Optimal regulation method and system for integrated energy system, electronic device and medium

Abstract

The application provides an optimization regulation method and system of a comprehensive energy system, an electronic device and a medium, and belongs to the field of comprehensive energy dispatching. The optimization regulation method comprises the following steps: establishing an optimization dispatching model of the comprehensive energy system; distributing the power of each device in the comprehensive energy system by taking the minimum total operation cost of the comprehensive energy system as the target of the optimization dispatching model; calculating the optimal solution of the optimization dispatching model by using an improved whale optimization algorithm; the optimal solution is the optimal power distribution of each device in the comprehensive energy system; and the improved whale optimization algorithm is that the neighborhood search is performed by using the von Neumann topology structure and the convergence factor is adjusted in the whale individual position updating step of the whale optimization algorithm. By improving the whale optimization algorithm, the neighborhood search is performed by using the von Neumann topology structure and the convergence factor is adjusted in the whale individual position updating step, so that the situation of falling into a local optimum in the solving process is avoided, the accuracy of the optimal solution is improved, and the utilization rate of the comprehensive energy system is improved.

Description

Technical Field

[0001] This invention relates to the field of integrated energy dispatching, and in particular to an optimized control method, system, electronic device, and medium for integrated energy systems based on an improved whale algorithm. Background Technology

[0002] With the increasing daily demands of society and the gradual emergence of the energy crisis, renewable energy and integrated energy systems that make full use of energy have developed significantly. An integrated energy system is a system with a complementary structure of multiple energy sources and a high energy utilization rate.

[0003] For the problem of optimizing and regulating integrated energy systems, it is necessary to first establish a system optimization model with multiple energy sources, determine the conditions of mutual influence and constraint between the various energy sources, and take the overall system operating cost as the objective function. In order to obtain the optimal solution, the traditional whale algorithm is simple and convenient to operate and has few parameters, but it is easy to get trapped in local optima and has low convergence accuracy, and cannot quickly and accurately find the optimal solution. Summary of the Invention

[0004] The purpose of this invention is to provide an optimization method for integrated energy systems based on an improved whale algorithm, which can accurately calculate the optimal power allocation scheme for each device in an integrated energy storage system and improve the utilization rate of the integrated energy system.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] An optimized control method for an integrated energy system includes:

[0007] An optimal scheduling model for an integrated energy system is established; the optimal scheduling model allocates the power of each device in the integrated energy system with the goal of minimizing the total operating cost of the integrated energy system.

[0008] An improved whale algorithm is used to calculate the optimal solution of the optimized scheduling model; the optimal solution is the optimal power allocation of each device in the integrated energy system; the improved whale algorithm uses a von Neumann topology to perform neighborhood search and adjust the convergence factor in the whale individual position update step of the whale algorithm.

[0009] Optionally, the objective function of the optimized scheduling model is:

[0010]

[0011] Where m is the objective function value, M1 is the operating cost of the integrated energy system, M2 is the loss and repair cost of the integrated energy system, T is the maximum control time, and M CT (t) represents the operating cost of the gas turbine at time t, M GB$(t)$ is the fuel cost of the gas boiler at time $t$, $M$ UM $(t)$ is the management cost of the integrated energy system at time $t$, $M$ Buy $(t)$ is the electricity purchase cost of the integrated energy system from the power grid at time $t$, $M$ again $(t)$ is the restart cost of the integrated energy system at time $t$.

[0012] Optionally, the improved whale algorithm is used to calculate the optimal solution of the optimal scheduling model, which specifically includes:

[0013] Initialize the whale population to obtain the initial population and set the maximum number of iterations; the initial population includes multiple whale individuals and the initial positions of each whale individual; the initial position of each whale individual represents a set of power allocations of each device in the integrated energy system;

[0014] Calculate the objective function values of each whale individual in the initial population;

[0015] For the $i$-th iteration, take the preliminary position of the whale individual with the smallest objective function value in the $i$-th generation population as the current optimal position; $0 < i$; the first generation population is the initial population; the preliminary position of the whale individual in the first generation population is the initial position of the corresponding whale individual;

[0016] Calculate the $i$-th convergence factor according to the number of iterations and the maximum number of iterations;

[0017] For any whale individual in the $i$-th generation population, calculate the updated position of the whale individual according to the current optimal position, the preliminary position of the whale individual, and the $i$-th convergence factor;

[0018] Judge whether the distance between the initial position and the updated position of the whale individual is greater than the set threshold;

[0019] If the distance between the initial position and the updated position of the whale individual is greater than the set threshold, perform neighborhood search using the von Neumann topology structure to determine the optimal position within the neighborhood;

[0020] Update the current optimal position according to the optimal position within the neighborhood;

[0021] Update the $i$-th convergence factor according to the number of iterations and the maximum number of iterations;

[0022] Determine the final position of the whale individual according to the updated current optimal position, the updated $i$-th convergence factor, and the preliminary position of the whale individual;

[0023] If the distance between the initial position and the updated position of the whale individual is less than or equal to the set threshold, take the updated position of the whale individual as the final position of the whale individual;

[0024] Based on the final position of each whale individual in the i-th generation population, calculate the objective function value for each whale individual, sort the whale individuals according to the magnitude of the objective function value, and select the first N whale individuals as the (i+1)-th generation population; the initial position of the whale individual in the (i+1)-th generation population is the final position of the corresponding whale individual in the i-th generation population.

[0025] Determine if the maximum number of iterations has been reached. If so, take the final position of the whale individual with the smallest objective function value in the i-th generation population as the optimal solution of the optimization scheduling model. Otherwise, proceed to the (i+1)-th iteration.

[0026] Optionally, the i-th convergence factor can be calculated using the following formula:

[0027]

[0028] in, Let i be the i-th convergence factor. max This represents the maximum number of iterations.

[0029] Optionally, the updated position of an individual whale in the i-th generation population can be calculated using the following formula:

[0030]

[0031] in, This represents the updated position of a whale individual in the i-th generation population. This represents the current optimal position at the i-th iteration. As the first coefficient, As the second coefficient, Let be the distance from the initial position to the current optimal position of an individual whale in the i-th generation population. Let r be the i-th convergence factor, and r be a random number between 0 and 1.

[0032] Optionally, the current optimal position at the i-th iteration can be updated using the following formula:

[0033]

[0034] in, Let P be the current optimal position after the update in the i-th iteration. best The optimal position within the neighborhood. This represents the current optimal position during the i-th iteration.

[0035] Optionally, the i-th convergence factor can be updated using the following formula:

[0036]

[0037] in, Let i be the updated convergence factor. max This represents the maximum number of iterations.

[0038] To achieve the above objectives, the present invention also provides the following solution:

[0039] An optimization and control system for an integrated energy system, comprising:

[0040] The model building unit is used to build an optimal scheduling model for the integrated energy system; the optimal scheduling model aims to minimize the total operating cost of the integrated energy system and allocates the power of each device in the integrated energy system.

[0041] The optimal solution calculation unit, connected to the model establishment unit, is used to calculate the optimal solution of the optimized scheduling model using an improved whale algorithm; the optimal solution is the optimal power allocation of each device in the integrated energy system; the improved whale algorithm uses a von Neumann topology for neighborhood search and increases the search step size in the whale individual position update step of the whale algorithm.

[0042] To achieve the above objectives, the present invention also provides the following solution:

[0043] An electronic device includes a memory and a processor, the memory storing a computer program, and the processor running the computer program to enable the electronic device to perform the above-described integrated energy system optimization and control method.

[0044] To achieve the above objectives, the present invention also provides the following solution:

[0045] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for optimizing and controlling an integrated energy system.

[0046] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects: With the goal of minimizing the total operating cost of the integrated energy system, an optimal scheduling model for the integrated energy system is established. An improved whale algorithm is used (in the whale individual position update step of the whale algorithm, a von Neumann topology is used for neighborhood search and the convergence factor is adjusted) to calculate the optimal solution of the optimal scheduling model; the optimal solution is the optimal power allocation for each device in the integrated energy system; by improving the whale algorithm, the situation of getting trapped in local optima during the solution process is avoided, the accuracy of the optimal solution is improved, and thus the utilization rate of the integrated energy system is improved. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of the optimized control method for the integrated energy system of the present invention;

[0049] Figure 2 The flowchart shows the solution to the optimization scheduling model using the improved whale algorithm.

[0050] Figure 3 A comparison chart of the control results of the improved whale algorithm and the traditional whale algorithm;

[0051] Figure 4 This is a schematic diagram of the module of the optimized control system of the integrated energy system of the present invention.

[0052] Symbol explanation:

[0053] Model building unit-1, optimal solution calculation unit-2. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0055] The purpose of this invention is to provide an optimization control method, system, electronic equipment, and medium for integrated energy systems. The aim is to solve the optimization problem of achieving the lowest total operating cost for combined cooling, heating, and power (CCHP) integrated energy systems while satisfying constraints on cooling, heating, and electricity balance, as well as constraints on energy storage devices and electrothermal / electric cooling conversion devices. By improving the whale algorithm, the invention accurately, rapidly, and sensitively solves the optimization scheduling model, thereby achieving effective optimization of each device within the integrated energy system.

[0056] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] Example 1

[0058] like Figure 1 As shown, the optimization and control method for the integrated energy system of the present invention includes:

[0059] S1: Establish an optimal scheduling model for the integrated energy system. The optimal scheduling model aims to minimize the total operating cost of the integrated energy system and allocates the power of each device in the integrated energy system.

[0060] The integrated energy system includes a power supply unit, a heating unit, and a cooling unit. The power supply unit is a gas turbine. The heating unit includes a waste heat boiler and a gas-fired boiler. The cooling unit is an electric chiller.

[0061] The power generated by the gas turbine is:

[0062]

[0063] in, The power generation capacity of the j-th gas turbine is expressed in watts (W / m²). C,j The power generated by the j-th gas turbine is expressed in watts (W / m). Let be the energy conversion efficiency value of the j-th gas turbine, in MW.

[0064] The mathematical model for the cooling, heating, and electrical loads of a gas turbine is as follows:

[0065]

[0066] Among them, M C,j The quantity of gas consumed by the j-th gas turbine for power generation, in m³. 3 , Let L be the energy conversion efficiency value of the j-th gas turbine, in MW. ch4 This represents the minimum calorific value of natural gas, expressed in MWh / m³. 3 .

[0067] In integrated energy systems, waste heat boilers generate thermal power from the low-grade heat energy produced when gas turbines are working, thereby achieving the cascade utilization of energy.

[0068] The formula for calculating thermal power is:

[0069]

[0070] Among them, Q rec The thermal power generated by the waste heat boiler is expressed in watts (W / m²). θ rec Whether the waste heat boiler is running, and when the waste heat boiler is running, θ rec =1, θ when the waste heat boiler is not running rec =0, Q represents the energy conversion efficiency of a waste heat boiler. C This refers to the thermal power output of the gas turbine.

[0071] The mathematical model for a gas-fired boiler is as follows:

[0072]

[0073] Among them, Q GB This refers to the thermal power output of the gas-fired boiler, measured in watts (W). For the heat conversion efficiency of a gas-fired boiler, M GB This refers to the amount of natural gas consumed by a gas-fired boiler to output a unit of heat power, expressed in cubic meters (m³). 3 .

[0074] The mathematical model of the electric chiller is:

[0075] C AC =P AC ·θ AC ;

[0076] Among them, C AC The power output of an electric chiller, measured in watts (W / m) or power units (P). AC θ represents the electrical power required by the electric chiller during cooling, expressed in watts (W). AC The coefficient of performance (COP) is used for cooling.

[0077] Specifically, the objective function of the optimized scheduling model is:

[0078]

[0079] Where m is the objective function value, i.e., the total operating cost of the integrated energy system; M1 is the operating cost of the integrated energy system in yuan; M2 is the loss repair cost of the integrated energy system in yuan; T is the maximum control time, which in this embodiment is T = 24. CT (t) represents the operating cost of the gas turbine at time t, in yuan (m). GB (t) represents the fuel cost of the gas-fired boiler at time t, in yuan (m). UM (t) represents the management cost of the integrated energy system at time t, in yuan (M). Buy (t) represents the cost of electricity purchased from the grid by the integrated energy system at time t, in yuan, M again (t) represents the restart cost of the integrated energy system at time t, in yuan.

[0080] The management cost of an integrated energy system is:

[0081]

[0082] in, P is the management coefficient for equipment b in the integrated energy system, expressed in yuan / MW. b (t) represents the output power of device b at time t, in watts (W), and B represents the total number of devices in the integrated energy system.

[0083] The cost of purchasing electricity from the grid for the integrated energy system is:

[0084] M Buy (t)=J Buy (t)P Buy (t);

[0085] Among them, J Buy (t) represents the unit price of electricity sold by the power grid at time t, with a unit price of yuan / MW. Buy (t) represents the efficiency of purchasing electricity from the grid at time t, in W / m.

[0086] The constraints of the optimized scheduling model are:

[0087]

[0088] Q rec (t)+Q GB (t)=Q AC (t)+Q load (t);

[0089] C AC (t)=C load (t);

[0090] Among them, P load (t) represents the electrical load of the integrated energy system at time t, in watts (W) and kilowatts (Q). load (t) represents the heat load of the integrated energy system at time t, in W / m³, C. load (t) represents the cooling load of the integrated energy system at time t, in watt-hours (Wm). Let P be the power generation capacity of the gas turbine at time t. Buy (t) represents the power (in MW) that the integrated energy system purchases or sells to the grid at time t. Buy (t) is a positive number representing the integrated energy system purchasing electricity from the grid, P Buy (t) being a negative number indicates that the integrated energy system sells electricity to the grid, P bat,ch (t) represents the electrical power absorbed by the integrated energy system at time t, i.e., the charging power, P. bat,dis (t) represents the electrical power released by the integrated energy system at time t, i.e., the discharge power, P. AC (t) represents the electrical power consumed by the electric chiller at time t, in MW and Q. rec (t) represents the thermal power generated by the waste heat boiler at time t, in watts (W / m²) and Q. GB (t) represents the thermal power generated by the gas-fired boiler at time t, in MW and Q. AC (t) represents the heat power required by the electric chiller at time t, in MW and C. AC(t) represents the cooling power generated by the electric chiller at time t, in watts (W).

[0091] S2: An improved whale algorithm is used to calculate the optimal solution of the optimized scheduling model. The optimal solution is the optimal power allocation for each device in the integrated energy system. The improved whale algorithm employs a von Neumann topology for neighborhood search and adjusts the convergence factor in the whale individual position update step. Specifically, the improved whale algorithm performs multi-dimensional optimization of the objective function on a 24-hour scale based on constraints.

[0092] The improved whale algorithm provided by this invention introduces a von Neumann topology and a control parameter reduction strategy to adjust the search step size, thereby enhancing the algorithm's global search capability and local search speed, and avoiding local optima.

[0093] The whale algorithm simulates the hunting behavior of humpback whales, known as the bubble web attack. This attack is accomplished by humpback whales forming unique bubbles along a spiral path when surrounding their prey. In the early stages of a whale pod's hunt, since the location of the optimal individual is not yet determined in space, the optimal individual is set as the target prey. After setting the search target, the whale updates its own position by searching for other target points.

[0094] The general idea of ​​the improved whale algorithm used in this invention is as follows: First, the whale pod searches for prey, quickly surrounds it, and selects the optimal target prey (current optimal position). At this point, the position is updated, and the optimal position X* of the individual whale in the current pod is recorded. New parameters A, E, and α are set, and the position is updated again. If the newly obtained position does not match the previous position, the whale swims away, the position update formula is modified, and a topological structure is introduced to change the convergence factor in the traditional algorithm. The position is recalculated, and it is determined whether the number of individual whales has reached its maximum value and whether the number of iterations has reached its maximum. If so, the algorithm terminates, and the optimal position of the individual whale is obtained.

[0095] It should be noted that this invention involves... The letter variables all represent the corresponding vectors.

[0096] Specifically, such as Figure 2 As shown, step S2 includes:

[0097] S201: Initialize the whale population to obtain an initial population and set the maximum number of iterations. The initial population includes multiple individual whales and the initial position of each individual whale. The initial position of each individual whale represents the power allocation of each device in a set of integrated energy systems.

[0098] That is, a solution vector of the objective function that satisfies the constraint conditions is randomly generated as the initial position of the whale individual. According to the established optimal scheduling model, the humpback whale can quickly surround the prey after finding it and continuously update its position, taking the position of the whale group currently in the best encirclement position as the target prey or approaching the best target prey.

[0099] S202: Calculate the objective function values of each whale individual in the initial population.

[0100] S203: For the i-th iteration, take the preliminary position of the whale individual with the minimum objective function value in the i-th generation population as the current optimal position. 0 < i. The first generation population is the initial population. The preliminary position of the whale individual in the first generation population is the initial position of the corresponding whale individual.

[0101] S204: Calculate the i-th convergence factor according to the iteration number and the maximum iteration number.

[0102] Specifically, the following formula is used to calculate the i-th convergence factor:

[0103]

[0104] Where is the i-th convergence factor, and i max is the maximum iteration number.

[0105] S205: For any whale individual in the i-th generation population, calculate the updated position of the whale individual according to the current optimal position, the preliminary position of the whale individual, and the i-th convergence factor.

[0106] Specifically, the following formula is used to calculate the updated position of the whale individual in the i-th generation population:

[0107]

[0108] Where is the updated position of the whale individual in the i-th generation population, is the current optimal position at the i-th iteration, is the first coefficient, is the second coefficient, is the distance from the preliminary position of the whale individual in the i-th generation population to the current optimal position, is the i-th convergence factor. In this embodiment, the convergence factor linearly decreases from 1 to 0, and r is a random number between 0 and 1.

[0109] Before step S205, the coefficients A, E, and the convergence factor can also be updated using the following formula:

[0110]

[0111] A = 3α(i)·r-α(i);

[0112] E = 3·r.

[0113] S206: Determine whether the distance between the initial position and the updated position of the individual whale is greater than a set threshold. In this embodiment, the threshold is set to 0.2.

[0114] S207: If the distance between the initial position and the updated position of the individual whale is greater than a set threshold, then a von Neumann topology is used to perform a neighborhood search to determine the optimal position within the neighborhood.

[0115] S208: Update the current optimal position based on the optimal position within the neighborhood.

[0116] Specifically, the current optimal position at the i-th iteration is updated using the following formula:

[0117]

[0118] in, Let P be the current optimal position after the update in the i-th iteration. best The optimal position within the neighborhood is the optimal position of the random search agent within the von Neumann topology. The minimum fitness function of each whale search agent within the neighborhood corresponds to the individual's historical optimal position. This represents the current optimal position during the i-th iteration.

[0119] S209: Update the i-th convergence factor based on the number of iterations and the maximum number of iterations.

[0120] Specifically, the i-th convergence factor is updated using the following formula:

[0121]

[0122] in, Let i be the updated convergence factor. max This represents the maximum number of iterations.

[0123] S210: Determine the final position of the whale individual based on the updated current optimal position, the updated i-th convergence factor, and the initial position of the whale individual.

[0124] S211: If the distance between the initial position and the updated position of the individual whale is less than or equal to a set threshold, then the updated position of the individual whale is taken as the final position of the individual whale. This is a whale spiral swimming maneuver used to simulate a whale using spiral motion to capture prey.

[0125] S212: Based on the final positions of each whale individual in the i-th generation population, calculate the objective function value for each whale individual. Sort the whale individuals according to the magnitude of the objective function value, and select the top N whale individuals as the (i+1)-th generation population. The initial position of the whale individual in the (i+1)-th generation population is the final position of the corresponding whale individual in the i-th generation population.

[0126] S213: Determine whether the number of iterations has reached the maximum number of iterations. If so, take the final position of the whale individual with the smallest objective function value in the i-th generation population as the optimal solution of the optimization scheduling model. Otherwise, proceed to the (i+1)-th iteration.

[0127] To better understand the solution of this invention, the optimization and control process of the integrated energy system will be further explained below.

[0128] First, using information obtained from literature reviews and on-site surveys, stratified sampling of the integrated energy system comprising wind, solar, and cooling / heating loads was conducted using LHS (Latin hypercube sampling) to obtain typical scenarios. The conditions for cooling, heating, and electrical balance within the integrated energy system were determined, and the relationships between them were established.

[0129] Secondly, the final optimized scheduling model is obtained by adding the various parts of the mathematical model established by the source and load.

[0130] Finally, an improved whale algorithm was adopted to perform multi-dimensional optimization of the objective function over 24 hours under constraints. Specifically, the whale population was set to N, with each individual in the population satisfying the constraints. The initial number of iterations started from 1, and the maximum number of iterations was set to i. max The process involves initializing the whale population size using a function, comparing each individual whale to the whale with the optimal objective function value, and identifying the whale with the smallest objective function value as the optimal individual. The number of variables in the objective function is considered the dimension of the whale search space. Each solution vector is considered the position of a whale in the space. The objective function value is considered the fitness function value. The optimal individual is then updated: the fitness function value of each individual whale is compared to that of the optimal individual. The whale with the smaller objective function value is updated as the optimal individual; if they are equal, the optimal individual remains unchanged. The updated optimal individual, its fitness function value, and its position are recorded.

[0131] This invention utilizes MATLAB for simulation experiments, obtaining new parameters by adopting a new topology and increasing the step size. The integrated energy system used in the simulation mainly includes a combined heat, cooling, and power (CHP) system such as a gas turbine, waste heat boiler, gas boiler, and electric chiller. The control results are compared in Table 1, and the system operating costs are compared in... Figure 3 As shown.

[0132] Table 1 Comparison of Regulation Results

[0133] data Improved Whale Algorithm Whale Algorithm <![CDATA[M CT ]]> 1034.24 1423.23 <![CDATA[M1]]> 7928.36 9345.34

[0134] Compared with existing technologies, this invention, when solving for the global optimal solution of a comprehensive energy system, introduces a von Neumann topology and an improved control parameter reduction strategy to adjust the search step size on the basis of the traditional whale algorithm. On the one hand, it improves the global search capability of the whale algorithm, enhances the global search capability and local search rate, and avoids being limited to local optima; on the other hand, it enhances population diversity and improves the convergence accuracy of the algorithm.

[0135] Example 2

[0136] In order to implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, an optimization and control system for an integrated energy system is provided below.

[0137] like Figure 4 As shown, the integrated energy system optimization and control system provided in this embodiment includes: a model establishment unit 1 and an optimal solution calculation unit 2.

[0138] The model building unit 1 is used to establish an optimal scheduling model for the integrated energy system. This optimal scheduling model aims to minimize the total operating cost of the integrated energy system and allocates power to each device within the system.

[0139] The optimal solution calculation unit 2 is connected to the model building unit 1. The optimal solution calculation unit 2 is used to calculate the optimal solution of the optimized scheduling model using an improved whale algorithm. The optimal solution is the optimal power allocation for each device in the integrated energy system. The improved whale algorithm uses a von Neumann topology for neighborhood search and increases the search step size in the whale individual position update step of the whale algorithm.

[0140] Example 3

[0141] This embodiment provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to execute the optimization and control method of the integrated energy system of Embodiment 1.

[0142] Alternatively, the aforementioned electronic device may be a server.

[0143] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the optimization and control method of the integrated energy system of Embodiment 1.

[0144] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0145] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An optimized control method for a comprehensive energy system, characterized in that, The optimization and control methods for the integrated energy system include: An optimal scheduling model for an integrated energy system is established; the optimal scheduling model allocates the power of each device in the integrated energy system with the goal of minimizing the total operating cost of the integrated energy system. The objective function of the optimized scheduling model is: ； in, m The objective function value, M 1 represents the operating cost of the integrated energy system. M 2 represents the cost of repairing and maintaining the integrated energy system. T To adjust the maximum time, M CT ( t )for t The operating cost of a gas turbine at any given time. M GB ( t )for t The fuel cost of a gas-fired boiler at any time M UM ( t )for t The management cost of the comprehensive energy system at all times M Buy ( t )for t The cost of purchasing electricity from the grid by the integrated energy system at all times. M again ( t )for t The cost of restarting a comprehensive energy system at all times; An improved whale algorithm is used to calculate the optimal solution of the optimized scheduling model; the optimal solution is the optimal power allocation of each device in the integrated energy system; the improved whale algorithm uses a von Neumann topology to perform neighborhood search and adjust the convergence factor in the whale individual position update step of the whale algorithm. Specifically, the improved whale algorithm is used to calculate the optimal solution of the optimized scheduling model, including: Initialize the whale population to obtain the initial population, and set the maximum number of iterations; the initial population includes multiple whale individuals and the initial position of each whale individual; the initial position of each whale individual represents the power allocation of each device in a set of integrated energy systems; Calculate the objective function value for each individual whale in the initial population; Regarding the first i In the next iteration, the first i The initial position of the whale individual with the smallest objective function value in the population is taken as the current optimal position; 0 < i The first generation population is the initial population; the initial position of a whale individual in the first generation population is the initial position of the corresponding whale individual. Calculate the number of iterations and the maximum number of iterations based on the number of iterations and the maximum number of iterations. i One convergence factor; Regarding the first i For any individual whale in the population, based on the current optimal position, the individual whale's initial position, and the [missing information], [missing information] i A convergence factor is used to calculate the updated position of the individual whale. Determine whether the distance between the initial position and the updated position of the individual whale is greater than a set threshold; If the distance between the initial position and the updated position of the individual whale is greater than a set threshold, then a von Neumann topology is used to perform a neighborhood search to determine the optimal position within the neighborhood. Update the current optimal position based on the optimal position within the neighborhood; Update the number of iterations and the maximum number of iterations. i One convergence factor; Based on the updated current optimal position, the updated [number]... i Based on a convergence factor and the initial position of the individual whale, the final position of the individual whale is determined. If the distance between the initial position and the updated position of the individual whale is less than or equal to a set threshold, then the updated position of the individual whale is taken as the final position of the individual whale. According to the i The final position of each whale individual in the population is determined, the objective function value for each whale individual is calculated, and the whale individuals are ranked according to the magnitude of the objective function value, with the top [whales] selected. N The first individual whale as the first i +1 generation population; i The initial position of an individual whale in the +1 generation population is the [missing information]. i The final location of the corresponding individual whale in the population; Check if the maximum number of iterations has been reached. If so, then... i The final position of the whale individual with the smallest objective function value in the population is taken as the optimal solution for the optimization scheduling model; otherwise, the process continues. i +1 iterations.

2. The method for optimizing and controlling a comprehensive energy system according to claim 1, characterized in that, Calculate the first using the following formula. i One convergence factor: ； in, For the first i One convergence factor, i max This represents the maximum number of iterations.

3. The method for optimizing and controlling a comprehensive energy system according to claim 1, characterized in that, Calculate the first using the following formula. i Updated position of individual whales in the population: ； in, For the first i The updated position of individual whales in the population. For the first i The current optimal position at the next iteration. As the first coefficient, As the second coefficient, For the first i The distance from the initial position to the current optimal position of an individual whale in the population. For the first i One convergence factor, r A random number between 0 and 1.

4. The method for optimizing and controlling a comprehensive energy system according to claim 1, characterized in that, Update the following formula: i The current optimal position at the next iteration: ； in, For the first i The current optimal position updated in the next iteration. P best The optimal position within the neighborhood. For the first i The current optimal position at the next iteration.

5. The method for optimizing and controlling a comprehensive energy system according to claim 1, characterized in that, Update the following formula: i One convergence factor: ； in, For the updated number i One convergence factor, i max This represents the maximum number of iterations.

6. An optimization control system for an integrated energy system, applied to the optimization control method for the integrated energy system according to any one of claims 1-5, characterized in that, The optimization and control system of the integrated energy system includes: The model building unit is used to build an optimal scheduling model for the integrated energy system; the optimal scheduling model aims to minimize the total operating cost of the integrated energy system and allocates the power of each device in the integrated energy system. The optimal solution calculation unit, connected to the model establishment unit, is used to calculate the optimal solution of the optimized scheduling model using an improved whale algorithm; the optimal solution is the optimal power allocation of each device in the integrated energy system; the improved whale algorithm uses a von Neumann topology for neighborhood search and increases the search step size in the whale individual position update step of the whale algorithm.

7. An electronic device, characterized in that, The device includes a memory and a processor, wherein the memory stores a computer program and the processor runs the computer program to enable the electronic device to perform the optimization and control method of the integrated energy system according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the optimization and control method of the integrated energy system as described in any one of claims 1 to 5.

Images