A multi-agent-based virtual power plant scheduling instruction rapid decomposition method

Abstract

The present application belongs to the technical field of virtual power plant instruction decomposition, and particularly relates to a kind of virtual power plant scheduling instruction fast decomposition method based on multi-agent.The present application can more flexibly cope with the change and demand fluctuation of power system, based on the historical data and current state of agent, calculates compensation value, ensures the reasonable distribution and optimized use of system resource, load and power, improves the overall operation efficiency of virtual power plant, through the setting of instruction decomposition level, the task allocation of agent can be dynamically adjusted according to the actual situation, avoids the overload of single agent, improves the execution efficiency of scheduling instruction, combined with current power data, high energy consumption tasks can be arranged preferentially when power is low, or power generation is reduced when power is high, reduces operating cost, improves economic benefit, uses the historical data of agent for compensation value calculation and decision-making, improves the scientificity and accuracy of scheduling instruction decomposition, reduces the influence of uncertain factors in scheduling process.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of virtual power plant instruction decomposition, and particularly relates to a multi-agent-based virtual power plant scheduling instruction rapid decomposition method. BACKGROUND

[0002] With the transformation of global energy structure and the rapid development of renewable energy, a virtual power plant is formed by integrating dispersed distributed energy, energy storage systems, controllable loads and other resources through advanced information communication technology and control technology, and forms a unified and coordinately controllable virtual power source. The virtual power plant can realize the optimization of energy scheduling, supply-demand balance and collaborative management, and improve the energy utilization efficiency and the stability of the power system. In the scheduling process of the virtual power plant, the decomposition of the scheduling instruction is one of the key links. The decomposition speed of the scheduling instruction directly affects the response speed and scheduling effect of the virtual power plant.

[0003] The traditional scheduling method usually relies on centralized optimization calculation. With the expansion of the virtual power plant and the increase of the number of distributed energy participating in, the complexity and calculation time of the centralized calculation increase significantly, and it is difficult to meet the requirements of real-time and high efficiency. In the scheduling instruction distribution process, the resource utilization is not balanced, some agents are over-loaded, and other agents are idle, resulting in the reduction of the overall system operation efficiency. SUMMARY

[0004] The purpose of the application is to provide a multi-agent-based virtual power plant scheduling instruction rapid decomposition method, which can effectively improve the operation efficiency and system stability of the virtual power plant by optimizing the decomposition and execution process of the scheduling instruction.

[0005] The technical solutions adopted by the application are as follows:

[0006] A multi-agent-based virtual power plant scheduling instruction rapid decomposition method comprises:

[0007] Obtaining scheduling instruction data in a virtual power plant, and obtaining a plurality of sub-instructions according to the scheduling instruction data;

[0008] Obtaining an agent for executing each sub-instruction;

[0009] Obtaining current power data of each agent;

[0010] Obtaining historical system resource usage data of each agent when executing the instruction, and obtaining a system resource compensation value according to the historical system resource usage data;

[0011] Obtaining historical load data of each agent, and obtaining a load compensation value according to the historical load data;

[0012] Obtaining power demand data and power generation capacity data of each agent, and obtaining power compensation value according to the power demand data and the power generation capacity data;

[0013] Obtaining an instruction decomposition level according to the current power data, the system resource compensation value, the load compensation value and the power compensation value;

[0014] Decomposing the scheduling instruction into a plurality of levels of sub-instructions according to the instruction decomposition level, and enabling the plurality of agents to execute the plurality of levels of sub-instructions corresponding to the decomposition in sequence.

[0015] In a preferred embodiment, the step of obtaining historical system resource usage data when each agent executes an instruction, and obtaining a system resource compensation value according to the historical system resource usage data, comprises:

[0016] Obtaining historical system resource usage data when each agent executes an instruction;

[0017] Obtaining a plurality of historical system resource usage rates, a number of historical system resource usage rates and a total number of historical system resource usage rates according to the historical system resource usage data;

[0018] Obtaining a standard system resource usage rate;

[0019] Calculating the system resource compensation value according to the plurality of historical system resource usage rates, the number of historical system resource usage rates, the total number of historical system resource usage rates and the standard system resource usage rate, wherein the calculation formula is:

[0020]

[0021] In the formula, C B represents the system resource compensation value, n represents the total number of historical system resource usage rates, i represents the number of historical system resource usage rates, C i represents the i-th historical system resource usage rate, C b represents the standard system resource usage rate.

[0022] In a preferred embodiment, the step of obtaining historical load data of each agent, and obtaining a load compensation value according to the historical load data, comprises:

[0023] Obtaining historical load data of each agent;

[0024] Obtaining a plurality of historical load values, a number of historical load values and a total number of historical load values according to the historical load data;

[0025] Calculating the load compensation value according to the plurality of historical load values, the number of historical load values and the total number of historical load values, wherein the calculation formula is:

[0026]

[0027] In the formula, P B is a load compensation value, x is a serial number of a historical load value, y is a total number of historical load values, P x is the xth historical load value, P x-1 is the (x-1)th historical load value.

[0028] In a preferred embodiment, the step of obtaining power demand data and power generation capacity data of each agent, and obtaining a power compensation value according to the power demand data and the power generation capacity data, comprises:

[0029] obtaining power demand data and power generation capacity data of each agent;

[0030] obtaining a plurality of power demand values, a total number of power demand values, and serial numbers of the power demand values according to the power demand data;

[0031] obtaining a plurality of power generation capacity values, a total number of power generation capacity values, and serial numbers of the power generation capacity values according to the power generation capacity data;

[0032] calculating the power compensation value according to the plurality of power demand values, the total number of power demand values, the serial numbers of the power demand values, the plurality of power generation capacity values, the total number of power generation capacity values, and the serial numbers of the power generation capacity values, wherein the calculation formula is:

[0033]

[0034] In the formula, D B is a power compensation value, f is a total number of power generation capacity values and a total number of power demand values, E g is the gth power demand value, A g is the gth power generation capacity value.

[0035] In a preferred embodiment, the step of obtaining a command decomposition level according to the current power data, the system resource compensation value, the load compensation value, and the power compensation value, comprises:

[0036] calculating a command decomposition value according to the current power data, the system resource compensation value, the load compensation value, and the power compensation value;

[0037] obtaining the command decomposition level according to the command decomposition value.

[0038] In a preferred embodiment, the step of calculating a command decomposition value according to the current power data, the system resource compensation value, the load compensation value, and the power compensation value, comprises:

[0039] obtaining a corresponding current power value according to the current power data;

[0040] calculating an instruction decomposition value according to the current power value, the system resource compensation value, the load compensation value and the power compensation value, wherein the calculation formula is:

[0041] Z=Y·C B ·P B ·D B ;

[0042] In the formula, Z represents the instruction decomposition value, Y represents the current power value, C B represents the system resource compensation value, P B represents the load compensation value, and D B represents the power compensation value.

[0043] In a preferred embodiment, the step of obtaining an instruction decomposition level according to the instruction decomposition value comprises:

[0044] obtaining an instruction level table, wherein the instruction level table comprises a plurality of instruction decomposition interval values and an instruction decomposition level corresponding to each instruction decomposition interval value;

[0045] obtaining a target instruction decomposition interval value according to the instruction decomposition value;

[0046] obtaining an instruction decomposition level from the instruction level table according to the target instruction decomposition interval value.

[0047] In a preferred embodiment, after the step of obtaining an instruction decomposition level from the instruction level table according to the target instruction decomposition interval value, the method further comprises:

[0048] obtaining a sub-instruction threshold number within the instruction decomposition level;

[0049] judging whether the number of sub-instructions within each instruction decomposition level exceeds the sub-instruction threshold number;

[0050] if the number of sub-instructions within the instruction decomposition level exceeds the sub-instruction threshold number, determining that the instruction decomposition level of the sub-instructions exceeds the normal execution number, marking the instruction decomposition level as exceeding, and issuing a warning message;

[0051] if the number of sub-instructions within the instruction decomposition level does not exceed the sub-instruction threshold number, determining that the instruction decomposition level of the sub-instructions is normal.

[0052] In a preferred embodiment, after the step of if the number of sub-instructions within the instruction decomposition level exceeds the sub-instruction threshold number, determining that the instruction decomposition level of the sub-instructions exceeds the normal execution number, marking the instruction decomposition level as exceeding, and issuing a warning message, the method further comprises:

[0053] constructing a level adjustment period;

[0054] acquiring the number of times that the same instruction decomposition level is marked as exceeding the instruction decomposition level in the instruction decomposition level adjustment period, and marking the same number of times of exceeding;

[0055] acquiring the same number of times of exceeding the threshold;

[0056] determining whether the same number of times of exceeding exceeds the threshold;

[0057] if the same number of times of exceeding exceeds the threshold, determining that the instruction decomposition interval value corresponding to the instruction decomposition level is abnormally divided, and re-dividing the instruction decomposition interval value corresponding to the instruction decomposition level;

[0058] if the same number of times of exceeding does not exceed the threshold, determining that the instruction decomposition interval value corresponding to the instruction decomposition level is normally divided.

[0059] And a multi-agent-based virtual power plant scheduling instruction rapid decomposition terminal, comprising:

[0060] one or more processors;

[0061] a storage device having one or more programs stored thereon;

[0062] When the one or more programs are executed by the one or more processors, the one or more processors implement the multi-agent-based virtual power plant scheduling instruction rapid decomposition method.

[0063] The technical effects obtained by the present application are:

[0064] The present application realizes rapid decomposition and execution of scheduling instructions through the cooperative work of multiple agents, can more flexibly cope with changes and demand fluctuations of the power system, calculates compensation values based on historical data and current states of the agents, ensures the reasonable allocation and optimized use of system resources, loads and power, improves the overall operation efficiency of the virtual power plant, dynamically adjusts the task allocation of the agents according to actual conditions through the setting of instruction decomposition levels, avoids the overload of a single agent, improves the execution efficiency of scheduling instructions, can prioritize high-energy-consuming tasks when power is low or reduce power generation when power is high, reduces operating costs and improves economic benefits, uses historical data of the agents for compensation value calculation and decision-making, improves the scientificity and accuracy of scheduling instruction decomposition, and reduces the influence of uncertain factors in the scheduling process. BRIEF DESCRIPTION OF DRAWINGS

[0065] Figure 1 is the method flowchart provided by the present application. DETAILED DESCRIPTION

[0066] In order to make the above objectives, characteristics and advantages of the present application more obvious and comprehensible, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0067] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application, however, can be practiced in a variety of ways beyond the specific embodiments described herein without departing from the scope of the present application, which is set forth with particularity in the claims. Implementations of the present application can be implemented using any combination of hardware, firmware, or software. Implementations of the present application can also be implemented using modules depending on the implementation of certain aspects of the present application. Software can comprise single or multi-threaded applications. Software can implement one or more threads of execution in one or more separate processes each of which can create one or more threads of execution to operate in a multithreaded environment.

[0068] Second, the term "one embodiment" or "an embodiment" as used herein means that a particular implementation can include a particular feature, structure, or characteristic, but every embodiment can not necessarily include the particular feature, structure, or characteristic. Furthermore, the following claims use the term "comprising" to mean "including, but not limited to," and thus should not be interpreted to be limiting of the aspects of the application. Additionally, the term "coupled" is used herein to express a relationship between or among multiple elements. Such a relationship can be a direct connection between elements, or an indirect connection between elements through one or more other elements.

[0069] Third, the present application is described in detail with reference to the accompanying drawings. In the detailed description of the embodiments of the present application, the accompanying drawings are only examples, and should not limit the scope of protection of the present application.

[0070] Please refer to the accompanying drawings Figure 1 As shown in the drawings, a multi-agent-based virtual power plant scheduling instruction rapid decomposition method is provided, which comprises the following steps:

[0071] S1, obtaining scheduling instruction data in a virtual power plant, and obtaining a plurality of sub-instructions according to the scheduling instruction data;

[0072] S2, obtaining an agent for executing each sub-instruction;

[0073] S3, obtaining current power data of each agent;

[0074] S4, obtaining historical system resource usage data of each agent when executing the instruction, and obtaining a system resource compensation value according to the historical system resource usage data;

[0075] S5, obtaining historical load data of each agent, and obtaining a load compensation value according to the historical load data;

[0076] S6, obtaining power demand data and power generation capacity data of each agent, and obtaining a power compensation value according to the power demand data and the power generation capacity data;

[0077] S7, obtaining an instruction decomposition level according to the current power data, the system resource compensation value, the load compensation value, and the power compensation value;

[0078] S8, decomposing the scheduling instruction into a plurality of levels of sub-instructions according to the instruction decomposition level, and making the plurality of agents execute the plurality of levels of sub-instructions corresponding to the decomposition in turn according to the instruction decomposition level.

[0079] As in the above steps S1 to S8, the scheduling instruction data in the virtual power plant generally includes an overall power scheduling plan, by analyzing these scheduling instructions, it is decomposed into a plurality of specific sub-instructions, each sub-instruction corresponds to a different task, such as power generation, load adjustment, etc. Each agent in the virtual power plant can be one or a combination of power equipment, power generation unit, load unit, obtain the agent executing each sub-instruction, and collect their current power data, historical system resource usage data, historical load data, power demand data and power generation capacity data, calculate the system resource compensation value according to the historical system resource usage data of the agent when executing the instruction (such as CPU, memory, bandwidth, etc.), evaluate its execution ability and consumption, calculate the load compensation value according to the historical load data of the agent (such as power load curve, etc.), evaluate its load response ability, calculate the power compensation value according to the power demand data and power generation capacity data of the agent, evaluate its power supply and demand balance ability, combine the current power data, system resource compensation value, load compensation value and power compensation value, and comprehensively evaluate the execution ability of each agent, determine the instruction decomposition level, decompose the scheduling instruction into a plurality of levels of sub-instructions according to the determined instruction decomposition level, and assign them to each agent for execution according to the priority and execution ability, through the cooperation of multiple agents, the scheduling instruction is quickly decomposed and executed, which can more flexibly cope with the changes and demand fluctuations of the power system, based on the historical data and current state of the agent, the compensation value is calculated to ensure the reasonable allocation and optimized use of system resources, load and power, improve the overall operation efficiency of the virtual power plant, through the setting of instruction decomposition level, the task allocation of the agent can be dynamically adjusted according to the actual situation, avoid single agent overload, improve the execution efficiency of the scheduling instruction, combined with the current power data, high energy-consuming tasks can be arranged in priority when the power is low, or the power generation capacity is reduced when the power is high, reduce the operating cost and improve the economic benefit, use the historical data of the agent to calculate the compensation value and make decisions, improve the scientificity and accuracy of the scheduling instruction decomposition, and reduce the influence of uncertain factors in the scheduling process.

[0080] In a specific embodiment, the step of obtaining the historical system resource usage data of each agent when executing the instruction, and obtaining the system resource compensation value according to the historical system resource usage data, comprises:

[0081] S401, obtaining the historical system resource usage data of each agent when executing the instruction;

[0082] S402, obtaining a plurality of historical system resource usage rates, the number of historical system resource usage rates and the total number of historical system resource usage rates corresponding to the historical system resource usage data;

[0083] S403, acquire a standard system resource usage rate;

[0084] S404, calculate a system resource compensation value according to the multiple historical system resource usage rates, the number of historical system resource usage rates, the total number of historical system resource usage rates, and the standard system resource usage rate, wherein the calculation formula is:

[0085]

[0086] In the formula, C B is the system resource compensation value, n is the total number of historical system resource usage rates, i is the number of historical system resource usage rates, C i is the i-th historical system resource usage rate, C b is the standard system resource usage rate.

[0087] As in the above steps S401 to S404, each agent consumes certain system resources such as CPU, memory, bandwidth, etc. when executing instructions, and the resource usage data of these agents in the past when executing similar instructions needs to be collected for analysis and evaluation. From the historical data obtained, multiple historical system resource usage rates are extracted, such as CPU usage rate, memory usage rate, etc. of the agent within a certain period of time, and the number and total number of these historical system resource usage rates are recorded for subsequent calculation and analysis. The standard system resource usage rate is a pre-set benchmark value for evaluating the resource usage efficiency of the agent. This standard value can be based on industry standards, device performance indicators or system administrator settings. According to the multiple historical system resource usage rates, their number and total number, and the standard system resource usage rate, the system resource compensation value is calculated. By analyzing the historical system resource usage data of the agent in detail, the resource consumption of the agent in executing different tasks can be accurately evaluated, which helps to more accurately allocate and schedule instructions, avoiding resource waste and overload. The calculation of the system resource compensation value takes into account the difference between the historical usage rate and the standard usage rate, which can dynamically adjust the task allocation of the agent. By understanding the resource usage history and current state of each agent, possible resource bottlenecks can be predicted and measures can be taken in advance. Using historical data for calculation and decision-making reduces the influence of subjective factors in the scheduling process, improves the scientificity and objectivity of decision-making, and reasonably allocates and uses system resources, which can reduce operating costs and improve economic benefits. For example, by balancing the load of each agent, reducing resource consumption during peak periods, and reducing energy costs, the virtual power plant can better adapt to environmental changes and demand fluctuations. This flexibility enables the virtual power plant to better cope with uncertainty, improve response speed and adaptability.

[0088] In a specific embodiment, the step of acquiring historical load data of each agent and obtaining a load compensation value according to the historical load data comprises:

[0089] S501, obtaining historical load data of each agent;

[0090] S502, obtaining a plurality of historical load values, a number of historical load values and a total number of historical load values according to the historical load data;

[0091] S503, calculating a load compensation value according to the plurality of historical load values, the number of historical load values and the total number of historical load values, wherein the calculation formula is:

[0092]

[0093] In the formula, P B is the load compensation value, x is the number of historical load values, y is the total number of historical load values, P x is the xth historical load value, P x-1 is the x-1th historical load value.

[0094] As in the above steps S501 to S503, each agent has its load data recorded in the past operation process, these data reflect the load conditions of the agent at different time periods, including power demand, output, etc. These historical load data need to be collected for further analysis and calculation. A plurality of specific historical load values are extracted from the obtained historical load data, which can represent the load conditions of the agent at different time points. The number and total number of these historical load values are recorded for subsequent statistical analysis and calculation. According to the extracted plurality of historical load values and their number and total number, the load compensation value is calculated. Through detailed analysis of the historical load data of the agent, its response capability under different load conditions can be accurately evaluated, which helps to more reasonably allocate and dispatch instructions to ensure stable operation of the power system. The calculation of the load compensation value takes into account the historical changes of the load data, which can dynamically adjust the dispatching strategy according to the load characteristics of the agent. By analyzing the historical load data, the load fluctuations that may occur when the agent executes the instructions can be predicted, and measures can be taken in advance to compensate. Using historical load data for calculation and decision-making reduces the influence of subjective factors in the dispatching process, improves the scientificity and objectivity of decision-making, and data-driven decision-making can better reflect the actual situation, thereby optimizing the dispatching effect. By reasonably allocating and using load resources, the operation cost can be reduced and the economic benefit can be improved, for example, by balancing the load of each agent, reducing resource consumption during peak periods and reducing energy costs.

[0095] In a specific embodiment, the step of obtaining power demand data and power generation capability data of each agent and obtaining power compensation value according to the power demand data and the power generation capability data comprises:

[0096] S601, acquire power demand data and power generation capacity data of each agent;

[0097] S602, acquire a plurality of power demand values, a total number of power demand values and a number of power demand values according to the power demand data;

[0098] S603, acquire a plurality of power generation capacity values, a total number of power generation capacity values and a number of power generation capacity values according to the power generation capacity data;

[0099] S604, calculate power compensation values according to the plurality of power demand values, the total number of power demand values, the number of power demand values, the plurality of power generation capacity values, the total number of power generation capacity values and the number of power generation capacity values, wherein the calculation formula is:

[0100]

[0101] In the formula, D B is the power compensation value, f is the total number of power generation capacity values and the total number of power demand values, E g is the gth power demand value, A g is the gth power generation capacity value.

[0102] As in the above steps S601 to S604, the power demand data and power generation capacity data of each agent are collected, which reflect the power demand amount of the agent at different time periods and its power generation capacity, a plurality of specific power demand values are extracted from the power demand data, and the number and total number of these demand values are recorded, which represent the power demand of the agent at different time points, a plurality of specific power generation capacity values are extracted from the power generation capacity data, and the number and total number of these power generation capacity values are recorded, which represent the power generation capacity of the agent at different time points, the power compensation values are calculated according to the extracted power demand values and power generation capacity values, by detailed analysis of the power demand and power generation capacity of each agent, the response capability of the agent under different load conditions can be more accurately evaluated, the calculation of the power compensation values takes into account the data of power demand and power generation capacity, and the power dispatching strategy can be dynamically adjusted according to the specific situation of the agent, the resource allocation is optimized, the influence of subjective factors is reduced, the scientificity and objectivity of the dispatching decision are improved, the allocation of dispatching instructions is flexibly adjusted, the environment changes and demand fluctuations are adapted, and reasonable allocation of power resources can reduce operating costs and improve economic benefits, for example, by balancing the power supply and demand of each agent, reducing power waste and overload problems during peak periods, reducing energy costs, by analyzing the power demand and power generation capacity data, future trends of power demand and power generation capacity can be predicted, and more scientific dispatching plans can be developed.

[0103] In a specific embodiment, the step of obtaining the instruction decomposition level according to the current power data, the system resource compensation value, the load compensation value and the power compensation value comprises:

[0104] S701, calculating an instruction decomposition value according to the current power data, the system resource compensation value, the load compensation value and the power compensation value;

[0105] S702, obtaining the instruction decomposition level according to the instruction decomposition value.

[0106] As in the above steps S701 to S702, the current power data, the system resource compensation value, the load compensation value and the power compensation value are collected, which reflect the current market environment and the resource consumption and response ability of each agent when executing the instruction, according to which an integrated instruction decomposition value is calculated, and the instruction decomposition level is determined according to the calculated instruction decomposition value. The instruction decomposition level can be divided into different levels according to the size of the decomposition value, and multiple thresholds can be set to divide the instruction decomposition value into different level intervals. Considering the current power and the resource usage of the agent, the scheduling instruction can be allocated more scientifically and reasonably, avoiding the decision deviation caused by a single factor. By calculating the instruction decomposition value and determining the decomposition level according to it, the agent with high resource use efficiency and low execution cost can be preferentially selected to execute the scheduling instruction, thereby optimizing the overall resource utilization efficiency. Combined with the current power data, the scheduling strategy can be dynamically adjusted to respond to market price changes in a timely manner, reduce operating costs and improve economic benefits. By comprehensively evaluating the load compensation value and the power compensation value of the agent, the load change and power demand can be better predicted and responded to. The setting of the instruction decomposition level makes it possible to flexibly adjust the execution order and priority of the scheduling instruction, adapt to different operating conditions and demand changes, and improve the flexibility and adaptability of scheduling.

[0107] In a specific embodiment, the step of calculating the instruction decomposition value according to the current power data, the system resource compensation value, the load compensation value and the power compensation value comprises:

[0108] S7011, obtaining a corresponding current power value according to the current power data;

[0109] S7012, calculating the instruction decomposition value according to the current power value, the system resource compensation value, the load compensation value and the power compensation value, wherein the calculation formula is:

[0110] Z=Y·C B ·P B ·D B ;

[0111] In the formula, Z represents the instruction decomposition value, Y represents the current power value, C B represents the system resource compensation value, P Bis expressed as a load compensation value, D B is expressed as a power compensation value.

[0112] As in the above steps S7011 to S7012, the current power data is obtained from the market data or the internal power market system, the current power reflects the supply and demand situation of the power market, and is an important reference data for scheduling decision-making. The corresponding current power value is calculated, which can be real-time power, hourly average power or power in other time periods. According to the current power value, the system resource compensation value, the load compensation value and the power compensation value, the comprehensive instruction decomposition value is calculated, which will be used to determine the priority of the agent executing the scheduling instruction. By comprehensively considering the current power data, the system resource compensation value, the load compensation value and the power compensation value, the execution ability and cost of each agent can be more comprehensively and accurately evaluated, and the reasonable allocation of scheduling instructions is ensured. The introduction of current power data can respond to the changes in the power market in time, prioritize scheduling high-energy-consuming tasks when the power is low, and reduce operating costs; when the power is high, unnecessary energy consumption is reduced, and economic benefits are improved. By calculating the comprehensive instruction decomposition value, the agent with high resource utilization efficiency and strong load response capability can be preferentially selected to execute the scheduling instruction, the resource allocation is optimized, and the overall operation efficiency is improved. The comprehensive consideration of the load compensation value and the power compensation value can better predict and respond to load fluctuations and power demand changes, avoid system failures caused by load exceeding the agent's ability range, and reduce subjective bias in scheduling decision-making through data-based calculation and analysis, improve the scientificity and objectivity of decision-making, and ensure that the scheduling strategy can truly reflect the system state and market conditions. According to the real-time power data and the compensation value of each agent, the allocation of scheduling instructions can be flexibly adjusted to adapt to the demand changes under different time periods and market conditions, and the flexibility and adaptability of scheduling are improved.

[0113] In one specific embodiment, the step of obtaining an instruction decomposition level according to the instruction decomposition value comprises:

[0114] S7021, obtaining an instruction level table, wherein the instruction level table comprises a plurality of instruction decomposition interval values and an instruction decomposition level corresponding to each instruction decomposition interval value;

[0115] S7022, obtaining a target instruction decomposition interval value according to the instruction decomposition value;

[0116] S7023, obtaining an instruction decomposition level from the instruction level table according to the target instruction decomposition interval value.

[0117] As in the above steps S7021 to S7023, the instruction level table is a pre-set reference table containing a plurality of instruction decomposition interval values and their corresponding instruction decomposition levels, each interval value represents a range, and each range corresponds to a specific level. The instruction decomposition level table can be set according to historical data and system optimization goals. According to the calculated instruction decomposition value, compare it with the decomposition interval value in the instruction level table to determine which interval the value belongs to. For example, if the instruction decomposition value is 15, it falls within the interval of 10-20. According to the target instruction decomposition interval value, find the corresponding instruction decomposition level from the instruction level table. By setting a detailed instruction level table, different instruction decomposition values can be managed in detail to ensure that the scheduling task allocation of each agent is more reasonable and accurate. The use of instruction level table can simplify the operation process when facing complex data calculation and decision-making, and facilitate the maintenance and update of scheduling strategy. Through the pre-set instruction decomposition interval value and the corresponding level, the scheduling priority of each agent can be quickly determined to improve the efficiency and response speed of scheduling decision-making. The instruction level table can be dynamically adjusted according to actual conditions to adapt to different market conditions and operating environments. The combination of instruction decomposition value and instruction level table ensures that scheduling decisions are based on scientific calculation and analysis results, reduces the influence of subjective factors, and improves the scientificity and rationality of decision-making.

[0118] In a specific embodiment, after the step of obtaining the instruction decomposition level from the instruction level table according to the target instruction decomposition interval value, the method further comprises:

[0119] S7024, obtaining the number of sub-instructions in the instruction decomposition level;

[0120] S7025, determining whether the number of sub-instructions in each instruction decomposition level exceeds the threshold number of sub-instructions;

[0121] If the number of sub-instructions in the instruction decomposition level exceeds the threshold number of sub-instructions, it is determined that the instruction decomposition level of the sub-instruction exceeds the normal execution number, marked as exceeding the instruction decomposition level, and an alarm information is issued;

[0122] If the number of sub-instructions in the instruction decomposition level does not exceed the threshold number of sub-instructions, it is determined that the instruction decomposition level of the sub-instruction is normal.

[0123] As described above in steps S7024 to S7025, a sub-instruction threshold number is set for each instruction decomposition level in advance, which represents the maximum number of sub-instructions that can be accommodated in each level under normal circumstances, which can be set based on historical data and operating experience of the system. For each instruction decomposition level, check the number of sub-instructions currently allocated to the level. If the number of sub-instructions in a certain level exceeds the preset threshold number, it is determined that the number of sub-instructions in this level exceeds the normal execution number, marked as exceeding the instruction decomposition level, and an alert message is issued. If the number of sub-instructions in a certain level does not exceed the preset threshold number, it is determined that the number of sub-instructions in this level is within the normal range. By setting the sub-instruction threshold and monitoring it in real time, it is possible to effectively avoid overload operation caused by excessive sub-instructions in a certain instruction decomposition level. When a certain instruction decomposition level exceeds the normal execution number, an alert message can be sent in time to remind the operation and maintenance personnel or system administrator to intervene. By monitoring the number of sub-instructions and setting the threshold, resources can be more reasonably allocated and scheduled to ensure balanced operation of each agent and avoid excessive use or waste of resources. Setting the sub-instruction threshold and monitoring it in real time helps to make scientific decisions based on actual operating conditions to ensure that the execution of scheduling instructions is within a controllable range, improving the scientificity and rationality of scheduling strategies. By setting the mark and alert message of exceeding the instruction decomposition level, an effective early warning mechanism is established to detect potential operational risks in advance and take preventive measures.

[0124] In a specific embodiment, after the step of determining that the number of sub-instructions in the instruction decomposition level exceeds the sub-instruction threshold number, marking the instruction decomposition level as exceeding the normal execution number, and issuing an alert message, the method further comprises:

[0125] S7026, constructing a level adjustment period;

[0126] S7027, obtaining the number of times a same instruction decomposition level is marked as exceeding the instruction decomposition level within the level adjustment period, and marking it as the same exceeding number;

[0127] S7028, obtaining the same exceeding threshold number;

[0128] S7029, determining whether the same exceeding number exceeds the same exceeding threshold number;

[0129] If the same exceeding number exceeds the same exceeding threshold number, it is determined that the instruction decomposition interval value corresponding to this instruction decomposition level is abnormal, and the instruction decomposition interval value corresponding to this instruction decomposition level is re-divided;

[0130] If the same exceeding number does not exceed the same exceeding threshold number, it is determined that the instruction decomposition interval value corresponding to this instruction decomposition level is normal.

[0131] As in the above steps S7026 to S7029, a fixed time period (for example, one day, half a day, or one hour) is determined as a level adjustment period, and during this period, the operation of the instruction decomposition level is continuously monitored and recorded. In each level adjustment period, the number of times that the same instruction decomposition level is marked as exceeding the instruction decomposition level is counted, which represents the frequency of the number of sub-instructions in the level exceeding the preset threshold in a period. A threshold is set to represent the allowed number of times that the same instruction decomposition level is marked as exceeding the instruction decomposition level in a level adjustment period. If the number of exceeding times exceeds the same exceeding threshold number of times, it is determined that the interval value division of the instruction decomposition level is abnormal, and re-division is performed. If it does not exceed, it is determined that the interval value division of the instruction decomposition level is normal. By monitoring the exceeding of the instruction decomposition level in the level adjustment period, the division of the instruction decomposition interval value can be dynamically adjusted and optimized to ensure its rationality and effectiveness. When a certain instruction decomposition level frequently exceeds the threshold, it can be identified and re-divided in time to avoid long-term unreasonable interval division leading to unstable operation of the system. By setting the adjustment period and the number of exceeding threshold times, automatic monitoring and adjustment can be performed to reduce human intervention, improve the efficiency and accuracy of scheduling management. At the same time, the establishment of the early warning mechanism can timely remind the system administrator to intervene and dynamically adjust the instruction decomposition interval value to ensure balanced distribution of the number of sub-instructions in each instruction decomposition level and avoid excessive concentration or dispersion of resources.

[0132] And a multi-agent-based virtual power plant scheduling instruction rapid decomposition terminal, comprising:

[0133] One or more processors;

[0134] A storage device having one or more programs stored thereon;

[0135] When the one or more programs are executed by the one or more processors, the one or more processors implement the multi-agent-based virtual power plant scheduling instruction rapid decomposition method.

[0136] The above only describes the preferred embodiments of the present application, and it should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should also be considered as the protection scope of the present application. The structures, devices and operation methods not specifically described and explained in the present application are implemented according to the conventional means in the art, unless otherwise specified and limited.

Claims

1. A method for quickly decomposing multi-agent based virtual power plant scheduling instructions, characterized in that, The method comprises the following steps: acquiring scheduling instruction data in a virtual power plant, and acquiring a plurality of sub-instructions according to the scheduling instruction data; acquiring an agent for executing each sub-instruction; acquiring current power data of each agent; acquiring historical system resource usage data of each agent when executing the instruction, and obtaining a system resource compensation value according to the historical system resource usage data; acquiring historical load data of each agent, and obtaining a load compensation value according to the historical load data; acquiring power demand data and power generation capacity data of each agent, and obtaining a power compensation value according to the power demand data and the power generation capacity data; obtaining an instruction decomposition level according to the current power data, the system resource compensation value, the load compensation value and the power compensation value; decomposing the scheduling instruction into a plurality of levels of sub-instructions according to the instruction decomposition level, and enabling the plurality of agents to execute the plurality of levels of sub-instructions corresponding to the decomposed sub-instructions in turn according to the instruction decomposition level; the step of obtaining the instruction decomposition level according to the current power data, the system resource compensation value, the load compensation value and the power compensation value comprises: calculating an instruction decomposition value according to the current power data, the system resource compensation value, the load compensation value and the power compensation value; obtaining the instruction decomposition level according to the instruction decomposition value; the step of calculating the instruction decomposition value according to the current power data, the system resource compensation value, the load compensation value and the power compensation value comprises: obtaining a corresponding current power value according to the current power data; calculating the instruction decomposition value according to the current power value, the system resource compensation value, the load compensation value and the power compensation value, wherein the calculation formula is: Z = Y · C B • P B • D B ; In the formula, Z represents a command resolution value, Y represents a current power value, C B represents a system resource compensation value, P B represents a load compensation value, D B represents a power compensation value; the step of obtaining the instruction decomposition level according to the instruction decomposition value comprises: obtaining an instruction level table, wherein the instruction level table comprises a plurality of instruction decomposition interval values and an instruction decomposition level corresponding to each instruction decomposition interval value; obtaining a target instruction decomposition interval value according to the instruction decomposition value; obtaining the instruction decomposition level from the instruction level table according to the target instruction decomposition interval value; the step of obtaining the instruction decomposition level from the instruction level table according to the target instruction decomposition interval value further comprises: obtaining a sub-instruction threshold number in the instruction decomposition level; judging whether the number of sub-instructions in each instruction decomposition level exceeds the sub-instruction threshold number; if the number of sub-instructions in the instruction decomposition level exceeds the sub-instruction threshold number, determining that the instruction decomposition level for executing the sub-instruction exceeds the normal execution number, marking it as an exceeding instruction decomposition level, and issuing a warning information; if the number of sub-instructions in the instruction decomposition level does not exceed the sub-instruction threshold number, determining that the instruction decomposition level for executing the sub-instruction is normal.

2. The multi-agent based virtual power plant dispatch instruction fast decomposition method according to claim 1, characterized in that, the step of acquiring the historical system resource usage data of each agent when executing the instruction, and obtaining the system resource compensation value according to the historical system resource usage data comprises: acquiring the historical system resource usage data of each agent when executing the instruction; acquiring a plurality of historical system resource usage rates, a number of the historical system resource usage rates and a total number of the historical system resource usage rates according to the historical system resource usage data; acquiring a standard system resource usage rate; The system resource compensation value is calculated according to the multiple historical system resource usage rates, the number of historical system resource usage rates, the total number of historical system resource usage rates and the standard system resource usage rate, wherein the calculation formula is: In the formula, C B is expressed as a system resource compensation value, n is expressed as a total number of historical system resource usage rates, i is expressed as a number of historical system resource usage rates, C i is expressed as the i-th historical system resource usage rate, C b is expressed as a standard system resource usage rate. 3.The multi-agent based virtual power plant dispatching instruction fast decomposition method of claim 1, wherein, The step of obtaining the historical load data of each agent and obtaining the load compensation value according to the historical load data comprises: Obtaining the historical load data of each agent; Obtaining the corresponding multiple historical load values, the number of historical load values and the total number of historical load values according to the historical load data; The load compensation value is calculated according to the multiple historical load values, the number of historical load values and the total number of historical load values, wherein the calculation formula is: In the formula, P B is expressed as a load compensation value, x is expressed as a number of historical load values, y is expressed as a total number of historical load values, P x is expressed as the xth historical load value, P x-1 is expressed as the x-1th historical load value.

4. The multi-agent based virtual power plant dispatch instruction fast decomposition method according to claim 1, characterized in that, The step of obtaining the power demand data and the power generation capacity data of each agent and obtaining the power compensation value according to the power demand data and the power generation capacity data comprises: Obtaining the power demand data and the power generation capacity data of each agent; Obtaining the corresponding multiple power demand values, the total number of power demand values and the number of power demand values according to the power demand data; Obtaining the corresponding multiple power generation capacity values, the total number of power generation capacity values and the number of power generation capacity values according to the power generation capacity data; The power compensation value is calculated according to the multiple power demand values, the total number of power demand values, the number of power demand values, the multiple power generation capacity values, the total number of power generation capacity values and the number of power generation capacity values, wherein the calculation formula is: In the formula, D B is expressed as a power compensation value, f is expressed as a total number of power generation capacity values and a total number of power demand values, E g is expressed as the gth power demand value, A g is expressed as the gth power generation capacity value.

5. The multi-agent based virtual power plant dispatch instruction fast decomposition method according to claim 1, characterized in that, The step of determining that the instruction decomposition level of the sub-instruction exceeds the normal execution number, marking the instruction decomposition level as exceeding and issuing a warning message further comprises: Building a level adjustment period; Obtaining the number of times that the same instruction decomposition level is marked as exceeding in the level adjustment period, and marking the number of times as the same exceeding number; Obtaining the same exceeding threshold number of times; Determining whether the same exceeding number of times exceeds the same exceeding threshold number of times; If the same exceeding number of times exceeds the same exceeding threshold number of times, it is determined that the instruction decomposition interval value corresponding to the instruction decomposition level is abnormally divided, and the instruction decomposition interval value corresponding to the instruction decomposition level is re-divided; If the same exceeding number of times does not exceed the same exceeding threshold number of times, it is determined that the instruction decomposition interval value corresponding to the instruction decomposition level is normally divided.

6. A multi-agent based virtual power plant dispatching instruction fast decomposition terminal, characterized in that, Comprise: One or more processors; Storage device, one or more programs are stored on the storage device; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for quickly decomposing the dispatching instruction of the multi-agent based virtual power plant according to any one of claims 1-5.

Images