57 results about "Biogeography" patented technology

The invention discloses a goods allocation distribution scheduling model establishing method in a two-end same-rail double-vehicle operation mode. According to the method, goods is reasonably distributed to available goods allocations according to the warehouse outbound / inbound frequency, mass and quantity attributes, mathematical expectations of the operation time of two stackers for executing warehouse outbound tasks are close to each other and are the minimum, the integral gravity center of the shelves is low, total masses of the shelf sets are close to each other, in a subsequent optimization algorithm, the goods allocation priority strategy is employed to make initial population mass of the algorithm be more optimal, the specific optimization algorithm is an integrated multi-target biogeography optimization algorithm, and excellent performance at any optimization solution phase is realized. Goods allocations with the high warehouse outbound / inbound frequency are arranged nearby two warehouse outbound / inbound stations, the integral gravity center is low, the total masses of the shelf sets are close to each other, and actual same-rail double-vehicle condition demands can be satisfied.

The invention discloses a multi-target distribution network reconstruction method considering distributed generation and load uncertainty. Wind power output force, photovoltaic power generation and load uncertainty are taken into consideration in the method. The three most important evaluation indexes, of optimized operation of a distribution network, including active loss, minimal voltage value of nodes and load balancing degree, namely three optimizing reconstruction targets, are given. Wind power output force, photovoltaic power output force and load uncertainty factors are processed through a scene analytical method. The final reconstruction scheme is obtained through multi-target disturbance biogeographic algorithm and fuzzy set theory. A multi-target reconstruction decision solution can be rapidly found, and high searching efficiency is ensured. Under an absorbing distributed power supply condition, various indexes of a network can be improved substantially through network reconstruction, so that the reconstruction is more adaptable to a real decision-making process.

An embodiment of the invention provides a cloud collaborative multi-task scheduling method and a cloud collaborative multi-task scheduling device. The cloud collaborative multi-task scheduling methodcomprises the steps of: acquiring a to-be-processed task received by each edge node; distributing all to-be-processed tasks to different edge nodes for processing to serve as a habitat distribution scheme, and randomly generating an initial population with a plurality of habitat distribution schemes; and based on a preset target function and a biogeography optimization algorithm, acquiring an optimal solution meeting the target function, and acquiring a to-be-processed task which should be allocated to each edge node. The cloud collaborative multi-task scheduling method is based on the presettarget function and the biogeography optimization algorithm, acquires the optimal solution meeting the target function, obtains the to-be-processed task to be allocated to each edge node, considers reasonable task allocation of all the edge nodes and the central cloud node, can obtain the optimal allocation scheme meeting the optimization target based on the preset target function, is implementedbased on the biogeography optimization algorithm, and greatly reduces the calculation overhead.

The invention discloses a power distribution network economy reconstructing method considering network loss and reliability. The power distribution network economy reconstructing method considering the network loss and reliability includes an economy optimizing model for summing based on power loss cost due to network loss and power loss cost due to deficiency of power supply amount under a power failure state, an object-oriented power distribution network reliability calculating method matched with the model, a power distribution network economy reconstructing model calculation method based on a biogeography algorithm, and power distribution network economy reconstructing steps based on the core content of the three parts, wherein the power distribution network reliability calculating method includes element collection class, block class, block class tree and power supply route determination methods, and the power distribution network economy reconstructing model calculation method includes the construction of residential suitability indexes, habitat characteristic vectors, transport models and the like. The power distribution network economy reconstructing method considering the network loss and reliability combines the yearly demand not supplied due to the network electricity interruption and the yearly power loss due to the network loss to construct the power distribution network economy reconstructing model which simultaneously considers the power distribution network reliability and network loss, and the model has visual economy characteristics and strives to obtain the most economical network structure. The power distribution network economy reconstructing method considering the network loss and reliability is suitable for reconstructing the power distribution network economy.

The invention discloses a method for constructing a core backbone grid structure based on BBO algorithm and power grid survivability. The method comprises the following steps: establishing a survivability index system taking the resistance, recoverability and connectivity of a power grid into consideration, and determining an integrated survivability index of the power grid system according to the survivability index system; step 2, using the minimum total length of a circuit and the maximum integrated survivability index as an objective function to construct a mathematical model of the core backbone grid structure; step 3, using a biogeography optimization algorithm to search the mathematical model of the core backbone grid structure and construct the core backbone grid structure of the power grid system. The method can quickly and accurately obtain a reasonable solution to the core backbone grid structure.

The invention discloses a dynamic task perception-oriented cloud manufacturing collaborative task scheduling method, which comprises the following steps of firstly, constructing a collaborative task scheduling model according to the proportion of tasks completed by a supply chain; generating an initial population as a current population when a new task arrives according to an original manufacturing task and an optional manufacturing service, dividing the current population into a plurality of sub-populations for subsequent iteration, and representing each collaborative task scheduling scheme in the current population by using matrix coding; and finally, solving is performed through an improved multi-population biogeography optimization algorithm, and fusing a multi-population strategy, a local search strategy and a cooperation mechanism, so that the task scheduling problem solving performance of the algorithm is improved. According to the method, a better scheduling scheme can be obtained in the scheduling stage and the re-scheduling stage.

The invention discloses a design method for an SVC (Static Var Compensators) controller based on improved atomic decomposition parameter identification. Based on an overcomplete damped sine atom library, a cosine migration model, a mixed migration operator and a mutation strategy are introduced to improve the biogeography optimization method, the improved biogeography optimization method is adopted to optimize the atom decomposition method, and the improved atom decomposition method is adopted to decompose a subsynchronous oscillation signal and identify a subsynchronous oscillation modal parameter; based on the identified subsynchronous oscillation modal parameter, an SVC subsynchronous damping controller is designed and optimized by the particle swarm algorithm. According to the invention, the subsynchronous oscillation modal parameter can be quickly and accurately identified, and the designed SVC subsynchronous damping controller has a favorable subsynchronous oscillation inhibition effect.

The invention discloses a distributed photovoltaic sitting and sizing method for determining minimum permeability. The method comprises the following steps: recording the topological structure, system parameter and running state data of an active power distribution network from an electric network database to form a basic database; building a corresponding probability density function according to distributed photovoltaic power generation output and certain randomness in power consumption of a user; solving a target function with a biogeographical algorithm by taking maximum reduction in the carbon emission after distributed photovoltaic access as a optimization target and considering the constraint conditions of trend reverse feeding and distributed photovoltaic minimum permeability. By adopting the distributed photovoltaic sitting and sizing method, the trend reverse feeding caused by large photovoltaic installed capacity is avoided under the condition of ensuring the minimum photovoltaic permeability, and the reduction in the carbon emission is maximized; a power user is guided to use electric energy and low carbon resources more efficiently, and the carbon emission is lowered, so that the formation of an integral low-carbon electric power system is prompted.

The invention belongs to the technical field of image processing, in particular to an image division method based on biogeography optimization capable of being used for image enhancement, mode identification, target tracking and the like. The method comprises the following steps that parameters are initialized; pictures to be divided are input, and clustering centers are initialized; a fuzzy matrix is calculated; the clustering centers are calculated again; the fitness value of each clustering center is extracted; the immigration rate and the emigration rate of each emigration center are extracted; the emigration centers are updated according to mutation operators; and division results are output. Because the biogeography migration strategy is adopted for optimizing the clustering centers, the calculation quantity is reduced, the selected clustering centers after the optimization have the overall situation characteristics, the problem of initialization sensitivity of the traditional clustering algorithm is solved, and the stability and the clustering performance of the clustering algorithm are improved. Because the immigration and emigration strategies are introduced for optimizing the clustering centers, the data center distribution characteristics can be more accurately reflected, in addition, the corresponding clustering center updating rules are designed, and the calculation quantity is reduced.

The invention provides an electric power Internet of Things multi-task cooperative distribution method and device, and the method comprises the steps: determining the average completion time delay of subtasks of all terminal nodes of an electric power Internet of Things according to the subtasks of the terminal nodes of the electric power Internet of Things and edge calculation nodes; constructing a multi-task cooperative distribution model according to the sub-task average completion time delay of all the terminal nodes of the power Internet of Things; and solving the multi-task collaborative allocation model through a task allocation algorithm of a biogeography optimization algorithm to obtain an optimal task allocation scheme. A multi-task collaborative allocation model is constructed through sub-task average completion time delay of all terminal nodes of the electric power Internet of Things, task allocation and convergence routing problems of task average completion time delay minimization are proposed, an optimal task allocation scheme is solved based on a task allocation algorithm of a biogeography optimization algorithm, and the optimal task allocation efficiency is improved. The solution search efficiency can be effectively improved, local optimum is avoided, and multi-task cooperative distribution of the power Internet of Things is better realized.

The invention provides a microgrid reliability evaluation method considering different operation strategies. The method comprises the following steps: I, a reliability model for an energy storage system is built based on a state space method; II, according to historical data of wind speeds and sunlight radiation intensities over the past 10 years in a certain area, an autoregressive moving averagemodel (ARMA model) is built, and according to a power conversion formula, a single wind power and photovoltaic unit output model considering unit fault in the next year is solved; III, a load time sequence model which plans to use a microgrid for power supply is built; IV, a biogeography particle swarm hybrid algorithm is adopted to solve the optimal allocation of a wind-solar-diesel-storage capacity in the microgrid considering an operation strategy; and V, in consideration of the specific grid structure of the microgrid, reliability evaluation is carried out. Before reliability evaluation,the wind-solar-diesel-storage capacity connected to the microgrid is determined, the evaluation is in consideration of the specific grid structure of the microgrid and the operation strategies, the evaluation conforms to the reality, and the power supply reliability in the case of independent operation of the microgrid can be effectively mastered.

The invention discloses a design method of an SVC (static var compensator) subsynchronous damping controller based on an improved BBO (biogeography-based optimization) algorithm. Through the IBBO (improved biogeography-based optimization) algorithm introducing a cosine migration model, a prematurity judgment mechanism, a mutative scale chaos variation strategy and a repetitive removing operation, based on a mechanism that the IBBO algorithm combines the SVC to restrain SSO (subsynchronous oscillation), the subsynchronous damping controller is subjected to an optimization design. Therefore, the SVC subsynchronous damping controller designed by the method disclosed by the invention can greatly improve themodal damping of torsional vibration of a machine set and effectively restrain the SSO so as to ensure the safe and stable operation of the machine set and a power grid.

The invention provides a bio-geographic optimization algorithm-oriented constraint handling method and device. The method comprises: an improved migration step: capturing individuals selected from a target population; extracting target dimension elements of the selected individuals; based on an individual emigration rate, performing weighted fusion on the target dimension elements of the selected individuals according to a simulated binary crossover operator to generate new elements to be immigrated; an improved variation step: updating target sub populations according to the new elements to be immigrated and performing disturbance using Gaussian distribution to obtain an excellent target population; and a feasible constraint handing step: determining the excellent target population, determining optimal individuals and updating varied parameters by a differential evolution algorithm. By combining the information search capability of the differential evolution algorithm and the information utilization capability of the bio-geographic algorithm, the global optimization capability of the handling scheme is promoted and balanced.

The invention provides a Spark and MBBO (multi-objective biogeography-based optimization) algorithm-based parallel virtual machine aggregation method. Through an extended Spark parallel framework and an MBBO algorithm, an optimal migration solution of a VMC problem can be solved in a relatively short convergence time, and a foundation is laid for subsequent virtual machine parallel migration. The method comprises the following steps of 1, mapping a virtual machine aggregation problem to a biogeography-based optimization algorithm, determining constraint conditions, and clearly determining solving objectives; and 2, based on the extended Spark parallel framework, distributing an initial habitat group meeting the constraint conditions to Spark computing nodes, iteratively executing an MBBO parallel algorithm, stopping algorithm execution until a stop condition is met, and obtaining an optimal solution capable of balancing a plurality of optimization solving objectives. While the extended Spark parallel framework is utilized, a biogeography concept is mapped to an optimization problem.

The invention relates to the field of mobile edge computing, in particular to an energy consumption optimization computing method and system based on mobile edge computing and an energy consumption optimization unloading method and system based on mobile edge. The computing method comprises the following steps: solving a series of cost solutions of time cost and energy consumption cost in each cost model by utilizing a biogeography optimization algorithm; separately sorting the series of cost solutions by adopting a fast non-dominated sorting algorithm, and separately obtaining a cost solutionset; calculating respective ideal solutions and negative ideal solutions according to a multi-criterion decision-making method TOPSIS, and finding out an optimal solution closest to the ideal solution from the cost solution set; substituting the optimal solution into a corresponding cost model, and determining the optimal time cost and energy consumption cost for unloading the current task by adopting edge equipment or central equipment and the optimal time cost and energy consumption cost for computing the current task by adopting local equipment. According to the method, the time, the energy consumption and the mobility of the mobile equipment can be comprehensively considered, and the effects of energy consumption computing and task unloading are ensured.

The invention discloses a dynamic balance detection control method based on the biogeographical intelligent optimization support vector machine algorithm. The method comprises the following steps: (1) collecting online data, (2) inputting off-line data, (3) setting the requirement for model precision, (4) preprocessing the data, (5) judging whether a dynamic balance system model exists, (6) judging whether the system unbalance exceeds a threshold value, (7) carrying out the biogeographical intelligent optimization support vector machine algorithm with Kalman filtering, (8) establishing the dynamic balance system model, and (9) carrying out dynamic balance adjustment. According to the method, system modeling is carried out based on the support vector machine algorithm according to the small sample and nonlinearity characteristics of a dynamic balance system, penalty factors and kernel function parameters of the support vector machine algorithm are optimized based on the biogeographical intelligent optimization algorithm, Kalman filtering is adopted for improving the robustness and accuracy of the whole algorithm in consideration of noise interference in a dynamic balance system spot, and therefore high-precision detection control over the dynamic balance system can be achieved.

A Docker and virtual machine aggregation placement method based on multi-objective biogeography optimization algorithm includes that firstly, Creatively Docker and virtual machine are taken as a unitof aggregation to build a DVMP (Docker and Virtual Machine Placement, Docker and VM placement) constraint model based on DVP three-tier architecture; Secondly, the constraint conditions of DVMP constraint model are defined, and the DVMP aggregation placement model is established. Next, a mapping method of MBBO-based Docker and virtual machine aggregation placement is executed; Then, the convergence scenario is adapted and coded to obtain the effective solution, and the optimal solution of the convergence problem between Docker and virtual machine is found by iteratively updating the initial population. Finally, Docker and virtual machine are aggregated according to the optimal placement scheme. The method of the invention can solve the problem that the virtual machine resource occupies large amount and is difficult to aggregate, and can optimize the energy consumption of the data center and the utilization rate of the server resource.

The invention discloses a biogeographic optimization method for the emergency service facility location problem. The method comprises the following steps: setting an initial value of each variable, and randomly initializing suitability vector Xi of each habitat; calculating habitat suitability f(Xi), corresponding species number si, immigration rate and emigration rate; judging whether the habitat needs to carry out immigration operation according to the migration rate; if the habitat needs to carry out the immigration operation, selecting a characteristic component xij to be immigrated to the habitat according to the immigration rate, and selecting a habitat k as an immigration object according to the emigration rate of the other habitats, and replacing corresponding position of a habitat i with the corresponding position of the selected habitat k; calculating probability P (si) of the number of species accommodated in the habitat, calculating mutation rate m(Xi) by utilizing the probability P (si), and judging whether each component of the habitat i has mutation operation based on the mutation rate m(Xi); and detecting whether a stop condition is met, and if not, continuing execution, or otherwise, outputting the current optimal solution. Compared with a conventional optimization method, the method has better optimization performance.

The invention discloses an IBBO based complex looped network directional protection MBPS solving method, which is characterized in that the effectiveness of a determined breakpoint is judged by adopting a protection association matrix, and a lot of calculation required by forming all simple directed circuits of the whole network is avoided; an improved biogeography optimization algorithm is proposed, an a transfer model, a transfer operator and a mutation operator of the traditional BBO algorithm are improved; and the breakpoint is solved by using an IBBO method, and efficient solving for a minimum breakpoint optimization model is achieved. The MBPS can be effectively solved for an ultrahigh-voltage power grid containing multiple looped networks according to the invention. Compared with the traditional optimization method, the method disclosed by the invention is high in convergence speed, good in iteration robustness and high in convergence precision, and has excellent optimization performance.

The invention discloses an energy-efficient and resource-limited mobile edge computing task allocation method, which comprises the following steps: establishing a joint optimization model based on energy consumption and processor resource waste according to different task allocation schemes and the influence on energy and processor resources of edge clouds under the condition of stipulated execution delay; further minimizing total energy consumption of task allocation and processor resource waste under the condition of stipulating execution delay, then mapping the joint optimization problem into an ecosystem model of a biogeography algorithm, and obtaining an optimal task allocation scheme according to a corresponding optimization target and a corresponding optimization condition; according to the invention, the problem that the mobile user equipment with limited resources cannot meet the resource requirements of the mobile application is solved, the mobile user equipment can unload part of tasks forming the mobile application to the base station or the edge cloud of the mobile edge computing, and the energy efficiency of the edge cloud and the resource utilization rate of the processor are improved.

Embodiments of the present invention disclose a method and a system for comprehensively optimizing expansion planning of a distribution network containing a distributed energy source and a charging station. The method comprises: establishing a multi-objective optimization function based on a system average power-off duration and a planned annual average cost of the distribution network; determining constraint conditions of the multi-objective optimization function; setting the capacity of a distributed energy and the capacity of the charging station of each node in the distribution network; and according to the capacity of the distributed energy and the capacity of the charging station of each node, the multi-objective optimization function and the constraints, solving the multi-objective optimization function by using the multi-objective perturbation biogeography algorithm; and according to the capacity of the distributed energy and the capacity of the charging station of each node in the distribution network corresponding to the required solutions of the multi-objective optimization function, optimizing the expansion planning of the distribution network containing the distributed energy source and the charging station. According to the method disclosed by the embodiments of the present invention, a plurality of variables of the distributed energy source and the charging station of an optional node in the distribution network are optimized.

The invention relates to an ISSR(Inter-simple Sequence Repeat)-PCR(Polymerase Chain Reaction) molecular marker method for macromitrium gymnostomum. The ISSR-PCR molecular marker method comprises the following steps of firstly, extracting genome DNA (Deoxyribose Nucleic Acid) of the macromitrium gymnostomum; secondly, performing ISSR-PCR amplification, wherein a reaction system for performing the ISSR-PCR amplification in step (2) is as follows: 30mu L reaction system contains 3mu L of 10*LAPCR (Polymerase Chain Reaction ) buffer solution, 50ng of template DNA, 1.5mmol / L of Mg<2+>, 0.25mmol / L of dNTP (Deoxyribonucleoside Triphosphate), 1.5U of Taq enzyme and 0.5mu mol / L of primer. A primer UBC(University of British Columbia) 834 is taken as an example, ISSR amplification comprises conditions of: annealing at the temperature of 94DEG C for 4 minutes, then annealing at the temperature of 94DEG C for 45 seconds, at the temperature of 53DEG C for 45 seconds and at the temperature of 72DEG C for 1 minute for 45 circles, and finally, prolonging the annealing time at the temperature of 72DEG C by 10 minutes. Compared with the prior art, the ISSR-PCR molecular marker method disclosed by the invention has the advantages that a strip amplified by an established ISSR-PCR reaction system for the macromitrium gymnostomum has the characteristics of high stability, high definition and high polymorphism; the shortages in the research on the genetic diversity of the macromitrium gymnostomum are made up; the achievements of the invention can be used for researching the genetic relationship, a molecular marker and biogeography, and has high scientific value and application value.

The invention provides a multi-constraint FIR (Infinite Impulse Response) digital filter generation method for a quantum biogeography evolution mechanism. Habitats are initialized and suitability indexes are calculated. The habitats are mapped into quantum habitats, the quantum habitats are arranged in a descending order, and each quantum habitat is initialized. Migration operation is carried out on the quantum habitats and two kinds of mutation operation are carried out on the last 50% of the quantum habitats; the quantum habitats are mapped into the habitats, the suitability indexes of the habitats are calculated, the quantum habitats are arranged in the descending order, the quantum habitats are updated, and quantum situation knowledge and quantum standard knowledge in a quantum belief space are updated; each quantum habitat is updated; and cyclic iteration is carried out, the optimum quantum habitat in the quantum situation knowledge is finally output, the optimum quantum habitat is mapped into the habitat, and the habitat corresponds to a parameter vector of an FIR digital filter. The FIR digital filter designed by the invention has the advantages of fast convergence speed, high filter performance and satisfaction of a multi-constraint demand.

The invention discloses a dynamic balance detection control method based on the biogeographical intelligent optimization support vector machine algorithm. The method comprises the following steps: (1) collecting online data, (2) inputting off-line data, (3) setting the requirement for model precision, (4) preprocessing the data, (5) judging whether a dynamic balance system model exists, (6) judging whether the system unbalance exceeds a threshold value, (7) carrying out the biogeographical intelligent optimization support vector machine algorithm with Kalman filtering, (8) establishing the dynamic balance system model, and (9) carrying out dynamic balance adjustment. According to the method, system modeling is carried out based on the support vector machine algorithm according to the small sample and nonlinearity characteristics of a dynamic balance system, penalty factors and kernel function parameters of the support vector machine algorithm are optimized based on the biogeographical intelligent optimization algorithm, Kalman filtering is adopted for improving the robustness and accuracy of the whole algorithm in consideration of noise interference in a dynamic balance system spot, and therefore high-precision detection control over the dynamic balance system can be achieved.

The invention discloses a drill jumbo telescopic arm limit working condition calculation method and belongs to the field of mechanical arm working condition calculation. The invention aims to solve the problem that the optimal design result of the telescopic arm cannot meet the actual engineering requirement due to the fact that the limit working condition of the telescopic arm of the drill jumbo is determined according to experience at present. Comprising the following steps: acquiring the gravity, gravity center position and rock recoil load of each component in the boom structure of the telescopic boom of the drill jumbo and the variation range of each degree of freedom of the boom structure; determining a telescopic boom top load calculation model; obtaining an optimization range of a novel biogeography optimization algorithm, and taking a calculation result of the telescopic arm top load calculation model as a habitat suitability index HSI; and initializing NH habitats, performing optimization through an optimization algorithm, and obtaining the habitat with the maximum top end load of the telescopic arm, wherein the corresponding freedom degree value combination is the limiting working condition of the telescopic arm, and the novel biogeography optimization algorithm includes an improved mobility model. The optimal solution of the limit working condition can be obtained.

Micron scale biogeography is a major driver of physiology and ecology of complex microbial biofilm communities, which remains elusive largely due to the lack of tools for spatially resolved phylogenetic mapping. This disclosure provides methods, computer-readable storage devices and kits that allow highly multiplexed and spatially resolved imaging of microbial community spatial organization. The disclosure provides a highly-multiplexed approach to resolve the spatial structure of complex microbial community at high taxonomic resolution.

The invention discloses an optimization method of manufacturing service supply chain oriented to network dependency perception, and proposes a mathematical model of manufacturing service composition oriented to network dependency perception to describe the optimization problem of manufacturing service supply chain. The method uses a matrix-based coding scheme, thereby formally representing a manufacturing service supply chain candidate. The first element of each column in the matrix represents the composition structure type (selection or parallelism) of the vertically composed service group, while the other elements in the column represent the selected basic candidate services, thereby cooperating to complete the corresponding subtasks. By combining the migration operator of a biogeography-based optimization (BBO) algorithm with an ABC algorithm, the optimization efficiency of a manufacturing service supply chain is improved. The method of the invention is superior to other methods ofthe prior art in solving the optimization problem of the manufacturing service supply chain through the comprehensive comparison of three aspects of practicability, effectiveness and efficiency.

The invention discloses a virtual power plant aggregation regulation and control communication network flow balancing method and device. The method comprises the following steps: generating a slice network mapping scheme based on slice node, slice link and slice gateway mapping; and carrying out iterative optimization on the slice network mapping scheme by adopting an improved biogeography principle algorithm to obtain an optimal mapping scheme. Through implementation of the method, a plurality of slice network mapping schemes are generated to serve as a population for improving a biogeography principle algorithm, meanwhile, the population and a migration operator are reset, the earlier-stage tentative search capability and the later-stage better convergence speed are increased, iterative optimization is performed on the initial mapping scheme population, SDN-defined network slice global optimization is performed, and the algorithm efficiency is improved. The invention discloses slice network mapping used for virtual power plant communication network flow balancing, which balances the flow of the whole physical network, reduces virtual power plant communication network congestion and network transmission delay, and improves network transmission real-time performance and network long-term average operation benefit and effectiveness maximization.

The invention discloses an electric power system based on wave power generation. The electric power system mainly comprises a wave power generation power prediction neural network model, a voltage source converter direct-current transmission technology (VSC-VDC) and a static var compensator (SVC) subsynchronous damping controller, wherein a normalization algorithm, an S-type tangent function, an S-type logarithmic function and an inverse normalization algorithm are adopted for the wave power generation power prediction neural network model, a VSC-VDC discrete control model and an unbalance algorithm are adopted for the voltage source converter direct-current transmission technology (VSC-VDC), and an improved biogeography optimization algorithm is adopted for the static var compensator (SVC) subsynchronous damping controller. According to the system, the wave power generation power prediction neural network model, the voltage source converter direct-current transmission technology (VSC-VDC) and the static var compensator (SVC) subsynchronous damping controller are combined together, and thus running performance and intelligent level of the electric power system based on wave power generation are improved.