New energy power generation network bionic intelligent supervision method and system

Abstract

The invention relates to a new energy power generation network bionic intelligent supervision method and system, and relates to the field of new energy power generation technology supervision and management. The method comprises the steps that at least two monitoring knowledge objects in the new energy power generation process are acquired, and an original collection data set is formed; initializing an original acquisition data set, and constructing an initial bionic intelligent data vector set in the new energy power generation process; whether an optimal solution exists in the initial bionic intelligent data vector set or not is judged, and if yes, the new energy power generation network is adjusted according to the optimal solution; and if not, providing a variation knowledge rule, iteratively updating the initial bionic intelligent data vector set through the variation knowledge rule to generate a variation bionic intelligent data vector set until an optimal solution of the variation bionic intelligent data vector set is screened out, and adjusting the new energy power generation network according to the optimal solution. Network supervision standardization and operation flow mobility are finally realized by using a bionic intelligent algorithm, and the management efficiency of new energy power generation technology supervision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of supervision and management of new energy power generation technology, and in particular to a bionic intelligent supervision method and system for a new energy power generation network. Background Art

[0002] The supervision of new energy power generation networks refers to the supervision of new energy power generation facilities and their related networks to ensure their safe, stable and efficient operation. The main goal of the supervision of new energy power generation networks is to prevent grid-connected safety accidents and ensure the overall safety of the power system. The supervision content involves network security management, equipment operation monitoring and maintenance, operation and control of power generation equipment, etc. It has the characteristics of wide distribution area of ​​stations, large computing scale and high safety level. The supervision of new energy power generation networks is of great significance to ensure the safe and stable operation of the power system. By strengthening the safety management of the network, we can effectively prevent grid-connected safety accidents and improve the overall safety and reliability of the power system. In addition, supervision can also promote technological innovation and the formulation and revision of network-related technical standards, and promote the progress and development of new energy power generation technology.

[0003] Traditional supervision of new energy power generation is mainly based on manual supervision, supplemented by electronic information technology. With the rapid development and continuous increase in installed capacity and operation and maintenance capacity, photovoltaic, wind power, and energy storage power stations are constantly exposing their differences from traditional power professionals.

[0004] The supervision of new energy power generation incorporates big data analysis technology to supervise real-time data. However, due to the low level of automation and intelligence, the data is complex and difficult to understand, and data communication is often difficult to analyze its faults and is not intuitive. There are problems such as the mobility, pluggability of modules, and bionic intelligence of related supervision equipment, which have long plagued the operation and maintenance of new energy power generation technology supervision and management. The stations are widely distributed, the cost of decentralized supervision and management is too high, and there is a lack of efficient and intelligent technical supervision methods. Summary of the invention

[0005] The first object of the present invention is to provide a bionic intelligent supervision method and system for a new energy power generation network to assist a digital and intelligent new energy technology supervision management system, realize supervision standardization and operation process mobility, and improve the efficiency of mobile and portable intelligent management of new energy power generation technology supervision.

[0006] In the first aspect, the bionic intelligent supervision method for a new energy power generation network provided by the present invention is realized by the following technical solutions:

[0007] A bionic intelligent supervision method for a new energy power generation network, comprising:

[0008] Acquire at least two monitoring knowledge objects of the renewable energy power generation process to form an original acquisition data set; the monitoring knowledge objects include state vector data of the renewable energy power generation process, communication request data required by the renewable energy power generation process, equipment control data of the renewable energy power generation process, and network configuration data of the renewable energy power generation process;

[0009] Initializing the original collected data set to construct an initial bionic intelligent data vector set of the new energy power generation process;

[0010] Determine whether the initial bionic intelligent data vector set has an optimal solution, and if so, adjust the new energy power generation network according to the optimal solution;

[0011] If not, provide variation knowledge rules, iteratively update the initial bionic intelligent data vector set through the variation knowledge rules to generate a variation bionic intelligent data vector set, until the optimal solution of the variation bionic intelligent data vector set is screened out, and adjust the new energy power generation network according to the optimal solution.

[0012] By adopting the above-mentioned technical solution, the bionic intelligent data vector set of the new energy power generation process is analyzed and screened, which can greatly improve the bionic intelligence and optimization solution capabilities of the new energy power generation technology supervision. Compared with the traditional supervision methods, it can effectively improve the intelligent management efficiency of the new energy power generation technology supervision.

[0013] A further technical solution is that the state vector data of the renewable energy power generation process includes voltage data, current data and fault data;

[0014] The communication request data includes fault notification request data, assistance request data, and result broadcast data;

[0015] The equipment control data of the new energy power generation process includes motor speed control data, PID control parameter feedback adjustment data, and equipment failure emergency processing data;

[0016] The network configuration data of the new energy power generation process includes network point-to-point communication configuration data, network blocking configuration data, network broadcast configuration data, and network security maintenance configuration data.

[0017] By adopting the above technical scheme, during the renewable energy power generation process, the voltage data, current data and fault data in the state vector data of the renewable energy power generation process are directly related to the actual power generation demand and the reliability of power generation; the fault notification request data, assistance request data and result broadcast data in the communication request data required for the renewable energy power generation process are used to coordinate the information communication and broadcast notification of each power generation site according to the actual power generation demand; the equipment control data of the renewable energy power generation process and the various data information in the network configuration data of the renewable energy power generation process are directly related to the state vector data and network security of the renewable energy power generation process. Therefore, the above data are all key data to be collected.

[0018] A further technical solution is that the initialization of the original collected data set to construct an initial bionic intelligent data vector set of the new energy power generation process specifically includes:

[0019] According to the relationship between any two monitoring knowledge objects in the original collected data set, obtaining the associated knowledge graph of the original collected data set;

[0020] Vectorizing the knowledge objects in the associated knowledge graph, imitating the characteristic data of organisms, and forming bionic intelligent data vectors;

[0021] According to at least two of the bionic intelligent data vectors, an initial bionic intelligent data vector set of the new energy power generation process is constructed.

[0022] By adopting the above technical solution, the knowledge graph bionic vector constructs three bionic feature dimensions based on biodiversity characteristics, collaborative characteristics and autonomous characteristics. The diversity feature dimension corresponds to the data sampling diversity of different knowledge graphs, the collaborative feature dimension corresponds to the communication interaction between knowledge graphs, and the autonomous feature corresponds to the independent bionic intelligent function of each knowledge graph. Through project demand customization and iterative optimization, it is ensured that the knowledge graph bionic vector accurately reflects the information of the knowledge graph.

[0023] A further technical solution is to determine whether the initial bionic intelligence data vector set has an optimal solution, specifically including:

[0024] Providing a random function, and performing formal processing on the data of the knowledge objects in the initial bionic intelligence data vector set according to the random function to generate initial parameters;

[0025] Providing an evaluation function, and evaluating at least two of the initial parameters according to the evaluation function to obtain an initial evaluation value;

[0026] It is determined whether the initial bionic intelligence data vector set has an optimal solution according to the initial evaluation value.

[0027] By adopting the above technical solution: the random function is a function used to generate random numbers, which is used to provide an initial, random solution in this method; the initial evaluation value represents the contribution of the initial vector individual to the target optimization, and also represents the value of the vector individual, which is used to make reference and preparation for subsequent iterative calculations.

[0028] A further technical solution is that the random function is expressed as: r=random(L,M);

[0029] In the formula, r represents the calculation result of the random function, random() represents the functional relationship between L and M, L represents the minimum value, and M represents the maximum value.

[0030] By adopting the above technical solution: the random function is a function used to generate random numbers, and between a maximum value and a minimum value, it is used in the method to provide an initial, random solution.

[0031] A further technical solution is that the evaluation function is expressed as:

[0032] p Gi =g i (s i ,u i ,c i ,e i );

[0033] In the formula, p Gi represents the initial ranking value of the vector individual, g i Represents the mapping relationship of the objective function, s i Indicates the state change of the bionic intelligence data vector individual, u i represents the fault warning of the bionic intelligent data vector individual, c i represents the collaborative task communication request of the bionic intelligence data vector individual, e i Represents cybersecurity threats to bionic intelligence data vector individuals.

[0034] By adopting the above technical solution, the main task of the evaluation function is to estimate the importance of the search node to determine the priority of the node. When determining the node, the characteristic information of the vector individual can be fully utilized to estimate the importance of the node, so that the node with higher importance can be selected for expansion during the search, thereby obtaining the optimal solution.

[0035] A further technical solution is that the mutation knowledge rule includes a bee colony algorithm or a random optimization search algorithm.

[0036] By adopting the above technical solutions, random optimization algorithms introduce randomness to find the global optimal solution or the approximate optimal solution. Based on the principles of probability theory and statistics, they perform random searches in the solution space through an iterative process in the hope of finding a solution of higher quality. Random optimization algorithms show superior performance in solving complex nonlinear problems and large-scale combinatorial optimization problems. The bee colony algorithm is an optimization algorithm based on the behavior of biological groups, which imitates the search and cooperation behavior in bee colonies to solve complex problems. It has good global search capabilities and the ability to avoid local optimal solutions by simulating the characteristics of information transmission, division of labor, cooperation and self-organization in bee colonies. The main advantages of the bee colony algorithm are good adaptability and global search capabilities, and are suitable for large-scale optimization problems.

[0037] A further technical solution is that the screening out of the optimal solution of the variant bionic intelligence data vector set specifically includes:

[0038] Establishing an optimization objective function based on the evaluation function;

[0039] It is determined whether the set of mutated bionic intelligent data vectors has an optimal solution according to the optimization objective function.

[0040] By adopting the above technical solution: since the optimal solution of the bionic intelligent data vector set is the bionic intelligent data vector that is most suitable for solving the problem of bionic intelligent supervision of new energy power generation, the evaluation values ​​of the objective function can be arranged in order of fitness through iterative calculation and sorting, so that the optimal value can be quickly screened out.

[0041] A further technical solution is that the optimization objective function is expressed as:

[0042] min∑p Gi =min∑g i (s i ,u i ,c i ,e i );

[0043] The optimization objective function satisfies the following constraints:

[0044] s i ∈S i ;

[0045] u i ∈U i ;

[0046] c i ∈C i ;

[0047] e i ∈E i ;

[0048] In the formula, s i ∈S i Represents the value constraint range set of the state change of the bionic intelligence data vector individual, u i ∈U i represents the value constraint range set of the fault warning of the bionic intelligent data vector individual, c i ∈C i The value constraint range set of the collaborative task communication request of the bionic intelligent data vector individual, e i ∈E i Represents the set of value constraint ranges to which the network security threats of individual bionic intelligence data vectors belong.

[0049] By adopting the above technical solution, each time an iterative optimization process is performed, the optimization objective function is used to calculate the overall evaluation value of the optimized set of associated knowledge graph vector individuals. Within a preset number of iterations, when the overall evaluation value of the optimized set of associated knowledge graph vector individuals is greater than or equal to a preset threshold, the optimized set of associated knowledge graph vector individuals corresponding to the current evaluation value is determined to be the optimal solution to the problem, so as to ensure the consistency and coordination of the management and maintenance of the associated knowledge graph, and also ensure the overall maximum effectiveness of the associated knowledge graph.

[0050] In the second aspect, the bionic intelligent supervision system for a new energy power generation network provided by the present invention is realized by the following technical solutions:

[0051] A bionic intelligent supervision system for a new energy power generation network, comprising:

[0052] A collection module is used to obtain at least two monitoring knowledge objects of the renewable energy power generation process to form an original collection data set; the monitoring knowledge objects include state vector data of the renewable energy power generation process, communication request data required by the renewable energy power generation process, equipment control data of the renewable energy power generation process, and network configuration data of the renewable energy power generation process;

[0053] An initialization module, used to initialize the original collected data set and construct an initial bionic intelligent data vector set for the new energy power generation process;

[0054] A decision module, for determining whether the initial bionic intelligent data vector set has an optimal solution, and adjusting the new energy power generation network according to the optimal solution;

[0055] and an updating module for providing variation knowledge rules, iteratively updating the initial bionic intelligent data vector set through the variation knowledge rules to generate a variation bionic intelligent data vector set, until the optimal solution of the variation bionic intelligent data vector set is screened out, and adjusting the new energy power generation network according to the optimal solution.

[0056] By adopting the above technical solution, each hardware module is set on the CPU or GPU motherboard, and the CPU or GPU motherboard provides computing basic resources. The acquisition module can be a sensor and / or a microprocessor, which is integrated on the motherboard and is used to collect at least two types of data in the supervision of new energy power generation technology. The initialization module can be integrated in the internal memory or in an external plug-in dongle device, and is used to initialize the bionic intelligent data vector set of the new energy power generation process according to at least two types of data. The decision module can be deployed in the local embedded system memory, or it can access the new energy power generation bionic intelligent supervision decision module deployed on the server side through the network, imitate the swarm intelligence of bees to determine whether the bionic intelligent data vector set belongs to the optimal solution or suboptimal solution of the new energy power generation technology supervision target, and if so, adjust the network of the new energy power generation technology according to the optimal or suboptimal bionic intelligent data vector set. The communication module can be stored in the internal memory or use an external plug-in dongle device. It builds a communication knowledge graph that imitates the bee's figure-8 dance according to the bionic intelligent data vector individual's own state changes, fault warnings, collaborative task communication requests, and network security threats, changes the relevant data of the bionic intelligent data vector, and then selectively updates the bionic intelligent data vector set until the bionic intelligent data vector set becomes the optimal solution or suboptimal solution to the new energy power generation technology supervision target.

[0057] In summary, the present invention includes the following beneficial technical effects:

[0058] Initialize the bionic intelligent data vector set of the new energy power generation process according to at least two knowledge objects obtained in the supervision of new energy power generation technology; judge whether the bionic intelligent data vector set meets the optimal solution or suboptimal solution of the new energy power generation technology supervision target, and if so, adjust the network of the new energy power generation technology according to the optimal or suboptimal bionic intelligent data vector set; otherwise, adjust the parameters of the bionic vector individuals in the knowledge graph according to the variation knowledge rules of the bionic vector individuals in the knowledge graph, and update the bionic vector group in the knowledge graph until the bionic vector set in the knowledge graph meets the target requirements of the supervision and management of the new energy power generation technology, so as to improve the optimization ability of the knowledge graph problem solving in the supervision and management of the new energy power generation technology, and improve the efficiency, mobility and intelligence of the supervision and management of the new energy power generation technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a method flow chart of an embodiment of the present invention.

[0060] Figure 2 It is a system block diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0062] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

[0063] The embodiment of the present invention provides a bionic intelligent supervision method for a new energy power generation network, comprising: acquiring at least two monitoring knowledge objects of a new energy power generation process to form an original acquisition data set; the monitoring knowledge objects include state vector data of the new energy power generation process, communication request data required for the new energy power generation process, equipment control data of the new energy power generation process, and network configuration data of the new energy power generation process; initializing the original acquisition data set to construct an initial bionic intelligent data vector set of the new energy power generation process; judging whether the initial bionic intelligent data vector set has an optimal solution, and if so, adjusting the new energy power generation network according to the optimal solution; otherwise, providing a variation knowledge rule, iteratively updating the initial bionic intelligent data vector set through the variation knowledge rule to generate a variation bionic intelligent data vector set, until the optimal solution of the variation bionic intelligent data vector set is screened out, and adjusting the new energy power generation network according to the optimal solution.

[0064] In an embodiment of the present invention, a bionic intelligent data vector set of a new energy power generation process is initialized based on at least two types of data collected; it is determined whether the bionic intelligent data vector set has an optimal solution or a suboptimal solution to the new energy power generation technology supervision target; if there is no optimal solution, a communication knowledge graph is constructed based on the bionic intelligent data vector individual according to its own state changes, fault warnings, collaborative task communication requests, and network security threats, and the relevant data of the bionic intelligent data vector is changed, and then the bionic intelligent data vector set is updated preferentially until the bionic intelligent data vector set becomes the optimal solution or suboptimal solution to the new energy power generation technology supervision target. The input of the present invention is the original data collected, and the output is the best or suboptimal bionic intelligent data vector, that is, the optimal solution or the suboptimal solution. Using the best bionic intelligent data vector supervision system is more efficient than using a worse bionic intelligent data vector supervision system. The scheme of the present invention improves the bionic intelligence and optimization solution capabilities of the new energy power generation technology supervision, and improves the portable and intelligent management efficiency of the new energy power generation technology supervision.

[0065] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0067] The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings.

[0068] An embodiment of the present invention provides a bionic intelligent supervision method for a new energy power generation network, and the main process of the method is described as follows.

[0069] like Figure 1 As shown:

[0070] Step S100: Acquire at least two monitoring knowledge objects of the new energy power generation process to form an original acquisition data set.

[0071] Among them, the monitoring knowledge objects include state vector data of the new energy power generation process, communication request data required for the new energy power generation process, equipment control data of the new energy power generation process and network configuration data of the new energy power generation process.

[0072] The state vector data of the new energy power generation process includes voltage data, current data and fault data; the communication request data required for the new energy power generation process includes fault notification request data, assistance request data, and result broadcast data; the equipment control data of the new energy power generation process includes motor speed control data, PID control parameter feedback adjustment data, and equipment fault emergency processing data; the network configuration data of the new energy power generation process includes network point-to-point communication configuration data, network blocking configuration data, network broadcast configuration data, and network security maintenance configuration data.

[0073] Among them, collecting at least two types of monitoring data is mainly to balance the global search and local search. By combining the information sharing mechanism, the algorithm can efficiently find the optimal solution in a complex search space.

[0074] Step S200: Initializing the original collected data set to construct an initial bionic intelligent data vector set for the new energy power generation process.

[0075] Among them, the initial bionic intelligent data vector set randomly selects values ​​according to the value range of each data to form a vector composed of initial random values, which constitutes the bionic evolution starting point of the new energy power generation bionic intelligent data vector set.

[0076] The construction of the initial bionic intelligent data vector set for the new energy power generation process specifically includes the following steps:

[0077] Step S210: obtaining an associated knowledge graph of the original collected data set according to the relationship between any two monitoring knowledge objects in the original collected data set;

[0078] Step S220: vectorizing the knowledge objects in the associated knowledge graph to imitate the characteristic data of organisms and form bionic intelligent data vectors;

[0079] Step S230: constructing an initial bionic intelligent data vector set of the new energy power generation process according to at least two of the bionic intelligent data vectors.

[0080] Among them, after obtaining the associated knowledge graph of the original collected data set, the associated knowledge graph is classified (extracted / unextracted), supports query and retrieval, extracts key content such as equipment information and processing results from the data source, and displays detailed knowledge entries; quickly finds problem descriptions and cause analysis related to new energy such as wind power, photovoltaics, and energy storage, and supports query and reset. The construction of the associated knowledge graph can realize the precipitation, aggregation and automatic extraction of processing experience in the field of new energy power generation. The construction of the associated knowledge graph is divided into multiple steps: data collection and acquisition, data preprocessing and cleaning, data knowledge formalization, knowledge aggregation into a knowledge graph, and knowledge graph optimization.

[0081] The initial bionic intelligent data vector individual constructs three bionic feature dimensions according to biodiversity characteristics, collaborative characteristics and autonomous characteristics. The diversity feature dimension corresponds to the data sampling diversity of different knowledge graphs, the collaborative feature dimension corresponds to the communication interaction between knowledge graphs, and the autonomous feature corresponds to the independent bionic intelligent function of each knowledge graph. Through project demand customization and iterative optimization, it is ensured that the knowledge graph bionic vector accurately reflects the information of the knowledge graph.

[0082] Step S300: determining whether the initial bionic intelligent data vector set has an optimal solution; if so, adjusting the new energy power generation network according to the optimal solution.

[0083] The specific steps include:

[0084] Step S310: providing a random function, and performing formal processing on the data of the knowledge objects in the initial bionic intelligence data vector set according to the random function to generate initial parameters;

[0085] Step S320: providing an evaluation function, and evaluating at least two of the initial parameters according to the evaluation function to obtain an initial evaluation value;

[0086] Step S330: judging whether the initial bionic intelligence data vector set has an optimal solution according to the initial evaluation value.

[0087] Among them, the random function is a function used to generate random numbers, which is used to provide an initial, random solution in this method; the initial evaluation value represents the contribution of the initial vector individual to the target optimization, and also represents the value of the vector individual, which is used to make reference and preparation for subsequent iterative calculations.

[0088] In steps S310 to S330, the data of the knowledge objects in the initial bionic intelligence data vector set are formalized, which may include binary coding or real number coding of the data.

[0089] The random function can be expressed as:

[0090] r = random(L,M);

[0091] In the formula, r represents the calculation result of the random function, random() represents the functional relationship between L and M, L represents the minimum value, and M represents the maximum value. The initial parameters and the knowledge graph corresponding to the initial parameters are represented as associated knowledge graph vector individuals.

[0092] Formal processing may include binary encoding or real number encoding of data, generating initial parameters, and representing the initial parameters and the knowledge graph corresponding to the initial parameters as associated knowledge graph vector individuals. The initial parameters may include: state vector data of the new energy power generation process, communication request data required for the new energy power generation process, equipment control data of the new energy power generation process, and network configuration data of the new energy power generation process; the initial parameters may also include parameters of random functions (such as the number of equipment in the new energy power generation process, the number of process sections, the number of expert experience rules, the time consumed by the new energy power generation process, etc.), vector set size, maximum number of iterative calculations, thresholds for evaluation function determination, mutation probability, etc.

[0093] The associated knowledge graph is represented as a graph object G i , the initial evaluation value of the initial bionic intelligence data vector individual is expressed as p Gi , initial evaluation value p Gi It indicates the contribution degree of the initial vector individual to the target optimization, and also indicates the value of the vector individual. According to the initial vector individual and its corresponding initial evaluation value p Gi, we can get the associated knowledge graph vector individual set, which is represented by {(G1,p G1 ),(G2,p G2 ),…,(G i ,p Gi ),…,(G N ,p GN )}, where N represents the number of individuals in the associated knowledge graph vector set, i = 1, 2, ..., N is a positive integer.

[0094] The evaluation function can be expressed as:

[0095] p Gi =g i (s i ,u i ,c i ,e i );

[0096] In the formula, p Gi represents the initial ranking value of the vector individual, g i Represents the mapping relationship of the objective function, s i Indicates the state change of the bionic intelligence data vector individual, u i represents the fault warning of the bionic intelligent data vector individual, c i represents the collaborative task communication request of the bionic intelligence data vector individual, e i Represents cybersecurity threats to bionic intelligence data vector individuals.

[0097] The evaluation function can also be improved from commonly used evaluation functions into a suitable many-to-one function mapping relationship according to specific project requirements.

[0098] Step S400: If not, provide a variation knowledge rule, and iteratively update the initial bionic intelligent data vector set through the variation knowledge rule to generate a variation bionic intelligent data vector set until the optimal solution of the variation bionic intelligent data vector set is screened out, and adjust the new energy power generation network according to the optimal solution.

[0099] Wherein, the mutation knowledge rule includes a bee colony algorithm or a random optimization search algorithm.

[0100] The principle of the bee colony algorithm is an optimization algorithm based on the behavior of biological groups, which imitates the search and cooperation behavior in bee colonies to solve complex problems. The principle of the bee colony algorithm includes the following three stages:

[0101] Leading bee stage: Leading bees search for nectar sources in the search space based on certain strategies. Each nectar source represents a possible solution to the problem. Leading bees will evaluate the quality of the nectar sources they find, usually measured by the objective function value. The better the quality of the nectar source, the higher the fitness of the solution.

[0102] Follower bee stage: Follower bees select nectar sources for further search based on the nectar source information shared by the leader bee with a certain probability. The probability of a follower bee selecting a nectar source is usually proportional to the quality of the nectar source. The better the quality of the nectar source, the greater the probability of being selected. Follower bees conduct local searches near the selected nectar source in the hope of finding a better solution;

[0103] Scouting bee stage: If a nectar source does not get a better result after multiple searches, or is stuck in a local optimum, the leading bee will abandon the nectar source and transform into a scout bee. The scout bee will randomly search for new nectar source areas in the search space to increase the possibility of the algorithm jumping out of the local optimum.

[0104] In combination with the present embodiment, the value range of the original collected data set (i.e., the state vector data of the new energy power generation process, the communication request data required for the new energy power generation process, the equipment control data of the new energy power generation process, and the network configuration data of the new energy power generation process) is equivalent to the activity range of the bees; each data or each value of the original collected data set is equivalent to the nectar source, and the closer it is to the value corresponding to the actual power generation demand, the better the quality of the nectar source; each bee is equivalent to a solution.

[0105] First, a group of bees are initialized and the fitness value of each solution is calculated, that is, the original collected data set is randomly assigned; each associated knowledge graph has a specific graphic meaning similar to the bee's 8-shaped dance, which is convenient for intuitive communication. Other bees adjust their search strategies based on this information, and then construct a set of variant bionic intelligent data vectors for the new energy power generation process. Bees move in the solution space (that is, the value range of the original collected data set), and each movement is determined by the current information and the individual's "intuition" (random factors). This combines global search and local search, which helps to strike a balance between exploring new areas and searching carefully in good areas that have been discovered; as the algorithm iterates, bees continuously update their positions based on the collected information, and the entire bee colony works together to gradually approach the optimal solution in the solution space; the calculation is terminated when the upper limit of the number of iterations is reached or the optimal solution that meets the requirements is found. By simulating the characteristics of information transmission, division of labor, cooperation, and self-organization in the bee colony, it has good global search capabilities and the ability to avoid local optimal solutions.

[0106] The random optimization algorithm introduces randomness to find the global optimal solution or the approximate optimal solution. First, find the approximate area of ​​the target solution in the large-scale search space, and then use a fine and slow search method to randomly and accurately locate the position of the optimal solution or the suboptimal solution; its main parameters are the random mutation probability, the search step length, and the iteration number threshold. The random mutation probability is the possibility of random search points changing randomly; the search step length is the amplitude of the search step, the search step length of the large-scale search is larger, and the search step length of the small-scale precise search is smaller; the iteration number threshold refers to the upper limit of the number of large-scale searches and the upper limit of the number of small-scale precise searches, which is used to control the convergence of random optimization search; the worst knowledge graph bionic vector evolution parameters in the associated knowledge graph bionic vector set are randomly changed to obtain a set of mutant bionic intelligent data vectors.

[0107] In this embodiment, the mutated bionic intelligent data vector set has the same function as the initial bionic intelligent data vector set, except that different specific data represent different states. If the evaluation value of the worst vector individual in the associated knowledge graph bionic vector set calculated in the last iteration is worse than the new bionic vector individual generated by the mutation of the vector individual, the vector individual is eliminated, and the new vector individual generated by the mutation is selected to participate in the bionic calculation of the next iteration; otherwise, the new individual generated by the mutation is eliminated, and the new bionic vector individual is continuously generated by the mutation of the bionic vector individual.

[0108] In step S400, the optimal solution of the variant bionic intelligence data vector set is selected, which specifically includes the following steps:

[0109] Step S410: establishing an optimization objective function based on the evaluation function;

[0110] Step S420: judging whether the set of mutated bionic intelligence data vectors has an optimal solution according to the optimization objective function.

[0111] Among them, the optimization objective function is expressed as:

[0112] min∑p Gi =min∑g i (s i ,u i ,c i ,e i );

[0113] The optimization objective function should also satisfy the following constraints:

[0114] s i ∈S i ;

[0115] u i ∈U i ;

[0116] c i ∈C i ;

[0117] e i ∈E i ;

[0118] In the formula, s i ∈S i Represents the value constraint range set of the state change of the bionic intelligence data vector individual, u i ∈U i represents the value constraint range set of the fault warning of the bionic intelligent data vector individual, c i ∈C i The value constraint range set of the collaborative task communication request of the bionic intelligent data vector individual, e i ∈E i Represents the set of value constraint ranges to which the network security threats of individual bionic intelligence data vectors belong.

[0119] The specific formula and parameters of the optimization objective function can be optimized and customized from the commonly used objective functions and their parameters according to the specific needs of the project. The process of judging whether the variant bionic intelligent data vector set has an optimal solution according to the optimization objective function is basically the same as the process of judging whether the initial bionic intelligent data vector set has an optimal solution, which will not be described in detail here.

[0120] In this embodiment, each time an iterative optimization process is performed, the optimization objective function is used to calculate the overall evaluation value of the individual set of associated knowledge graph vectors of the optimized new energy power generation process.

[0121] Within the preset number of iterations, when the overall evaluation value of the optimized set of associated knowledge graph vector individuals is greater than or equal to a preset threshold, the optimized set of associated knowledge graph vector individuals corresponding to the current evaluation value is determined to be the optimal solution to the problem, so as to ensure the consistency and coordination of the management and maintenance of the associated knowledge graph of the new energy power generation process, and also ensure the overall maximum effectiveness of the associated knowledge graph of the new energy power generation process.

[0122] The following is an example to illustrate this method:

[0123] The objective function of the bionic intelligent data vector set of solar energy new energy power generation is min∑p Gi =min∑g i (s i ,u i , c i , e i ), where s iThe value range of is the state change set (normal, fault, maintenance) of the individual solar power generation bionic intelligent data vector, u i The value type includes a collection of various faults {short circuit fault, aging fault, moisture fault, open circuit fault}, c i The value range includes the collaborative task communication request set of bionic intelligent data vector individuals (assisting power supply, assisting inspection, assisting alarm), e i The value range includes the network security threat set of bionic intelligent data vector individuals (Trojan attack, vulnerability attack, virus attack, hacker intrusion, illegal operation by internal personnel). The bee colony algorithm assists relevant personnel in minimizing the possibility of untimely handling of faults, the possibility of faults caused by incorrect operations, the possibility of failed or untimely collaboration, and the losses caused by network security threats more conveniently and efficiently through a visualized knowledge graph.

[0124] Based on the same inventive concept, the present invention also discloses a bionic intelligent supervision system for a new energy power generation network, which is used to implement the bionic intelligent supervision method for a new energy power generation network in any of the aforementioned steps S100 to S420, such as Figure 2 As shown, including:

[0125] A collection module is used to obtain at least two monitoring knowledge objects of the renewable energy power generation process to form an original collection data set; the monitoring knowledge objects include state vector data of the renewable energy power generation process, communication request data required by the renewable energy power generation process, equipment control data of the renewable energy power generation process, and network configuration data of the renewable energy power generation process;

[0126] An initialization module, used to initialize the original collected data set and construct an initial bionic intelligent data vector set for the new energy power generation process;

[0127] A decision module, for determining whether the initial bionic intelligent data vector set has an optimal solution, and adjusting the new energy power generation network according to the optimal solution;

[0128] and an updating module for providing variation knowledge rules, iteratively updating the initial bionic intelligent data vector set through the variation knowledge rules to generate a variation bionic intelligent data vector set, until the optimal solution of the variation bionic intelligent data vector set is screened out, and adjusting the new energy power generation network according to the optimal solution.

[0129] The initial bionic intelligent data vector set of the new energy power generation process includes voltage data, current data and fault data;

[0130] The communication request data required for the renewable energy power generation process includes fault notification request data, assistance request data, and result broadcast data;

[0131] The equipment control data of the new energy power generation process includes motor speed control data, PID control parameter feedback adjustment data, and equipment failure emergency processing data;

[0132] The network configuration data of the new energy power generation process includes network point-to-point communication configuration data, network blocking configuration data, network broadcast configuration data, and network security maintenance configuration data.

[0133] Furthermore, the initialization module includes:

[0134] A graph construction unit, which obtains a related knowledge graph of the original collected data set according to the relationship between any two monitoring knowledge objects in the original collected data set;

[0135] The vectorization unit is used to vectorize the knowledge objects in the associated knowledge graph, imitate the characteristic data of organisms, and form bionic intelligent data vectors.

[0136] A vector set construction unit is used to construct an initial bionic intelligent data vector set of the new energy power generation process according to at least two of the bionic intelligent data vectors.

[0137] Update modules include:

[0138] A function construction unit, used for providing a random function, an evaluation function and an optimization target function, used for formalizing the data of the knowledge object in the initial / mutated bionic intelligence data vector set according to the random function, generating initial / mutated parameters, and evaluating the initial / mutated parameters according to the evaluation function to obtain initial / mutated evaluation values;

[0139] The function calculation unit determines whether the initial bionic intelligence data vector set has an optimal solution according to the initial evaluation value, and determines whether the mutated bionic intelligence data vector set has an optimal solution according to the optimization objective function.

[0140] Each functional module or functional unit may be computer software or hardware device. When it is a hardware device, it may be integrated and installed on a CPU or GPU mainboard, or it may be separately provided.

[0141] CPU or GPU motherboard, providing basic computing resources.

[0142] The acquisition module can collect real-time data of new energy power generation equipment through serial port line or network cable.

[0143] The initialization module can be integrated in the internal memory or in an external plug-in dongle device, and is used to initialize the bionic intelligent data vector set of the new energy power generation process based on at least two types of data.

[0144] The decision-making module can be deployed in the local embedded system memory, or it can access the new energy power generation bionic intelligent supervision decision-making module deployed on the server side through the network. It imitates the swarm intelligence of bees to determine whether the bionic intelligent data vector set belongs to the optimal solution or suboptimal solution of the new energy power generation technology supervision target. If so, the network of the new energy power generation technology is adjusted according to the optimal or suboptimal bionic intelligent data vector set.

[0145] The communication module can be stored in the internal memory or use an external plug-in dongle device. It builds a communication knowledge graph that imitates the bee's figure-8 dance according to the bionic intelligent data vector individual's own state changes, fault warnings, collaborative task communication requests, and network security threats, changes the relevant data of the bionic intelligent data vector, and then selectively updates the bionic intelligent data vector set until the bionic intelligent data vector set becomes the optimal solution or suboptimal solution to the new energy power generation technology supervision target.

[0146] The handheld bionic intelligent supervision system device for renewable energy power generation network can adopt a packaging mode to prevent static electricity. The bionic intelligent supervision system device for renewable energy power generation network can adopt an instant plug-in module or be fixed by a fixing device.

[0147] Based on the same inventive concept, the present invention also discloses an intelligent terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the bionic intelligent supervision method of the new energy power generation network in steps S100 to S420.

[0148] Based on the same inventive concept, the present invention also discloses a computer-readable storage medium storing a computer program that can be loaded by a processor and execute any one of the bionic intelligent supervision methods for a new energy power generation network in steps S100 to S420.

[0149] It should be noted that all implementation methods in the above method embodiments are applicable to the bionic intelligent supervision system of the new energy power generation network and can achieve the same technical effect.

[0150] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0151] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system and module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0152] In the embodiments provided in the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0155] 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, server, or 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, ROM, RAM, disk or optical disk and other media that can store program codes.

[0156] In addition, it should be pointed out that in the system and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For ordinary technicians in the field, it can be understood that all or any steps or components of the method and device of the present invention can be implemented in hardware, firmware, software or a combination thereof in any computing device (including processors, storage media, etc.) or a network of computing devices. This can be achieved by ordinary technicians in the field using their basic programming skills after reading the description of the present invention.

[0157] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing system. The computing system can be a well-known general system. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0158] As described above, the above embodiments are only used to introduce the technical solution of the present application in detail, but the description of the above embodiments is only used to help understand the method and core idea of ​​the present invention and should not be understood as limiting the present invention. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention.

Claims

1. A bionic intelligent supervision method for a new energy power generation network, characterized in that: include: Acquire at least two monitoring knowledge objects of the renewable energy power generation process to form an original acquisition data set; the monitoring knowledge objects include state vector data of the renewable energy power generation process, communication request data required by the renewable energy power generation process, equipment control data of the renewable energy power generation process, and network configuration data of the renewable energy power generation process; Initializing the original collected data set to construct an initial bionic intelligent data vector set of the new energy power generation process; Determine whether the initial bionic intelligent data vector set has an optimal solution, and if so, adjust the new energy power generation network according to the optimal solution; If not, provide variation knowledge rules, iteratively update the initial bionic intelligent data vector set through the variation knowledge rules to generate a variation bionic intelligent data vector set, until the optimal solution of the variation bionic intelligent data vector set is screened out, and adjust the new energy power generation network according to the optimal solution.

2. A bionic intelligent supervision method for a new energy power generation network according to claim 1, characterized in that: The state vector data of the new energy power generation process includes voltage data, current data and fault data; The communication request data required for the renewable energy power generation process includes fault notification request data, assistance request data, and result broadcast data; The equipment control data of the new energy power generation process includes motor speed control data, PID control parameter feedback adjustment data, and equipment failure emergency processing data; The network configuration data of the new energy power generation process includes network point-to-point communication configuration data, network blocking configuration data, network broadcast configuration data, and network security maintenance configuration data.

3. The bionic intelligent supervision method for a new energy power generation network according to claim 1 is characterized by: Initializing the original collected data set to construct an initial bionic intelligent data vector set for the new energy power generation process specifically includes: According to the relationship between any two monitoring knowledge objects in the original collected data set, obtaining the associated knowledge graph of the original collected data set; Vectorizing the knowledge objects in the associated knowledge graph, imitating the characteristic data of organisms, and forming bionic intelligent data vectors; According to at least two of the bionic intelligent data vectors, an initial bionic intelligent data vector set of the new energy power generation process is constructed.

4. The bionic intelligent supervision method for a new energy power generation network according to claim 1 is characterized in that: Determining whether the initial bionic intelligence data vector set has an optimal solution specifically includes: Providing a random function, and performing formal processing on the data of the knowledge objects in the initial bionic intelligence data vector set according to the random function to generate initial parameters; Providing an evaluation function, and evaluating at least two of the initial parameters according to the evaluation function to obtain an initial evaluation value; It is determined whether the initial bionic intelligence data vector set has an optimal solution according to the initial evaluation value.

5. A bionic intelligent supervision method for a new energy power generation network according to claim 4, characterized in that: The random function is expressed as: r = random(L,M); In the formula, r represents the calculation result of the random function, random() represents the functional relationship between L and M, L represents the minimum value, and M represents the maximum value.

6. A bionic intelligent supervision method for a new energy power generation network according to claim 4, characterized in that: The evaluation function is expressed as: p Gi =g i (s i ,u i ,c i ,e i ); In the formula, p Gi represents the initial ranking value of the vector individual, g i Represents the mapping relationship of the objective function, s i Indicates the state change of the bionic intelligence data vector individual, u i represents the fault warning of the bionic intelligent data vector individual, c i represents the collaborative task communication request of the bionic intelligence data vector individual, e i Represents cybersecurity threats to bionic intelligence data vector individuals.

7. The bionic intelligent supervision method for a new energy power generation network according to claim 1 is characterized in that: The mutation knowledge rule includes a bee colony algorithm or a random optimization search algorithm.

8. The bionic intelligent supervision method for a new energy power generation network according to claim 4 is characterized in that: The step of selecting the optimal solution of the set of variant bionic intelligent data vectors includes: Establishing an optimization objective function based on the evaluation function; It is determined whether the set of mutated bionic intelligent data vectors has an optimal solution according to the optimization objective function.

9. A bionic intelligent supervision method for a new energy power generation network according to claim 8, characterized in that: The optimization objective function is expressed as: min∑p Gi =min∑g i (s i ,u i ,c i ,e i ); The optimization objective function satisfies the following constraints: s i ∈S i ; in i ∈U i ; c i ∈C i ; and i ∈E i ; In the formula, s i ∈S i Represents the value constraint range set of the state change of the bionic intelligence data vector individual, u i ∈U i represents the value constraint range set of the fault warning of the bionic intelligent data vector individual, c i ∈C i The value constraint range set of the collaborative task communication request of the bionic intelligent data vector individual, e i ∈E i Represents the set of value constraint ranges to which the network security threats of individual bionic intelligence data vectors belong.

10. A bionic intelligent supervision system for a new energy power generation network, comprising: A collection module, used to obtain at least two monitoring knowledge objects of the renewable energy power generation process to form an original collection data set; The monitoring knowledge objects include state vector data of the new energy power generation process, communication request data required by the new energy power generation process, equipment control data of the new energy power generation process, and network configuration data of the new energy power generation process; An initialization module, used to initialize the original collected data set and construct an initial bionic intelligent data vector set for the new energy power generation process; A decision module, for determining whether the initial bionic intelligent data vector set has an optimal solution, and adjusting the new energy power generation network according to the optimal solution; and an updating module for providing variation knowledge rules, iteratively updating the initial bionic intelligent data vector set through the variation knowledge rules to generate a variation bionic intelligent data vector set, until the optimal solution of the variation bionic intelligent data vector set is screened out, and adjusting the new energy power generation network according to the optimal solution.

Images