Distributed power supply regulation and control method and system based on artificial fish swarm algorithm

Abstract

The invention discloses a distributed power supply regulation and control method and system based on an artificial fish swarm algorithm, and relates to the technical field of power distribution network electric energy dispatching, and the method comprises the steps: collecting the detailed data of each distributed power supply needing to be dispatched, and constructing a coal power fish swarm, a photovoltaic fish swarm, a wind power fish swarm and an energy storage fish swarm; performing fish school iteration by taking the required electric quantity as a target and the required time as a step length, and scheduling various electric energy to the target; when one demand target corresponds to a plurality of fish schools, triggering a predation rule, and screening out an optimal fish school to prey other fish schools by taking the generating capacity and the stability as judgment criteria; when the demand targets are saturated, but the number of the fish schools is not zero, triggering a parasitism rule, changing each fish school target, and parasitizing the energy storage fish schools; and after scheduling is completed, feedback information of the demand target is collected to carry out parameter adjustment on each fish school. According to the method, the predation rule and the parasitic rule are introduced, so that the traditional artificial fish swarm algorithm can better adapt to the distributed power supply, and the scheduling capability of unstable energy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution network dispatching, and in particular to a distributed power supply control method and system based on an artificial fish swarm algorithm. Background Art

[0002] In order to meet the needs of distributed new energy and large industrial load regulation, many scholars have conducted research in related fields, promoting the distribution network control mode from one-way source and load, planned scheduling, to multi-directional interaction, intelligent decision-making, and supporting the coordinated operation of massive dispersed objects of source, network, load and storage.

[0003] In today's environment, with the integration of distributed power sources such as wind power generation and photovoltaic power generation into the power grid, power distribution faces the following challenges in the field of distributed power generation regulation. The output of wind and solar energy is affected by weather conditions and seasonal changes, resulting in instability and unpredictability of power generation. This intermittency poses challenges to the load balance and supply and demand matching of the power grid. The large-scale access of distributed power sources may lead to rapid fluctuations in the load of the power grid, which requires the power grid dispatching system to have a rapid response capability to adapt to such fluctuations. Due to the volatility of distributed power output, the frequency regulation and peak regulation tasks of the power grid have become more complicated, and the traditional peak regulation method based on thermal power generation may not be able to meet the rapidly changing needs. The fluctuation of distributed power sources may affect the voltage and frequency stability of the power grid, and the power grid needs to take additional measures to maintain stability and reliability. In order to alleviate the impact of intermittency and volatility, it is necessary to rely more on energy storage systems and demand response strategies, which requires the development of efficient energy storage technology and flexible demand management mechanisms.

[0004] The purpose of the present invention is to dispatch electric energy based on an artificial fish school algorithm. However, since the traditional artificial fish school algorithm cannot fit the distribution network in today's environment, predation rules and parasitic rules are introduced to optimize the algorithm to achieve electric energy dispatch. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is that due to the volatility of the output of distributed power sources, the power dispatching task of the power grid becomes more complicated, and the traditional dispatching method based mainly on thermal power generation may not be able to meet the rapidly changing needs.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a distributed power supply control method based on an artificial fish school algorithm, comprising: collecting detailed data of each distributed power supply to be scheduled, constructing a coal-fired power fish school, a photovoltaic fish school, a wind power fish school and an energy storage fish school based on the artificial fish school algorithm; taking the required power as the target, the required time as the step length, and the power generation of various fish schools as the power source, performing fish school iteration, and scheduling various types of electric energy to the required operation location; when congestion occurs, that is, when one demand target corresponds to multiple fish schools, triggering a predation rule, using power generation and stability as judgment criteria, screening out the optimal fish school to prey on other fish schools, and eliminating traces of iterative steps of other fish schools; when saturation occurs, that is, the demand target is saturated, but the number of fish schools is not zero, triggering a parasitic rule, changing the target of each fish school to an energy storage fish school, and parasitizing the energy storage fish school; after the scheduling is completed, collecting feedback information of the demand target to adjust the parameters of each fish school.

[0008] As a preferred solution of the distributed power supply control method based on artificial fish school algorithm described in the present invention, the distributed power supply detailed data includes photovoltaic panel area, daily radiation intensity change prediction curve and photovoltaic panel conversion efficiency; air density, blade swept area, average wind speed and wind turbine conversion efficiency at the wind power plant; coal consumption per unit time, coal low calorific value and coal power plant conversion efficiency; charging efficiency, discharge efficiency and discharge amount per unit time of energy storage device.

[0009] As a preferred solution of the distributed power supply control method based on artificial fish school algorithm described in the present invention, the coal-fired power fish school is represented as: ; in, It represents the next moving point of the coal-fired fish school. It means that the initial position of the coal-fired fish school is 0. Expressed as coal consumption per unit time, Expressed as the lower calorific value of coal, It is expressed as the power demand time, Expressed as the conversion efficiency of coal-fired power plants, It is expressed as the power demand of any target within the fish school observation range. is represented by the current power of the corresponding target; the photovoltaic fish school is represented by, ; in, It represents the next moving point of the photovoltaic fish school. It means that the initial position of the photovoltaic fish school is 0. Expressed as the photovoltaic panel area, Expressed as The average radiation intensity over time, It is expressed as the power demand time, Expressed as the photovoltaic panel conversion efficiency, It is expressed as the power demand of any target within the fish school observation range. is represented by the current power of the corresponding target; the wind-powered fish school is represented by, ; in, It represents the next moving point of the wind-powered fish school. Indicates that the initial position of the wind-driven fish school is 0. Expressed as air density, is expressed as the blade swept area, Expressed as the average wind speed, It is expressed as the wind turbine conversion efficiency; the energy storage fish school is expressed as, ; in, It represents the next moving point of the energy storage fish school. It means that the current position of the energy storage fish school is initially 0. Indicates the discharge amount of the energy storage device per unit time, It is represented by the current storage capacity of the energy storage device. It means that if the value in the brackets is greater than or equal to 0, it takes 1, otherwise it takes 0. Expressed as the discharge efficiency of the energy storage device.

[0010] As a preferred solution of the distributed power control method based on artificial fish swarm algorithm described in the present invention, the predation rule includes: when congestion occurs, the power generation and stability As the criterion, the best fish group is selected as follows: ; in, It means taking the two largest sets of data in the array. is represented as the set of power generation, They represent the power generation of coal-fired power, photovoltaic power, wind power, and energy storage corresponding to different individuals in the same population, and the rest are marked with subscripts The parameters are expressed as parameter data corresponding to different individuals; the stability Including coal power stability , Photovoltaic stability , Wind power stability and energy storage stability , expressed as, ; in, It is expressed as the actual coal supply of the day under the individual. It is expressed as the target coal supply for the day under the individual. Expressed as the power demand time conduct equal parts, Represented as a prediction curve based on irradiation intensity change The radiation intensity at the time, Represented as a random number between 0 and 1.

[0011] As a preferred solution of the distributed power supply control method based on artificial fish swarm algorithm described in the present invention, wherein: the predation rule also includes: Loading Stability Collection In, according to The population categories and individuals in the algorithm are used to calculate the corresponding stability results, and the smallest one is recorded as stability. , expressed as, ; According to the final and Perform screening predation, expressed as, ; in, Expressed as Population The final position of the individual, Expressed as Population The current location of the individual, Expressed as Population The previous position of the individual.

[0012] As a preferred solution of the distributed power control method based on artificial fish school algorithm described in the present invention, the parasitic rule includes: when the demand target is saturated, but there are still fish schools that need to be iterated, the parasitic rule is triggered, the energy storage fish school is used as the host fish, and other fish schools are used as parasitic fish, and the iteration target of the parasitic fish is changed, and the target is changed to the energy storage fish school, which is expressed as: ; in, Expressed as The individual power demand, Expressed as The maximum power storage capacity of an individual Expressed as The current charge level of the entity.

[0013] As a preferred solution of the distributed power control method based on artificial fish school algorithm described in the present invention, the parameter adjustment of each fish school includes collecting feedback information of the demand target after the scheduling is completed. If the feedback information is suitable, the process is terminated. If it is not suitable, the following process is performed. In the case of coal-fired power, when the feedback information is that the scheduling power is too large to cause redundancy, the actual coal consumption per unit time of the scheduling source is obtained and the pre-collected For comparison, if the actual coal consumption is greater than then Update, more actual coal consumption per unit time, if the actual coal consumption is less than or equal to The actual efficiency is calculated based on the redundant power. When the feedback information is that the dispatched power is too low to cause a deficit, the actual efficiency is calculated based on the deficit power. In the case of photovoltaics, when the feedback information is that the dispatched power is too large to cause redundancy, the actual irradiation intensity change prediction curve of the dispatched source is obtained and compared with the pre-collected irradiation intensity change prediction curve. If the actual average irradiation is greater than The process ends if the actual average irradiation is less than or equal to The actual efficiency is calculated based on the redundant power. Increase and update; when the feedback information is that the dispatched power is too low to cause a deficit, if the actual average irradiation is greater than or equal to then If the actual average irradiance is less than The process ends; in the case of wind power, when the feedback information is that the dispatched power is too large to cause redundancy, the actual wind speed of the dispatched source is obtained and compared with the pre-collected wind speed. If the actual wind speed is greater than The process ends if the actual wind speed is less than or equal to The actual efficiency is calculated based on the redundant power. Increase the update; when the feedback information is that the dispatch power is too low to cause a deficit, if the actual wind speed is greater than or equal to then If the actual average irradiance is less than The process ends; in the case of energy storage, when the feedback information is that the dispatched power is too large to cause redundancy, the actual efficiency is calculated based on the redundant power. When the feedback information is that the dispatched power is too low to cause a deficit, the actual efficiency is calculated based on the deficit power. Perform a reduction update.

[0014] Another object of the present invention is to provide a distributed power supply control system based on an artificial fish school algorithm, which can construct a fish school model according to the collected data, schedule electric energy through model iteration, and adjust model parameters according to feedback after scheduling.

[0015] In order to solve the above technical problems, the present invention provides the following technical solutions: a system for a distributed power supply control method based on an artificial fish school algorithm, comprising: a model building module, a model running module, an event processing module and a correction module; the model building module is used to collect data and build a fish school model, collect detailed data of each distributed power supply to be scheduled, and build a coal-fired power fish school, a photovoltaic fish school, a wind power fish school and an energy storage fish school based on the artificial fish school algorithm; the model running module is used to iterate the model, take the demand power as the target, the demand time as the step length, and the power generation of various fish schools as the power source, perform fish school iteration, and schedule various types of electric energy to The required operation place; the event processing module is used to handle the phenomena occurring in the iteration. When congestion occurs, that is, one demand target corresponds to multiple fish schools, the predation rule is triggered, and the power generation and stability are used as the judgment criteria to screen out the best fish school to prey on other fish schools, eliminating the traces of the iterative steps of other fish schools; when saturation occurs, that is, the demand target is saturated, but the number of fish schools is not zero, the parasitic rule is triggered, and the target of each fish school is changed to an energy storage fish school, which parasitizes the energy storage fish school; the correction module is used to correct and adjust the model. After the scheduling is completed, the feedback information of the demand target is collected to adjust the parameters of each fish school.

[0016] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the distributed power supply control method based on the artificial fish school algorithm are implemented as described above.

[0017] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a distributed power supply control method based on an artificial fish swarm algorithm as described above.

[0018] The beneficial effects of the present invention are as follows: by introducing predation rules and parasitic rules, the present invention enables the traditional artificial fish school algorithm to better adapt to the volatility and intermittency of distributed power sources, thereby improving the scheduling capability of unstable energy sources.

[0019] The algorithm of the present invention can more effectively manage and balance the energy supply and demand in the power grid, especially in the face of rapid fluctuations when large-scale distributed power sources are connected, which helps to maintain the stability of the power grid. In the case of fluctuations in the output of distributed power sources, the optimized artificial fish swarm algorithm can quickly respond to changes in the power grid load and effectively cope with the complexity of frequency modulation and peak load regulation tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 This is a roadmap of a distributed power supply control method based on an artificial fish swarm algorithm in Example 1.

[0021] Figure 2 This is a module structure diagram of a distributed power supply control system based on artificial fish swarm algorithm in Example 3. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0024] Example 1 Reference Figure 1 , which is the first embodiment of the present invention, and which provides a distributed power supply control method based on an artificial fish swarm algorithm, including: Figure 1 As shown: Step 1: Collect detailed data of each distributed power source that needs to be dispatched, and build coal-fired power fish school, photovoltaic fish school, wind power fish school and energy storage fish school based on the artificial fish school algorithm.

[0025] The collected distributed power source details data include the photovoltaic panel area of ​​the photovoltaic power plant, the predicted curve of the radiation intensity change on the day and the photovoltaic panel conversion efficiency.

[0026] Air density at the wind farm, blade swept area, average wind speed and wind turbine conversion efficiency.

[0027] Coal consumption per unit time, lower calorific value of coal and conversion efficiency of coal-fired power plants.

[0028] The charging efficiency, discharging efficiency and discharge capacity per unit time of the energy storage device.

[0029] The coal-fired fish school is represented as: ; in, It represents the next moving point of the coal-fired fish school. It means that the initial position of the coal-fired fish school is 0. Expressed as coal consumption per unit time, Expressed as the lower calorific value of coal, It is expressed as the power demand time, Expressed as the conversion efficiency of coal-fired power plants, It is expressed as the power demand of any target within the fish school observation range. Represents the current power level of the corresponding target.

[0030] The photovoltaic fish school is constructed as follows: ; in, It represents the next moving point of the photovoltaic fish school. It means that the initial position of the photovoltaic fish school is 0. Expressed as the photovoltaic panel area, Expressed as The average radiation intensity over time, It is expressed as the power demand time, Expressed as the photovoltaic panel conversion efficiency, It is expressed as the power demand of any target within the fish school observation range. Represents the current power level of the corresponding target.

[0031] The wind-powered fish school is constructed as: ; in, It represents the next moving point of the wind-powered fish school. Indicates that the initial position of the wind-driven fish school is 0. Expressed as air density, is expressed as the blade swept area, Expressed as the average wind speed, Expressed as wind turbine conversion efficiency.

[0032] The energy storage fish school is represented by: ; in, It represents the next moving point of the energy storage fish school. It means that the current position of the energy storage fish school is initially 0. Indicates the discharge amount of the energy storage device per unit time, It is represented by the current storage capacity of the energy storage device. It means that if the value in the brackets is greater than or equal to 0, it takes 1, otherwise it takes 0. Expressed as the discharge efficiency of the energy storage device.

[0033] Step 2: Taking the required power as the target, the required time as the step length, and the power generation of various fish schools as the power source, perform fish school iteration and dispatch various types of electricity to the required operation locations.

[0034] Step 3: When congestion occurs, that is, when one demand target corresponds to multiple fish schools, the predation rule is triggered, and the power generation and stability are used as the judgment criteria to select the optimal fish school to prey on other fish schools and eliminate the traces of the iterative steps of other fish schools.

[0035] The hunting rules include that when crowding occurs, the power generation and stability As the criterion, the best fish group is selected as follows: ; in, It means taking the two largest sets of data in the array. is represented as the set of power generation, They represent the power generation of coal-fired power, photovoltaic power, wind power, and energy storage corresponding to different individuals in the same population, and the rest are marked with subscripts The parameters are represented as parameter data corresponding to different individuals.

[0036] The stability Including coal power stability , Photovoltaic stability , Wind power stability and energy storage stability , expressed as, ; in, It is expressed as the actual coal supply of the day under the individual. It is expressed as the target coal supply for the day under the individual. Expressed as the power demand time conduct equal parts, Represented as a prediction curve based on irradiation intensity change The radiation intensity at the time, Represented as a random number between 0 and 1.

[0037] Will get Loading Stability Collection In, according to The population categories and individuals in the algorithm are used to calculate the corresponding stability results, and the smallest one is recorded as stability. , expressed as, ; According to the final and Perform screening predation, expressed as, ; in, Expressed as Population The final position of the individual, Expressed as Population The current location of the individual, Expressed as Population The previous position of the individual.

[0038] In actual situations, after iteration, there are multiple types of energy that can be dispatched for the demand target. However, if all of them are dispatched, there will be serious power redundancy. The present invention introduces the predator rule power generation and stability As the evaluation criteria, we choose which type of energy to be dispatched as the final dispatch object. Wind power and photovoltaic power are clean energy sources that are environmentally friendly but have poor stability. Thermal power has good stability but causes great environmental pollution and does not conform to today's carbon neutrality strategy. Predator rules can be used for better dispatching. Predator rules can be used not only for dispatching between different types of energy, but also for dispatching different individuals of the same type of energy, because there will be multiple thermal power plants, photovoltaic power plants, etc. in reality.

[0039] Step 4: When saturation occurs, that is, the demand target is saturated, but the number of fish schools is not zero, the parasitic rule is triggered, and the targets of each fish school are changed to energy storage fish schools, and the energy storage fish schools are parasitized.

[0040] When the demand target is saturated, but there are still fish schools that need to be iterated, the parasitic rule is triggered, and the energy storage fish school is used as the host fish, and other fish schools are used as parasitic fish. The iteration target of the parasitic fish is changed, and the target is changed to the energy storage fish school, which is expressed as: ; in, Expressed as The individual power demand, Expressed as The maximum power storage capacity of an individual Expressed as The current charge level of the entity.

[0041] The parasitic rule of the present invention can dispatch the excess electricity to the energy storage device, thereby reducing the waste of electricity.

[0042] Step 5: After the scheduling is completed, collect feedback information of the required targets and adjust the parameters of each fish school.

[0043] After the scheduling is completed, the feedback information of the demand target is collected. If the feedback information is suitable, the process ends. If it is not suitable, the following process is carried out: Suitable means that the absolute value of the difference between the scheduled power and the required power is less than or equal to the threshold, and the state is suitable. The threshold is generally 30% of the required power, which can be adjusted according to the actual working conditions. Unsuitable means that the absolute value of the difference between the scheduled power and the required power is greater than the threshold, and the state is unsuitable. The redundancy and deficit phenomena in the following are respectively the state where the difference between the scheduled power and the required power is greater than the threshold and the state where the difference is less than or equal to the threshold.

[0044] In the case of coal-fired power, when the feedback information is that the dispatched power is too large to cause redundancy, the actual coal consumption per unit time of the dispatched source is obtained and the pre-collected For comparison, if the actual coal consumption is greater than then Update, more actual coal consumption per unit time, if the actual coal consumption is less than or equal to The actual efficiency is calculated based on the redundant power. Make an enlarged update.

[0045] When the feedback information is that the dispatched power is too low to cause a deficit, the actual efficiency is calculated based on the deficit power. Perform a reduction update.

[0046] In the case of photovoltaics, when the feedback information is that the dispatched power is too large to cause redundancy, the actual irradiance intensity change prediction curve of the dispatched source is obtained and compared with the pre-collected irradiance intensity change prediction curve. If the actual average irradiance is greater than The process ends if the actual average irradiation is less than or equal to The actual efficiency is calculated based on the redundant power. Make an enlarged update.

[0047] When the feedback information is that the dispatched power is too low to cause a deficit, if the actual average irradiation is greater than or equal to then If the actual average irradiance is less than The process ends.

[0048] In the case of wind power, when the feedback information is that the dispatched power is too large to cause redundancy, the actual wind speed of the dispatched source is obtained and compared with the pre-collected wind speed. If the actual wind speed is greater than The process ends if the actual wind speed is less than or equal to The actual efficiency is calculated based on the redundant power. Make an enlarged update.

[0049] When the feedback information is that the dispatched power is too low to cause a deficit, if the actual wind speed is greater than or equal to then If the actual average irradiance is less than The process ends.

[0050] In the case of energy storage, when the feedback information is that the dispatched power is too large to cause redundancy, the actual efficiency is calculated based on the redundant power. Make an enlarged update.

[0051] When the feedback information is that the dispatched power is too low to cause a deficit, the actual efficiency is calculated based on the deficit power. Perform a reduction update.

[0052] Example 2 The second embodiment of the present invention is different from the first embodiment in that a distributed power supply control method based on an artificial fish school algorithm also includes: in order to verify and illustrate the technical effects adopted in this method, this embodiment compares the test results by means of scientific demonstration to verify the real effect of this method.

[0053] City A is currently in need of circuit maintenance, and a 5-hour power outage is expected until 6 p.m. The power required is 2,000,000 kWh. The parameter data of each power plant are collected as shown in Table 1: Table 1 Parameter data table

[0054] Based on the above data, we construct coal-fired power schools, photovoltaic schools, wind power schools and energy storage schools, with a demand of 2,000,000 kWh as the target, a step of 5 hours, and the power generated by each power plant as the driving force for iteration. Now City A has 500,000 kwh of spare energy, so the initial , coal-fired power plants have no stored electricity, so the initial electricity is 0.

[0055] Substitute the data into the coal-fired fish school for iteration, ; Convert the MJ unit in the coal-fired power fish school to kwh to get the position of the next step .

[0056] Substitute the data into the photovoltaic fish school for iteration. The photovoltaic power plant has no stored electricity, so the initial electricity is 0, ; Get the next step location .

[0057] Substitute the data into the wind fish school for iteration. The wind farm already has 400,000 kwh of electricity, so the initial electricity is 400000.

[0058] ; Get the next step location .

[0059] Substitute the data into the energy storage fish school for iteration, ; Get the next step location .

[0060] According to the next step position obtained above, it can be seen that the coal-fired fish school, photovoltaic fish school, wind power fish school, and energy storage fish school all meet the requirements and iterate towards the target. At this time, there is crowding, which triggers the predation rule.

[0061] Calculate , ; according to get .

[0062] Calculate According to the collected data, ; because so .

[0063] Calculate , ; Since the scheduling time is in the afternoon, the afternoon time period of the photovoltaic radiation intensity change prediction curve is intercepted for calculation. .

[0064] according to get , and finally the coal-fired power plant will be selected as the final dispatch object based on screening and predation.

[0065] After the coal-fired power is dispatched, although the target demand is met, the wind power fish school and the photovoltaic fish school still exist and continue to generate electricity. If no operation is performed, electricity will be wasted. At this time, the parasitic rule is triggered, and the energy storage fish school is used as the host fish, and other fish schools are used as parasitic fish. The iteration target of the parasitic fish is changed, and the target is changed to the energy storage fish school, which is expressed as, ; It can be seen from this embodiment that the scheduling result of the method of the present invention meets the actual scheduling strategy, and the present invention can reduce the waste of electric energy through parasitic rules.

[0066] Example 3 Reference Figure 2 , which is the third embodiment of the present invention, and is different from the previous two embodiments in that: a system for a distributed power supply control method based on an artificial fish school algorithm, comprising a model building module, a model running module, an event processing module and a correction module; the model building module is used to collect data and build a fish school model, collect detailed data of each distributed power supply to be scheduled, and build a coal-fired power fish school, a photovoltaic fish school, a wind power fish school and an energy storage fish school based on the artificial fish school algorithm; the model running module is used to iterate the model, with the demand power as the target, the demand time as the step length, and the power generation of various fish schools as the power source, to iterate the fish school, and schedule various types of power. To the required operation location; the event processing module is used to handle phenomena occurring during iteration. When congestion occurs, that is, one demand target corresponds to multiple fish schools, the predation rule is triggered, and the power generation and stability are used as the judgment criteria to select the optimal fish school to prey on other fish schools and eliminate the traces of the iterative steps of other fish schools; when saturation occurs, that is, the demand target is saturated, but the number of fish schools is not zero, the parasitic rule is triggered, and the targets of each fish school are changed to energy storage fish schools, which parasitize the energy storage fish schools; the correction module is used to correct and adjust the model. After the scheduling is completed, the feedback information of the demand target is collected to adjust the parameters of each fish school.

[0067] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0068] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0069] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0070] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0071] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A distributed power control method based on artificial fish swarm algorithm, characterized by: include, Collect detailed data of each distributed power source that needs to be dispatched, and build coal-fired power fish schools, photovoltaic fish schools, wind power fish schools and energy storage fish schools based on the artificial fish school algorithm; Taking the power demand as the target, the demand time as the step length, and the power generation of various fish schools as the power source, the fish schools are iterated to dispatch various types of power to the required operation locations; When crowding occurs, that is, when one demand target corresponds to multiple fish schools, the predation rule is triggered, and the power generation and stability are used as the judgment criteria to select the best fish school to prey on other fish schools, eliminating the traces of the iterative steps of other fish schools; When saturation occurs, that is, the demand target is saturated, but the number of fish schools is not zero, the parasitic rule is triggered, and the target of each fish school is changed to energy storage fish school, and the energy storage fish school is parasitized; After the scheduling is completed, feedback information of the demand target is collected to adjust the parameters of each fish school.

2. The distributed power control method based on artificial fish swarm algorithm according to claim 1, characterized in that: The distributed power supply detailed data includes photovoltaic panel area, daily radiation intensity change prediction curve and photovoltaic panel conversion efficiency; Air density at the wind farm, blade swept area, average wind speed, and wind turbine conversion efficiency; Coal consumption per unit time, coal lower calorific value and coal power plant conversion efficiency; The charging efficiency, discharging efficiency and discharge capacity per unit time of the energy storage device.

3. The distributed power control method based on artificial fish swarm algorithm according to claim 2, characterized in that: The coal-fired fish swarm is represented by, ； in, It represents the next moving point of the coal-fired fish school. It means that the initial position of the coal-fired fish school is 0. Expressed as coal consumption per unit time, Expressed as the lower calorific value of coal, It is expressed as the power demand time, Expressed as the conversion efficiency of coal-fired power plants, It is expressed as the power demand of any target within the fish school observation range. Represented as the current power of the corresponding target; The photovoltaic fish swarm is represented as, ； in, It represents the next moving point of the photovoltaic fish school. It means that the initial position of the photovoltaic fish school is 0. Expressed as the photovoltaic panel area, Expressed as The average radiation intensity over time, It is expressed as the power demand time, Expressed as the photovoltaic panel conversion efficiency, It is expressed as the power demand of any target within the fish school observation range. Represented as the current power of the corresponding target; The wind-powered fish school is represented by, ； in, It represents the next moving point of the wind-powered fish school. Indicates that the current position of the wind-driven fish school is initially 0. Expressed as air density, is expressed as the blade swept area, Expressed as the average wind speed, Expressed as wind turbine conversion efficiency; The energy storage fish school is represented by: ； in, It represents the next moving point of the energy storage fish school. It means that the current position of the energy storage fish school is initially 0. Indicates the discharge amount of the energy storage device per unit time, It is represented by the current storage capacity of the energy storage device. It means that if the value in the brackets is greater than or equal to 0, it takes 1, otherwise it takes 0. Expressed as the discharge efficiency of the energy storage device.

4. The distributed power control method based on artificial fish swarm algorithm according to claim 3, characterized in that: The hunting rules include: when crowding occurs, the power generation and stability As the criterion, the best fish group is selected as follows: ； in, It means taking the two largest sets of data in the array. is represented as the set of power generation, They represent the power generation of coal-fired power, photovoltaic power, wind power, and energy storage corresponding to different individuals in the same population, and the rest are marked with subscripts The parameters are expressed as parameter data corresponding to different individuals; The stability Including coal power stability , Photovoltaic stability , Wind power stability and energy storage stability , expressed as, ； in, It is expressed as the actual coal supply of the day under the individual. It is expressed as the target coal supply for the day under the individual. Expressed as the power demand time conduct equal parts, Represented as a prediction curve based on irradiation intensity change The radiation intensity at the time, Represented as a random number between 0 and 1.

5. A distributed power control method based on artificial fish swarm algorithm as claimed in claim 4, characterized in that: The predation rule also includes: Loading Stability Collection In, according to The population categories and individuals in the algorithm are used to calculate the corresponding stability results, and the smallest one is recorded as stability. , expressed as, ； According to the final and Perform screening predation, expressed as, ； in, Expressed as Population The final position of the individual, Expressed as Population The current location of the individual, Expressed as Population The previous position of the individual.

6. A distributed power control method based on artificial fish swarm algorithm as claimed in claim 5, characterized in that: The parasitic rule includes that when the demand target is saturated but there are still fish schools that need to be iterated, the parasitic rule is triggered, the energy storage fish school is used as the host fish, and other fish schools are used as parasitic fish, and the iteration target of the parasitic fish is changed, and the target is changed to the energy storage fish school, which is expressed as: ； in, Expressed as The individual power demand, Expressed as The maximum power storage capacity of an individual Expressed as The current charge level of the entity.

7. A distributed power control method based on artificial fish swarm algorithm as claimed in claim 6, characterized in that: The parameter adjustment of each fish group includes collecting feedback information of the target after the scheduling is completed. If the feedback information is suitable, the process ends. If it is not suitable, the following process is performed: In the case of coal-fired power, when the feedback information is that the dispatched power is too large to cause redundancy, the actual coal consumption per unit time of the dispatched source is obtained and the pre-collected For comparison, if the actual coal consumption is greater than then Update, more actual coal consumption per unit time, if the actual coal consumption is less than or equal to The actual efficiency is calculated based on the redundant power. Perform enlargement and update; When the feedback information is that the dispatched power is too low to cause a deficit, the actual efficiency is calculated based on the deficit power. Perform a reduction update; In the case of photovoltaics, when the feedback information is that the dispatched power is too large to cause redundancy, the actual irradiance intensity change prediction curve of the dispatched source is obtained and compared with the pre-collected irradiance intensity change prediction curve. If the actual average irradiance is greater than The process ends if the actual average irradiation is less than or equal to The actual efficiency is calculated based on the redundant power. Perform enlargement and update; When the feedback information is that the dispatched power is too low to cause a deficit, if the actual average irradiation is greater than or equal to then Perform a reduction update if the actual average irradiance is less than Then the process ends; In the case of wind power, when the feedback information is that the dispatched power is too large to cause redundancy, the actual wind speed of the dispatched source is obtained and compared with the pre-collected wind speed. If the actual wind speed is greater than The process ends if the actual wind speed is less than or equal to The actual efficiency is calculated based on the redundant power. Perform enlargement and update; When the feedback information is that the dispatched power is too low to cause a deficit, if the actual wind speed is greater than or equal to then Perform a reduction update if the actual average irradiance is less than Then the process ends; In the case of energy storage, when the feedback information is that the dispatched power is too large to cause redundancy, the actual efficiency is calculated based on the redundant power. Perform enlargement and update; When the feedback information is that the dispatched power is too low to cause a deficit, the actual efficiency is calculated based on the deficit power. Perform a reduction update.

8. A system using a distributed power supply control method based on an artificial fish school algorithm as claimed in any one of claims 1 to 7, characterized in that: It includes model building module, model running module, event processing module and correction module; The model building module is used to collect data and build a fish school model, collect detailed data of each distributed power source to be scheduled, and build a coal-fired power fish school, a photovoltaic fish school, a wind power fish school and an energy storage fish school based on an artificial fish school algorithm; The model operation module is used to iterate the model, taking the required power as the target, the required time as the step length, and the power generation of various fish schools as the power source, to iterate the fish schools and dispatch various types of electric energy to the required operation location; The event processing module is used to process phenomena that occur during iteration. When congestion occurs, that is, one demand target corresponds to multiple fish schools, the predation rule is triggered, and the power generation and stability are used as the judgment criteria to select the best fish school to prey on other fish schools, eliminating the traces of the iteration steps of other fish schools; when saturation occurs, that is, the demand target is saturated, but the number of fish schools is not zero, the parasitic rule is triggered, and the target of each fish school is changed to an energy storage fish school, and the energy storage fish school is parasitized; The correction module is used to correct and adjust the parameters of the model. After the scheduling is completed, feedback information of the demand target is collected to adjust the parameters of each fish school.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a distributed power supply control method based on an artificial fish swarm algorithm according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a distributed power supply control method based on an artificial fish swarm algorithm according to any one of claims 1 to 7 are implemented.

Images