal power plants based on a gravity model. This method and related device can realize dynamic coordination of multiple agents and optimization of tool calling, thereby improving the efficiency of problem solving in complex industrial environments.

[0005] To achieve the above objectives, this invention discloses a multi-agent scheduling method for SIS (System-Independent Synchronization) in thermal power plants based on a gravity model, comprising:

[0006] Acquire multidimensional vector index data of each agent in the SIS system of a thermal power plant;

[0007] The multidimensional vector index data of each agent is input into the trained agent dynamic gravity scheduling model to select the group of agents that can be executed and called.

[0008] The system invokes agents within a group of agents to control thermal power plants.

[0009] The further improvement of the SIS multi-agent scheduling method for thermal power plants based on the gravity model described in this invention lies in:

[0010] Furthermore, the multi-dimensional vector index data of the intelligent agent includes at least device type, numerical type, host type, economic indicator classification, statistical analysis type, fault anomaly and handling suggestion tendency.

[0011] Furthermore, in the agent dynamic gravity scheduling model, the gravity value F between object i and object j in each feature space is... ij for:

[0012]

[0013] Where G is the gravitational constant, R ij Let be the Euclidean distance between object i and object j, ε be a small numerical constant, α be the dynamic weights, and Ci be the scene factor.

[0014] Furthermore, the gravitational value F of each object in the intelligent agent dynamic gravity scheduling model i d for:

[0015]

[0016] in, F represents the weight values ​​in different feature spaces. i Let be the sum of all gravitational forces on object i in dimensional space.

[0017] Furthermore, the acceleration of object i in the aforementioned agent dynamic gravity scheduling model for:

[0018]

[0019] Furthermore, in the agent dynamic gravity scheduling model, the next velocity of object i... and location Based on the current speed Location and acceleration The calculation yielded that,

[0020]

[0021] Where ω is a random value within [0,1].

[0022] This invention discloses a multi-agent scheduling system (SIS) for thermal power plants based on a gravity model, comprising:

[0023] The acquisition module is used to acquire multi-dimensional vector index data of each agent in the SIS system of a thermal power plant;

[0024] The filtering module is used to input the multi-dimensional vector index data of each agent into the trained agent dynamic gravity scheduling model in order to filter out the group of agents that can be executed and called.

[0025] The calling module is used to call upon agents in a group of agents to control a thermal power plant.

[0026] Furthermore, the multi-dimensional vector index data of the intelligent agent includes at least device type, numerical type, host type, economic indicator classification, statistical analysis type, fault anomaly and handling suggestion tendency.

[0027] This invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the gravity model-based SIS multi-agent scheduling method for thermal power plants.

[0028] This invention discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the gravity-based SIS multi-agent scheduling method for thermal power plants.

[0029] The present invention has the following beneficial effects:

[0030] The gravity model-based multi-agent scheduling method and related devices for thermal power plants described in this invention input the multi-dimensional vector index data of each agent into the trained agent dynamic gravity scheduling model to select a group of agents that can be executed and invoked. This solves the technical bottlenecks of traditional SIS systems in dynamic adjustment, multi-source data fusion, and intelligent decision-making, thereby improving the overall operating efficiency and economy of thermal power plants. It can also be used in existing systems and actual plant-level operations to support the intelligent transformation and upgrading of the entire industry. Attached Figure Description

[0031] The accompanying drawings, which form part of this specification, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0032] Figure 1This is a system structure diagram of the present invention;

[0033] Figure 2 This is a business process diagram of the present invention;

[0034] Figure 3 This is a flowchart of the dynamic gravity scheduling model of the intelligent agent in this invention. Detailed Implementation

[0035] 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, not all, of the embodiments of the present invention. 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.

[0036] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0037] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0038] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this invention generally indicates that the preceding and following objects have an "or" relationship.

[0039] It should be understood that although terms such as first, second, third, etc., may be used in the embodiments of the present invention to describe the preset range, these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from one another. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0040] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0041] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0042] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0043] Example 1

[0044] refer to Figure 1 , Figure 2 and Figure 3 The SIS multi-agent scheduling method for thermal power plants based on a gravity model, as described in this invention, includes the following steps:

[0045] 1) Construct a dynamic gravity scheduling model for intelligent agents;

[0046] The specific process of step 1) is as follows:

[0047] 11) Obtain multi-dimensional vector index data of each agent according to the business scenario type, and set it as the gravity object index parameter. At the same time, set the object fitness threshold of the agent to determine the correlation evaluation between agents.

[0048] Specifically, the multi-dimensional vector indicators of the intelligent agent are the key dimensions and main parameters, such as device type, numerical type, host type, economic indicator classification, statistical analysis type, fault anomaly and handling suggestion tendency. The object fitness threshold is the allowable upper and lower range of fluctuation for each gravitational object indicator parameter. It can be set as a fixed value or as a percentage, matching the indicator parameter limit Max / Min, i.e., the maximum or minimum value.

[0049] Furthermore, an agent object fitness threshold can be set and used in conjunction with an inter-agent correlation evaluation metric. By aggregating agents that meet the threshold conditions, the number of gravity objects can be flexibly scaled to adapt to the differentiated needs for richness and computational efficiency in different environments. Agent objects are screened through problem object fitness threshold evaluation, and then further selected using the agent correlation metric.

[0050] The setting of multi-dimensional parameters of the intelligent agent is directly related to the requirements of actual business problems. In the economic analysis of the unit, economic indicator parameters and the quality of related prediction models are high-impact factors. In the safety analysis, high-impact and low-impact factor parameters are also included. The more impact factor parameters there are, the more adaptable the intelligent agent selected for dynamic scheduling will be to the needs.

[0051] 12) Based on business operation requirements, dynamically set the weights of different feature dimension parameters, and the sum of the weights of all dimension parameters is 1.

[0052] Specifically, the weight ω of the multidimensional feature parameters is equal to the sum of the weights of all dimensions, which is 1. Each parameter is treated as a calculation dimension during model iteration, but the importance of different dimensions varies. The weights are used to adjust the weight distribution of feature parameters under different business scenario requirements. For example, when prioritizing economic needs, the weight of economic indicator parameters can be manually adjusted to be higher.

[0053] 13) Set the running time range of the dynamic gravity model according to business needs and actual equipment execution status.

[0054] Specifically, the single iteration time Δt of the gravity model and the time θt to complete one dynamic scheduling operation are as follows: the main agent screening performance decreases with the increase of equipment operating pressure and also changes with the richness and tendency of demand characteristics. Setting the running time range of the dynamic gravity model can effectively lock different business demand scheduling actions within the same time range.

[0055] 14) Set the fitness threshold according to the multidimensional features required.

[0056] 15) Based on the actual needs of users, set typical scenarios for the output of the dynamic gravity scheduling model.

[0057] The typical scenarios described are typical operational cases provided by adapting to the characteristics of frequently occurring problems. The returned responses need to be generated through specific business scheduling based on the actual problem. This can provide users with commonly used question templates for the smart assistant, improve the problem targeting and system efficiency, and obtain answers that meet expectations and have practical significance.

[0058] 2) The execution process of the agent dynamic gravity scheduling model is as follows:

[0059] 21) After multidimensional extraction and mapping of the user problem feature vector, combined with step 11), perform iterative calculation of the gravity model between the problem object and the agent object, where the gravity value F in each feature space is... ij for:

[0060]

[0061] Where G is the gravitational constant, R ij Let ε be the Euclidean distance between object i and object j, α be a small numerical constant, β be dynamic weights that can be adaptively adjusted according to the complexity of the problem, and Ci be the scene factor that can take into account environmental factors.

[0062] 22) Based on the multidimensional feature gravity weight parameters set in step 12), the gravity values ​​in each feature space calculated in step 21) are weighted and summed to obtain the gravity value F of each object. i d for:

[0063]

[0064] in, F represents the weight values ​​in different feature spaces. i Let be the sum of all gravitational forces on object i in dimensional space.

[0065] The weighting parameters set in step 12) can reduce the number of forces involved in the resultant force calculation. By introducing the set KO of the top K objects with the optimal fitness value and the largest mass, some irrelevant objects are filtered out, highlighting the influence of the better individuals. The gravitational value F of each object after optimization is thus optimized. i d for:

[0066]

[0067] 23) Based on the gravitational values ​​of each object obtained in step 22), calculate the acceleration of object i according to the laws of motion. for:

[0068]

[0069] 24) The next velocity and position of object i can be determined based on its current velocity. Location and acceleration Calculations show that

[0070]

[0071] Where ω is a random value within [0,1].

[0072] After completing the above calculations and updates, the calculation and screening of the agent dynamic gravity scheduling model function can be continued iteratively. Once the fitness evaluation meets the threshold condition, a group of agents that can be executed and called can be selected.

[0073] 3) Based on the toolchain optimization three-level decision-making mechanism, when calling step 24) to select the intelligent agent group, provide multi-source fusion raw data, statistical analysis tools, model calculation functions and other tools for the specific business execution of each intelligent agent. Finally, integrate the output of each tool and fuse the intelligent agent's response to return a structured, rich, and easy-to-understand answer to the user.

[0074] Example 2

[0075] The gravity-based SIS multi-agent scheduling system for thermal power plants described in this invention includes:

[0076] The acquisition module is used to acquire multi-dimensional vector index data of each agent in the SIS system of a thermal power plant;

[0077] The filtering module is used to input the multi-dimensional vector index data of each agent into the trained agent dynamic gravity scheduling model in order to filter out the group of agents that can be executed and called.

[0078] The calling module is used to call upon agents in a group of agents to control a thermal power plant.

[0079] In this embodiment, the multi-dimensional vector index data of the intelligent agent includes at least device type, numerical type, host type, economic indicator classification, statistical analysis type, fault anomaly and handling suggestion tendency.

[0080] The module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0081] Example 3

[0082] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the gravity-based multi-agent scheduling method for a thermal power plant (SIS). For example, the steps include: acquiring multi-dimensional vector index data of each agent in the SIS system of the thermal power plant; inputting the multi-dimensional vector index data of each agent into a trained agent dynamic gravity scheduling model to filter out a group of agents available for execution; and calling agents from the agent group to perform thermal power plant control. The memory may include main memory, such as high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device. The processor, network interface, and memory are interconnected via an internal bus, which may be an industry-standard architecture bus, a peripheral component interconnection standard bus, an extended industry-standard architecture bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory stores the program; specifically, the program may include program code, which includes computer operation instructions. The memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0083] Example 4

[0084] A computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the gravity-based multi-agent scheduling method for thermal power plants (SIS). For example, the method includes: acquiring multi-dimensional vector index data of each agent in the thermal power plant SIS system; inputting the multi-dimensional vector index data of each agent into a trained agent dynamic gravity scheduling model to filter out a group of agents available for execution; and invoking agents in the agent group to perform thermal power plant control. Specifically, the computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include random access memory and / or cache memory, etc. The non-volatile memory may include read-only memory, hard disk, flash memory, optical disk, magnetic disk, etc.

[0085] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0086] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0087] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0089] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and disclosure of the invention. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0090] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

[0091] The above description is merely a preferred embodiment of the present invention and does not constitute any limitation on the present invention. Any simple modifications, alterations, or equivalent structural changes made to the above embodiments based on the technical essence of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A multi-agent scheduling method for SIS in a thermal power plant based on a gravity model, characterized in that, include: Acquire multidimensional vector index data of each agent in the SIS system of a thermal power plant; The multidimensional vector index data of each agent is input into the trained agent dynamic gravity scheduling model to select the group of agents that can be executed and called. The system invokes agents within a group of agents to control thermal power plants.

2. The SIS multi-agent scheduling method for thermal power plants based on a gravity model according to claim 1, characterized in that, The multidimensional vector index data of the intelligent agent includes at least the device type, numerical type, host type, economic indicator classification, statistical analysis type, fault anomaly and handling suggestion tendency.

3. The SIS multi-agent scheduling method for thermal power plants based on a gravity model according to claim 1, characterized in that, In the agent dynamic gravity scheduling model, the gravity value F between object i and object j in each feature space is... ij for: Where G is the gravitational constant, R ij Let be the Euclidean distance between object i and object j, ε be a small numerical constant, α be the dynamic weights, and Ci be the scene factor.

4. The SIS multi-agent scheduling method for thermal power plants based on a gravity model according to claim 3, characterized in that, The gravitational value F of each object in the agent dynamic gravity scheduling model i d for: in, F represents the weight values ​​in different feature spaces. i Let be the sum of all gravitational forces on object i in dimensional space.

5. The SIS multi-agent scheduling method for thermal power plants based on a gravity model according to claim 4, characterized in that, The acceleration of object i in the agent dynamic gravity scheduling model for:

6. The multi-agent scheduling method for thermal power plants based on a gravity model according to claim 5, characterized in that, The next velocity of object i in the agent dynamic gravity scheduling model and location Based on the current speed Location and acceleration The calculation yielded that, Where ω is a random value within [0,1].

7. A multi-agent scheduling system (SIS) for thermal power plants based on a gravity model, characterized in that, include: The acquisition module is used to acquire multi-dimensional vector index data of each agent in the SIS system of a thermal power plant; The filtering module is used to input the multi-dimensional vector index data of each agent into the trained agent dynamic gravity scheduling model in order to filter out the group of agents that can be executed and called. The calling module is used to call upon agents in a group of agents to control a thermal power plant.

8. The SIS multi-agent scheduling system for thermal power plants based on a gravity model according to claim 7, characterized in that, The multidimensional vector index data of the intelligent agent includes at least the device type, numerical type, host type, economic indicator classification, statistical analysis type, fault anomaly and handling suggestion tendency.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the SIS multi-agent scheduling method for thermal power plants based on the gravity model as described in any one of claims 1-6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the SIS multi-agent scheduling method for thermal power plants based on the gravity model as described in any one of claims 1-6.

Images