A capacity optimization configuration method and system based on a particle swarm optimization algorithm

Abstract

The application discloses a capacity optimization configuration method and system based on a particle swarm optimization algorithm, which determines an optimization target and a constraint condition of an offshore renewable energy comprehensive utilization system, and utilizes the particle swarm optimization algorithm to optimize the configuration of the offshore renewable energy comprehensive utilization system; the optimization configuration of the offshore renewable energy comprehensive utilization system is completed based on the optimization target and the constraint condition and the selection of a suitable particle swarm optimization algorithm. Through the optimization configuration, the overall cost of the system, including initial investment, operation and maintenance cost and the cost of an energy recovery device, can be reduced. The particle swarm optimization algorithm can find the optimal solution of a cost function, so that the cost minimization is realized.

Description

Technical Field

[0001] This invention relates to the field of system optimization technology, and in particular to a capacity optimization configuration method and system based on particle swarm optimization algorithm. Background Technology

[0002] The design objectives of the system need to be clearly defined, which typically include cost minimization, system reliability maximization, and control of excess energy rate. For example, the study uses the system's economy and reliability as optimization objectives, considering equipment investment and operating costs, as well as the system's carbon emission reduction performance. During the optimization process, various constraints need to be considered, such as the number of devices, load failure rate, the matching degree between power supply and load, and battery capacity. These constraints limit the possible system configuration schemes, ensuring the feasibility of the system in actual operation. Marine renewable energy integrated utilization systems may include multiple energy forms such as wind, solar, wave, and tidal energy. How to effectively integrate these energy sources to achieve complementarity and optimization is a technical challenge. Research is needed on how to achieve efficient energy utilization through energy management and scheduling to meet the needs of different loads. This includes predicting power generation, configuring energy storage systems, and achieving supply and demand balance. The marine environment is complex and variable, and the system needs to be able to adapt to different environmental conditions, such as wind speed, waves, and tidal currents. This requires the system to have high adaptability and stability. During the system design and optimization process, technical feasibility and economic analysis of the selected technologies and equipment are necessary to ensure the system's economic attractiveness and market competitiveness. Particle Swarm Optimization (PSO) is a commonly used optimization algorithm that finds optimal solutions by simulating the foraging behavior of bird flocks. In the optimal configuration of integrated offshore renewable energy utilization systems, selecting a suitable PSO algorithm version and adjusting parameters according to the optimization objectives and constraints are crucial steps in achieving system optimization. The optimal configuration of integrated offshore renewable energy utilization systems typically involves multiple objectives, such as cost, reliability, and environmental impact. How to handle these multi-objective problems and find the optimal trade-off solution is a technical challenge. Summary of the Invention

[0003] The present invention aims to at least partially solve one of the technical problems in the related art.

[0004] To address this, this invention proposes a capacity optimization configuration method based on the particle swarm optimization algorithm. Through optimized configuration, the overall system cost can be reduced, including initial investment, operation and maintenance expenses, and the cost of energy recovery devices. The particle swarm optimization algorithm can find the optimal solution to the cost function, thereby minimizing the cost.

[0005] To achieve the above objectives, another aspect of the present invention proposes a capacity optimization configuration system based on the particle swarm optimization algorithm.

[0006] To achieve the above objectives, this invention proposes a capacity optimization configuration method based on particle swarm optimization algorithm, comprising:

[0007] The optimization objective and constraints of the marine renewable energy integrated utilization system are determined, and the optimal configuration of the marine renewable energy integrated utilization system is performed using the particle swarm optimization algorithm; wherein, the particle swarm optimization algorithm process is as follows:

[0008] S1, initialize a random position of an array and its associated velocity while satisfying the constraints of inequalities;

[0009] S2, Write out the required fitness functions according to the needs of each system, and then calculate the fitness value of each particle through the function;

[0010] S3, calculate the fitness function for each individual;

[0011] S4, compare the current value with the previous best value pbest of the individual's fitness function; if the current fitness value is smaller, then assign the current coordinates to pbest. i ;

[0012] S5, determine the location of the current global minimum fitness value;

[0013] S6: Compare the current global minimum with the previous global minimum gbest. If the current global minimum is smaller than the previous one, assign the current global minimum and its coordinates to gbest. i ;

[0014] S7, update the speed and individual position according to formulas (1) and (2);

[0015] S8. Repeat steps S2-S7 until the optimization is satisfied or the maximum number of iterations is reached.

[0016] Based on the optimization objective and constraints, and the calculations of particle swarm optimization algorithms S1-S8, the optimal configuration of the marine renewable energy integrated utilization system is completed.

[0017] To achieve the above objectives, a second aspect of this application proposes a capacity optimization configuration system based on a particle swarm optimization algorithm, comprising:

[0018] The optimization objective and constraints of the marine renewable energy integrated utilization system are determined, and the optimal configuration of the marine renewable energy integrated utilization system is performed using the particle swarm optimization algorithm; wherein, the particle swarm optimization algorithm process is as follows:

[0019] S1, initialize a random position of an array and its associated velocity while satisfying the constraints of inequalities;

[0020] S2, Write out the required fitness functions according to the needs of each system, and then calculate the fitness value of each particle through the function;

[0021] S3, calculate the fitness function for each individual;

[0022] S4, compare the current value with the previous best value pbest of the individual's fitness function; if the current fitness value is smaller, then assign the current coordinates to pbest. i ;

[0023] S5, determine the location of the current global minimum fitness value;

[0024] S6: Compare the current global minimum with the previous global minimum gbest. If the current global minimum is smaller than the previous one, assign the current global minimum and its coordinates to gbest. i ;

[0025] S7, update the speed and individual position according to formulas (1) and (2);

[0026] S8. Repeat steps S2-S7 until the optimization is satisfied or the maximum number of iterations is reached.

[0027] Based on the optimization objective and constraints, and the calculations of particle swarm optimization algorithms S1-S8, the optimal configuration of the marine renewable energy integrated utilization system is completed.

[0028] This invention discloses a capacity optimization configuration method and system based on the particle swarm optimization algorithm. Through optimized configuration, the overall system cost can be reduced, including initial investment, operation and maintenance costs, and the cost of energy recovery devices. The particle swarm optimization algorithm can find the optimal solution to the cost function, thereby minimizing costs. Optimized configuration can improve system reliability and ensure the stability of energy supply. System reliability indicators can be evaluated and improved through the optimization algorithm to ensure stable operation under various conditions.

[0029] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0030] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0031] Figure 1 This is a flowchart of the particle swarm optimization algorithm according to an embodiment of the present invention. Detailed Implementation

[0032] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0033] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0034] The following description, with reference to the accompanying drawings, illustrates a capacity optimization configuration method and system based on the particle swarm optimization algorithm according to an embodiment of the present invention.

[0035] Emerging technologies such as Swarm Intelligence (SID) are used to solve many nonlinear engineering problems. Particle Swarm Optimization (PSO) is a field within Swarm Intelligence, inspired by swarming patterns in nature, such as flocked birds. For example, during foraging, there are individuals and the flock. Individuals use their experience to determine the location of food and inform the flock. Upon receiving this information, the flock changes its direction and moves towards the food. As individual information is continuously updated, the flock's direction and position also change, eventually reaching the food. Based on this phenomenon, a Particle Swarm Optimization algorithm is proposed and mathematically described.

[0036] The concept of PSO involves changing the position of each velocity relative to its pd and gd at each time step. The acceleration is generated by random weights and independent random numbers, and is the relative position of its acceleration with respect to pd and gd. The modified velocity and position for each person can be obtained using the current calculated velocity and distance, as shown in formulas (5-1) and (5-2) below:

[0037]

[0038] In the formula: v i The velocity of the i-th particle; x i The position of the i-th particle; k is the number of iterations; w is the inertia weight; c1 and c2 are learning factors; rand() is a random number between 0 and 1; pbest is the historical best value found by each particle itself; gbest is the best value found by all examples.

[0039] In the particle swarm optimization algorithm, the control parameters play an important role in the optimization process. These control parameters include the population size N, the inertia weight w, the learning factor c1c2, the number of iterations k, etc.

[0040] The population size N determines the scope of the algorithm's application. The larger N is, the larger the search range is. Although it is easier to find the optimal solution, it will also increase the time required to find the optimal solution.

[0041] The inertia weight factor w can improve the algorithm's performance, and its value operates within a linear decreasing range of 0.9 to 0.4. A suitable choice of inertia weight provides a balance between global and local development results, seeking the optimal solution through sufficient average iterations. Its value can be set according to the following equation:

[0042]

[0043] In the formula: w max Maximum inertial weight; W min Minimum inertial weight; iter max Maximum number of iterations; current iteration number of iter.

[0044] Learning factors c1 and c2 affect the trajectory of particles and are responsible for regulating the direction of movement of individuals and groups.

[0045] Specifically, the particle swarm optimization algorithm of this application finds the optimal solution by iteratively iterating through the parameters, and then uses constraints or boundary conditions to determine whether it has reached the optimal solution set by the system. The specific algorithm flow is as follows: Figure 1 As shown.

[0046] The optimization objective and constraints of the marine renewable energy integrated utilization system are determined, and the optimal configuration of the marine renewable energy integrated utilization system is performed using the particle swarm optimization algorithm; wherein, the particle swarm optimization algorithm process is as follows:

[0047] S1, initialize a random position of an array and its associated velocity while satisfying the constraints of inequalities;

[0048] S2, Write out the required fitness functions according to the needs of each system, and then calculate the fitness value of each particle through the function;

[0049] S3, calculate the fitness function for each individual;

[0050] S4, compare the current value with the previous best value pbest of the individual's fitness function; if the current fitness value is smaller, then assign the current coordinates to pbest. i ;

[0051] S5, determine the location of the current global minimum fitness value;

[0052] S6: Compare the current global minimum with the previous global minimum gbest. If the current global minimum is smaller than the previous one, assign the current global minimum and its coordinates to pbest. i ;

[0053] S7, update the speed and individual position according to formulas (1) and (2);

[0054] S8. Repeat steps S2-S7 until the optimization is satisfied or the maximum number of iterations is reached.

[0055] Based on the optimization objective and constraints, and the calculations of particle swarm optimization algorithms S1-S8, the optimal configuration of the marine renewable energy integrated utilization system is completed.

[0056] Specifically, as an independent island microgrid system, optimizing the capacity of the marine renewable energy integrated utilization system is a crucial step in system research. Compared to power generation systems that can be integrated into a large power grid, renewable energy power generation systems have higher requirements for the external environment. Changes in external natural conditions can significantly impact the system's stability. Therefore, to improve the system's power generation performance, multi-energy complementary power generation methods can be considered, and their capacity can be optimized. During the capacity optimization process, the system's operational economy, power supply reliability, and energy utilization rate are all important considerations. Given a defined system structure and parameters, the marine renewable energy integrated utilization system studied in this invention needs to identify suitable optimization objectives and constraints, and then combine them with appropriate intelligent optimization algorithms to complete the optimized configuration of the system.

[0057] The capacity optimization configuration of the system of the present invention includes two optimization objectives: system reliability and economy [70: reliability means that the system can operate stably and meet the electricity demand of Daguan Island Village; economy means that the overall cost of the system platform is minimized.

[0058] There are two main methods for solving multi-objective optimization problems: Method one is to transform multiple objectives into a single objective for solution. Currently, commonly used transformation methods include the linear weighting method and the principal objective method. Method two is to use a hierarchical sequence method, arranging multiple objectives in order of priority, and then searching for the optimal solution, ensuring that each optimal solution satisfies the objective of the next higher level. Finally, through iterative processes, the optimal solution is found. This invention selects the linear weighting method to integrate the two objectives, and sets the weighting coefficients based on experience and data from domestic and international research.

[0059] Specifically,

[0060] System cost function

[0061] 1. System equipment investment cost

[0062] The power investment cost of the system depends on the type of power source for each distributed power source. The main equipment on the offshore renewable energy integrated utilization system power generation platform includes wind power generation equipment, tidal power generation equipment, solar photovoltaic power generation equipment, salinity gradient power generation equipment, and battery storage equipment. For ease of calculation, it is assumed that the products used for each type of power generation equipment are of the same model. Assuming that each distributed power source has the same interest rate and the same service life, the formula for calculating its equipment investment cost is shown in equation (5-4):

[0063]

[0064] Where: C1 is the equivalent annual cost of the initial investment in the system power supply, in ten thousand yuan / year; C INI Initial investment cost of power supply, in ten thousand yuan; discount rate (r); service life of equipment, in years.

[0065] 2. Other system investment costs

[0066] In addition to the distributed power supply units, the system also includes a seawater desalination unit and a battery energy storage unit. Assume the initial investment cost of the seawater desalination unit is a constant C. sail Then the formulas for calculating the other investment costs of the system are shown in equation (5-5):

[0067]

[0068] Where: the equivalent annual cost of other initial investments in the C2 system, in ten thousand yuan / year;

[0069] 3. System operation and maintenance costs

[0070] The costs of system operation and maintenance vary depending on the system equipment, and these costs increase with the number of years the equipment has been in use. For ease of calculation, this invention estimates the system operation and maintenance costs based on an average annual cost, using the following formula:

[0071]

[0072] In the formula: C oM System operation and maintenance costs, 10,000 yuan; C m The annual operating and maintenance cost of the equipment is 10,000 yuan. The annual inflation rate is taken as 0.054%.

[0073] 4. Equivalent annual total investment cost of the system

[0074] Based on the above analysis of system power investment costs, other investment costs, and operation and maintenance expenses, the equivalent annual total investment cost ACS(x) of the system is the sum of all items:

[0075]

[0076] System reliability indicators

[0077] In setting the objective function of a system, in addition to the system's economic efficiency, its reliability must also be considered. It is known that the system's stability can be evaluated using the load failure rate (LPSP). Its mathematical expression is as follows:

[0078]

[0079] Where: Puhe(t) is the total system load power in hour t; Loss(t) is the load power loss in hour t.

[0080] Based on the above analysis of the system's economy and reliability, a penalty factor is defined to transform the multi-objectives in the optimal configuration into a single objective function. This allows the system to achieve reliability and stability while minimizing the equivalent annual investment cost. The integrated objective function is shown in equation (5-9).

[0081] F = ACS(x) + α|LPSP(x) - LPSP set | (5-9)

[0082] Where: F is the objective function for optimal configuration; ACS(x) is the total investment cost in the equivalent year, in ten thousand yuan; α is the penalty factor, with a fixed value of 2500; LPSP(x) is the actual value of the load failure rate; LPSP set The setting value for load power failure rate.

[0083] Therefore, the closer the actual value of the load power failure rate is to the set value, the more stable the system is.

[0084] Energy surplus rate

[0085] This invention uses the energy surplus rate to measure the system's energy utilization, which is defined as the electrical energy wasted by the system during the evaluation period divided by the total system load.

[0086]

[0087] In the formula: P exc (t) The excess power of the system in hour t.

[0088] Furthermore, for renewable energy integrated power generation platforms, constraints can be considered including the number or capacity of distributed power sources, energy storage system constraints, distributed power source-load matching constraints, and load failure rate constraints. The specific formulas for each constraint are shown below:

[0089] I. Installation Quantity Constraints

[0090] The marine renewable energy integrated utilization system platform designed in this invention is placed in the sea area near Daguan Island, so the number of system devices installed will be constrained by the platform size, geographical environment and other conditions.

[0091] II. Constraints of Energy Storage Systems

[0092] Battery energy storage systems play a crucial role in the power generation platform of renewable energy integrated utilization systems, including storing electrical energy, stabilizing voltage, and balancing loads. The constraints on energy storage systems can be divided into two aspects: battery capacity constraints and power constraints.

[0093] III. Power Supply and Load Matching Constraints

[0094] When designing the power generation capacity of the system, the load demand must be fully considered in order to ensure a stable output when supplying power to the outside world.

[0095] IV. Load power failure rate constraint

[0096] Theoretical analysis shows that, in order to ensure the system can operate stably and reliably, the load power failure rate must be less than the set load power failure rate value.

[0097] Based on the above system analysis, the constraints in the capacity optimization configuration model of the renewable energy comprehensive utilization system can be summarized as follows:

[0098]

[0099] Furthermore, the system simulation parameters were set as follows: wind turbine generator with a rated power of 20kW, cut-in wind speed of 4m / s, rated wind speed of 14m / s, and cut-out wind speed of 25m / s; photovoltaic power generation system with a rated power of 60kW and a solar irradiance of 1000W / m² under standard conditions. 2The reference temperature is 25℃; in the tidal power generation system, the rated power of the turbine is 50kW; the rated power of the salinity gradient power generation system is 5kW; the rated capacity of the battery energy storage system is 500Ah, and the initial state of charge (SOC) is 0.7. Optimization calculations are performed using relevant software based on the distribution functions of wind speed and light intensity, as well as the input data of ambient temperature and load. After program debugging, the final particle population size is set to 30, particle dimension to 4, iteration count to 100, learning factors c1 and c2 to 2, inertia weight to 0.7, load failure rate to 0, and the power load of Daguan Island Village to 73.2kW. The maximum number of wind turbine generators, photovoltaic arrays, turbine generators, battery banks, and permeable membrane modules that can be installed in the salinity gradient power system are 2, 1000, 2, 1500, and 1000, respectively. Based on the set parameter data and the parameter data of the marine renewable energy integrated utilization system, the particle swarm optimization algorithm is used to optimize the system capacity configuration, and the number of equipment installed after optimization is converted into the corresponding rated power.

[0100] According to embodiments of the present invention, a capacity optimization configuration method based on particle swarm optimization (PSO) can reduce the overall system cost, including initial investment, operation and maintenance costs, and the cost of energy recovery devices, through optimized configuration. PSO can find the optimal solution to the cost function, thereby minimizing costs. Optimized configuration can improve system reliability and ensure the stability of energy supply. System reliability indicators can be evaluated and improved through optimization algorithms to ensure stable operation under various conditions. PSO can effectively control the energy surplus rate, ensuring efficient energy utilization and avoiding resource waste. Optimized configuration can consider environmental factors, reducing emissions and improving energy efficiency to mitigate environmental impact. PSO can help find the optimal energy conversion and utilization methods, improving the overall energy efficiency of the system.

[0101] Furthermore, this invention also proposes a capacity optimization configuration system based on particle swarm optimization algorithm, comprising:

[0102] The optimization objective and constraints of the marine renewable energy integrated utilization system are determined, and the optimal configuration of the marine renewable energy integrated utilization system is performed using the particle swarm optimization algorithm; wherein, the particle swarm optimization algorithm process is as follows:

[0103] S1, initialize a random position of an array and its associated velocity while satisfying the constraints of inequalities;

[0104] S2, Write out the required fitness functions according to the needs of each system, and then calculate the fitness value of each particle through the function;

[0105] S3, calculate the fitness function for each individual;

[0106] S4, compare the current value with the previous best value pbest of the individual's fitness function; if the current fitness value is smaller, then assign the current coordinates to pbest. i ;

[0107] S5, determine the location of the current global minimum fitness value;

[0108] S6: Compare the current global minimum with the previous global minimum gbest. If the current global minimum is smaller than the previous one, assign the current global minimum and its coordinates to gbest. i ;

[0109] S7, update the speed and individual position according to formulas (1) and (2);

[0110] S8. Repeat steps S2-S7 until the optimization is satisfied or the maximum number of iterations is reached.

[0111] Based on the optimization objective and constraints, and the calculations of particle swarm optimization algorithms S1-S8, the optimal configuration of the marine renewable energy integrated utilization system is completed.

[0112] Furthermore, formulas (1) and (2):

[0113]

[0114] In the formula: v i The velocity of the i-th particle; x i The position of the i-th particle; k is the number of iterations; w is the inertia weight; c1 and c2 are learning factors; rand() is a random number between 0 and 1; pbest is the historical best value found by each particle itself; gbest is the best value found by all examples.

[0115] Furthermore, the capacity optimization configuration of the marine renewable energy integrated utilization system includes two optimization objectives. The two optimization objectives are integrated using a linear weighting method, and the weighting coefficients are set.

[0116] Furthermore, the corresponding objective function includes a system cost function, a system reliability index, and an energy surplus rate; wherein the system cost function includes system equipment investment cost, other system investment cost, system operation and maintenance costs, and the equivalent annual total investment cost of the system; the constraints include: installation quantity constraints and energy storage system constraints; wherein the energy storage system constraints include constraints on battery capacity, battery power, power supply and load matching constraints, and load failure rate constraints.

[0117] According to embodiments of the present invention, a capacity optimization configuration system based on particle swarm optimization (PSO) can reduce the overall system cost, including initial investment, operation and maintenance costs, and the cost of energy recovery devices, through optimized configuration. PSO can find the optimal solution to the cost function, thereby minimizing costs. Optimized configuration can improve system reliability and ensure the stability of energy supply. System reliability indicators can be evaluated and improved through optimization algorithms to ensure stable operation under various conditions. PSO can effectively control the energy surplus rate, ensuring efficient energy utilization and avoiding resource waste. Optimized configuration can consider environmental factors, reducing emissions and improving energy efficiency to mitigate environmental impact. PSO can help find the optimal energy conversion and utilization methods, improving the overall energy efficiency of the system.

[0118] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0119] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A capacity optimization configuration method based on particle swarm optimization algorithm, characterized in that, include: The optimization objective and constraints of the marine renewable energy integrated utilization system are determined, and the optimal configuration of the marine renewable energy integrated utilization system is performed using the particle swarm optimization algorithm; wherein, the particle swarm optimization algorithm process is as follows: S1, initialize a random position of an array and its associated velocity while satisfying the constraints of inequalities; S2, Write out the required fitness functions according to the needs of each system, and then calculate the fitness value of each particle through the function; S3, calculate the fitness function for each individual; S4, compare the current value with the previous best value pbest of the individual's fitness function; if the current fitness value is smaller, then assign the current coordinates to pbest. i ; S5, determine the location of the current global minimum fitness value; S6: Compare the current global minimum with the previous global minimum gbest. If the current global minimum is smaller than the previous one, assign the current global minimum and its coordinates to gbest. i ; S7, update the speed and individual position according to formulas (1) and (2); S8. Repeat steps S2-S7 until the optimization is satisfied or the maximum number of iterations is reached. Based on the optimization objective and constraints, and the calculations of particle swarm optimization algorithms S1-S8, the optimal configuration of the marine renewable energy integrated utilization system is completed.

2. The method according to claim 1, characterized in that, Formulas (1) and (2): In the formula: v i The velocity of the i-th particle; x i The position of the i-th particle; k is the number of iterations; w is the inertia weight; c1 and c2 are learning factors; rand() is a random number between 0 and 1; pbest is the historical best value found by each particle itself; gbest is the best value found by all examples.

3. The method according to claim 2, characterized in that, The capacity optimization configuration of the marine renewable energy integrated utilization system includes two optimization objectives. The two optimization objectives are integrated using a linear weighting method, and the weighting coefficients are set.

4. The method according to claim 3, characterized in that, The corresponding objective functions include the system cost function, system reliability index, and energy surplus rate; wherein, the system cost function includes system equipment investment cost, system other investment cost, system operation and maintenance cost, and the equivalent annual total investment cost of the system; the constraints include: installation quantity constraints and energy storage system constraints; wherein, the energy storage system constraints include constraints on battery capacity, constraints on battery power, power supply and load matching constraints, and load failure rate constraints.

5. A capacity optimization configuration system based on particle swarm optimization algorithm, characterized in that, include: The optimization objective and constraints of the marine renewable energy integrated utilization system are determined, and the optimal configuration of the marine renewable energy integrated utilization system is performed using the particle swarm optimization algorithm; wherein, the particle swarm optimization algorithm process is as follows: S1, initialize a random position of an array and its associated velocity while satisfying the constraints of inequalities; S2, Write out the required fitness functions according to the needs of each system, and then calculate the fitness value of each particle through the function; S3, calculate the fitness function for each individual; S4, compare the current value with the previous best value pnest of the individual's fitness function; if the current fitness value is small, then assign the current coordinates to pnest. i ; S5, determine the location of the current global minimum fitness value; S6: Compare the current global minimum with the previous global minimum gbest. If the current global minimum is smaller than the previous one, assign the current global minimum and its coordinates to gbest. i ; S7, update the speed and individual position according to formulas (1) and (2); S8. Repeat steps S2-S7 until the optimization is satisfied or the maximum number of iterations is reached. Based on the optimization objective and constraints, and the calculations of particle swarm optimization algorithms S1-S8, the optimal configuration of the marine renewable energy integrated utilization system is completed.

6. The system according to claim 5, characterized in that, Formulas (1) and (2): In the formula: v i The velocity of the i-th particle; x i The position of the i-th particle; k is the number of iterations; w is the inertia weight; c1 and c2 are learning factors; rand() is a random number between 0 and 1; pbest is the historical best value found by each particle itself; gbest is the best value found by all examples.

7. The system according to claim 6, characterized in that, The capacity optimization configuration of the marine renewable energy integrated utilization system includes two optimization objectives. The two optimization objectives are integrated using a linear weighting method, and the weighting coefficients are set.

8. The system according to claim 7, characterized in that, The corresponding objective functions include the system cost function, system reliability index, and energy surplus rate; wherein, the system cost function includes system equipment investment cost, system other investment cost, system operation and maintenance cost, and the equivalent annual total investment cost of the system; the constraints include: installation quantity constraints and energy storage system constraints; wherein, the energy storage system constraints include constraints on battery capacity, constraints on battery power, power supply and load matching constraints, and load failure rate constraints.

Images