Park energy optimization method and system based on multi-target optimization algorithm

Abstract

The invention provides a park energy optimization method and system based on a multi-target optimization algorithm, and relates to the technical field of data processing. The method comprises the following steps: constructing a double-layer park energy optimization model, wherein the double-layer park energy optimization model comprises an upper-layer park energy optimization model and a lower-layer park energy optimization model; acquiring planning data of load equipment in the park; determining a supply equipment configuration scheme through an upper-layer park energy optimization model on the premise of meeting the energy demand of load equipment and by taking the minimum annual total cost as a target; constructing a park energy network; acquiring the actual generating capacity of the photovoltaic power generation equipment and the wind power generation equipment; on the premise that clean energy generated by photovoltaic power generation equipment and wind power generation equipment is preferentially used, multi-target optimization is carried out through a lower-layer park energy optimization model with minimum operation cost, minimum carbon emission and maximum clean energy utilization rate as multiple targets, and an energy scheduling scheme between supply equipment and load equipment is determined.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a park energy optimization method and system based on a multi-objective optimization algorithm. Background Art

[0002] With the popularization and development of clean energy, more and more industrial parks are deploying clean energy equipment for cost considerations. For example, photovoltaic power generation equipment and wind power generation equipment can reduce the demand for purchasing electricity from the national power grid and reduce the energy cost of the industrial park. On the other hand, it can reduce greenhouse gas emissions and improve the environmental quality of the park.

[0003] However, due to the dual uncertainty of electricity load and clean energy generation, there will be a mismatch between electricity supply and demand. With the rapid development of technologies such as pattern recognition, machine vision, and deep learning, as well as the urgent need for energy optimization, more and more modern technologies are being applied to energy optimization.

[0004] Existing energy optimization methods often only consider economic efficiency and perform single-objective optimization with the goal of minimizing the cost of park energy use. This may lead to excessive carbon emissions and low clean energy utilization during daily operations, resulting in inefficient operation of the park's energy system. Summary of the invention

[0005] In order to solve the technical problem that the existing energy optimization methods in the prior art often only consider the economic efficiency and perform single-objective optimization with the goal of minimizing the energy use cost of the park, which may lead to excessive carbon emissions and low clean energy utilization rate during daily operation, and cause low operating efficiency of the park energy system, the present invention provides a park energy optimization method and system based on a multi-objective optimization algorithm.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect

[0008] An embodiment of the present invention provides a park energy optimization method based on a multi-objective optimization algorithm, comprising:

[0009] S1: constructing a two-layer park energy optimization model, wherein the two-layer park energy optimization model includes: an upper-layer park energy optimization model and a lower-layer park energy optimization model;

[0010] S2: Obtain planning data of load equipment in the park, which includes power load, heat load and cooling load;

[0011] S3: on the premise of meeting the energy demand of the load equipment and taking the annual total cost as the minimum, a supply equipment configuration plan is determined through the upper-level park energy optimization model, and the supply equipment configuration plan includes the types and quantities of various supply equipment;

[0012] S4: constructing a campus energy network according to the supply equipment configuration plan, wherein the campus energy network includes a power network, a heating network, and a cooling network;

[0013] S5: Obtaining the actual power generation of photovoltaic power generation equipment and wind power generation equipment;

[0014] S6: Based on the premise of giving priority to the use of clean energy generated by photovoltaic power generation equipment and wind power generation equipment, and with multiple goals of minimizing operating costs, minimizing carbon emissions, and maximizing clean energy utilization, the lower-level park energy optimization model is used to perform multi-objective optimization to determine the energy scheduling plan between each supply equipment and load equipment to supply energy to the park.

[0015] Second aspect

[0016] An embodiment of the present invention provides a park energy optimization system based on a multi-objective optimization algorithm, comprising:

[0017] processor;

[0018] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the park energy optimization method based on the multi-objective optimization algorithm as described in the first aspect is implemented.

[0019] The third aspect

[0020] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for optimizing campus energy based on a multi-objective optimization algorithm as described in the first aspect is implemented.

[0021] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0022] (1) In the present invention, the supply equipment configuration plan is determined with the goal of minimizing the total annual cost, and the types and quantities of various supply equipment are determined. The types and quantities of various supply equipment can be flexibly determined according to the planning data and energy demand characteristics of the park. By configuring and combining different supply equipment such as gas equipment, thermal equipment, power grid equipment, photovoltaic power generation equipment and wind power generation equipment, the energy supply of the park can be diversified and optimized, and the reliability and stability of the energy supply can be improved. By optimizing the supply equipment configuration plan, the energy cost of the park can be effectively reduced, and the impact on the environment can be reduced to a certain extent.

[0023] (2) In the present invention, multi-objective optimization is carried out with the minimum operating cost, the minimum carbon emission and the maximum clean energy utilization rate as multiple goals to determine the energy scheduling plan between each supply equipment and load equipment to supply energy to the park. Not only the economic goal of minimizing the energy use cost of the park is considered, but also the two environmental protection goals of minimizing carbon emission and maximizing the clean energy utilization rate are considered. Carbon emissions are reduced, the utilization rate of clean energy is increased, the operating efficiency of the park's energy system is improved, the development and utilization of renewable energy is further promoted, and the energy structure is transformed towards a clean and low-carbon direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A schematic diagram of a process flow of a park energy optimization method based on a multi-objective optimization algorithm provided by an embodiment of the present invention;

[0026] Figure 2 A schematic diagram of the structure of a park energy optimization method based on a multi-objective optimization algorithm provided by an embodiment of the present invention;

[0027] Figure 3 A schematic diagram of a flow chart of a method for solving an upper-level park energy optimization model provided by an embodiment of the present invention;

[0028] Figure 4 A schematic diagram of a flow chart of a method for solving a lower-level park energy optimization model provided by an embodiment of the present invention;

[0029] Figure 5 A schematic diagram of the structure of a park energy optimization system based on a multi-objective optimization algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0031] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0032] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0033] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0034] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0035] Reference Manual Attached Figure 1 , showing a flow chart of a park energy optimization method based on a multi-objective optimization algorithm provided in an embodiment of the present invention.

[0036] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a park energy optimization method based on a multi-objective optimization algorithm provided by an embodiment of the present invention.

[0037] The embodiment of the present invention provides a campus energy optimization method based on a multi-objective optimization algorithm, which can be implemented by a campus energy optimization device based on a multi-objective optimization algorithm, and the campus energy optimization device based on a multi-objective optimization algorithm can be a terminal or a server. The processing flow of the campus energy optimization method based on a multi-objective optimization algorithm can include the following steps:

[0038] S1: Construct a two-layer campus energy optimization model.

[0039] Among them, the two-layer park energy optimization model includes: an upper-layer park energy optimization model and a lower-layer park energy optimization model.

[0040] Among them, the upper-level park energy optimization model is used to determine the supply equipment configuration plan based on the park planning data.

[0041] Among them, the lower-level park energy optimization model is used to determine the energy scheduling plan based on the actual power generation of photovoltaic power generation equipment and wind power generation equipment.

[0042] Furthermore, decomposing the park energy optimization problem into two levels can achieve hierarchical management, making the problem clearer and easier to understand. The upper model is responsible for determining the supply equipment configuration plan, and the lower model is responsible for energy scheduling under the given configuration plan. Each model has its own responsibilities and the levels are clear.

[0043] It should be noted that the supply equipment configuration plan determined by the upper-level park energy optimization model will guide the construction of the park energy network. After that, the lower-level park energy optimization model will prioritize energy scheduling based on the constructed park energy network. In other words, the upper-level park energy optimization model is the basis of the lower-level park energy optimization model.

[0044] In the present invention, the supply equipment configuration scheme determined by the upper model provides guidance and basis for the lower model, and the lower model can be adjusted and optimized according to actual conditions and needs, so that the park can better adapt to changes in the external environment and changes in internal needs.

[0045] S2: Obtain planning data of campus load equipment.

[0046] Among them, load equipment includes: power load, thermal load and cooling load.

[0047] It should be noted that by obtaining the planning data of power, heat and cooling load equipment, we can accurately understand the energy demand of the park in different areas, which can provide reliable data support for the formulation of energy supply plans.

[0048] S3: Based on meeting the energy demand of load equipment and aiming at minimizing the total annual cost, the supply equipment configuration plan is determined through the upper-level campus energy optimization model.

[0049] Among them, the supply equipment configuration plan includes the types and quantities of various supply equipment.

[0050] Among them, the supplied equipment includes: gas equipment, thermal equipment, power grid equipment, photovoltaic power generation equipment and wind power generation equipment.

[0051] It should be noted that by minimizing the total annual cost as the goal, the energy procurement and operating costs of the park can be reduced to the greatest extent while ensuring that the energy needs of the load equipment are met. By rationally allocating the types and quantities of various supply equipment, energy costs can be effectively controlled and the economic benefits of the park can be improved.

[0052] Reference Manual Attached Figure 3 , showing a flow chart of a method for solving an upper-level park energy optimization model provided by an embodiment of the present invention.

[0053] In a possible implementation, S3 specifically includes sub-steps S301 to S303:

[0054] S301: Taking the minimization of the annual total cost as the goal, construct the upper objective function of the upper campus energy optimization model.

[0055] Optionally, the upper layer objective function is specifically:

[0056] F u (X) = min{C y}

[0057] Among them, F u () represents the upper objective function, X represents the supply equipment configuration plan, min represents minimization, C y represents the annual total cost function.

[0058] Among them, the annual total cost function is specifically:

[0059] C y =C pur +C op +C e +C f +C pol +C ab

[0060] Among them, C pur Indicates the equipment purchase cost, C op represents the equipment operating cost, C e Indicates the electricity purchase cost, C f represents the natural gas purchase cost, C pol represents the cost of pollutant treatment, C ab represents the cost of abandoning clean energy.

[0061] The specific cost of equipment purchase is:

[0062]

[0063] Among them, γ i represents the value retention rate of the i-th type of supply equipment, d i represents the purchase quantity of the i-th type of supply equipment, c i represents the purchase cost of the i-th supply equipment, and I represents the supply equipment set.

[0064] The specific equipment operating costs are:

[0065]

[0066] Among them, a i represents the unit maintenance cost of the i-th supply equipment, P i Represents the output power of the i-th supply device.

[0067] The specific cost of electricity purchase is:

[0068] C e =Q e c e

[0069] Among them, Q e represents the annual power grid purchase, c e Represents the annual average electricity price.

[0070] The specific cost of purchasing electricity and natural gas is:

[0071] C f =Q f c f

[0072] Among them, Q f represents the annual natural gas purchase volume, c f Represents the annual average unit price of natural gas.

[0073] The specific cost of pollutant treatment is:

[0074] C pol =Wc pol

[0075] Where W represents the annual pollutant emissions, c pol Represents the unit pollutant treatment cost.

[0076] It should be noted that, considering the cost of pollutant treatment, the optimization model also helps to reduce the amount of pollutant emissions in the park. By reducing pollutant emissions, it can not only reduce environmental pollution, but also help avoid additional governance costs and legal risks caused by environmental pollution.

[0077] The specific costs of clean energy abandonment are:

[0078] C ab =c ab Q a (1-η)

[0079] Among them, Q a represents the annual clean energy power generation, η represents the clean energy utilization rate, c ab Represents the unit clean energy abandonment cost.

[0080] It should be noted that, considering the cost of clean energy abandonment, the optimization model tends to improve the utilization rate of clean energy. By minimizing the cost of clean energy abandonment, the system can be encouraged to make more use of clean energy such as photovoltaic power generation and wind power generation, reduce dependence on traditional energy, and achieve clean and low-carbon energy supply.

[0081] The annual clean energy power generation is as follows:

[0082]

[0083] Among them, Q krepresents the annual power generation of the kth power generation equipment, K1 represents the set of photovoltaic power generation equipment, and K2 represents the set of wind power generation equipment.

[0084] In the present invention, the upper objective function takes into account various cost factors, including equipment purchase cost, equipment operating cost, electricity purchase cost, natural gas purchase cost, pollutant treatment cost and clean energy abandonment cost. Such a comprehensive cost function helps to comprehensively evaluate the economic feasibility of the supply equipment configuration plan. By minimizing the annual total cost function, the system can automatically find the optimal supply equipment configuration plan, including the types and quantities of various supply equipment. This ensures that energy supply is achieved at the lowest cost while meeting the energy needs of the load equipment.

[0085] S302: Setting upper-level constraint conditions of the upper-level campus energy optimization model.

[0086] Optionally, the upper-level constraints include:

[0087] Power demand constraints:

[0088] α(Q a +Q e )≥Q min

[0089] Among them, Q e represents the annual power grid purchase, Q a represents the annual clean energy power generation, Q min represents the energy demand of the power load, and α represents the power supply coefficient.

[0090] It should be noted that the power demand constraint ensures that the selected energy supply solution can meet the power load demand of the park, which helps to ensure that the basic power demand of the park is met and improves the reliability of power supply.

[0091] Heat demand constraints:

[0092] H a ≥H min

[0093] Among them, H a Indicates the annual heat output of gas equipment and thermal equipment, H min Represents the thermal load energy demand.

[0094] It should be noted that the heat demand constraint ensures that the selected energy supply solution can meet the thermal load demand of the park, which helps to ensure that the basic thermal demand of the park is met and improves the reliability of heat supply.

[0095] Cooling demand constraints:

[0096] (1-α)β(Q a+Q e )≥L min

[0097] Among them, (1-α) represents the cooling coefficient, β represents the cooling power conversion coefficient, and L min Represents the cooling load energy demand.

[0098] It should be noted that the cooling demand constraint ensures that the selected energy supply solution can meet the cooling load demand of the park, which helps to ensure that the basic cooling demand of the park is met and improves the reliability of cooling supply.

[0099] Device power constraints:

[0100] P j,min ≤P j ≤P j,max

[0101] Among them, P j represents the power of the jth supply device, P j,min represents the lower power limit of the jth supply device, P j,max Indicates the power upper limit value of the jth supply device.

[0102] It should be noted that the device power constraint ensures that the power of the selected supply device is within a reasonable range. By limiting the power of each supply device between the preset lower limit and upper limit, this helps to avoid over-investment or under-investment, while ensuring that the supply device operates in a safe and efficient state.

[0103] Equipment capacity constraints:

[0104] Q j,min ≤Q j ≤Q j,max

[0105] Among them, Q j represents the capacity of the jth supply device, Q j,min represents the lower limit of the capacity of the jth supply device, Q j,max Represents the upper capacity limit of the j-th supply device.

[0106] It should be noted that the equipment capacity constraint ensures that the capacity of the selected supply equipment is within a reasonable range. By limiting the capacity of each supply equipment between the preset lower and upper limits, this helps to avoid insufficient or wasted equipment capacity and ensures that the supply equipment has the appropriate size and capacity to meet the energy needs of the park.

[0107] S303: Solve the upper-level park energy optimization model through a genetic algorithm to determine the type and quantity of supply equipment.

[0108] Among them, the genetic algorithm (GA) is a heuristic algorithm inspired by the theory of evolution in nature and used to solve optimization problems. It simulates the natural selection and genetic mechanism in biological evolution, generates a set of solutions through continuous iteration, and gradually optimizes this set of solutions by simulating operations such as natural selection, crossover and mutation until the optimal solution is found or the stopping condition is met.

[0109] In traditional genetic algorithms, elite selection or roulette wheel selection is often used for selection, which is prone to premature convergence and fall into a local optimal solution. In order to solve this problem, the present invention provides an improved genetic algorithm, which is specifically:

[0110] The inverse of the objective function is used as the fitness function of the genetic algorithm.

[0111] It should be noted that using the reciprocal of the objective function as the fitness function of the genetic algorithm can better guide the search process when solving minimization problems. Generally speaking, the larger the fitness function, the better the individual's performance in the solution space. In minimization problems, the smaller the objective function value, the better the individual's performance. Therefore, the reciprocal of the objective function can be used as the fitness function, so that the smaller the objective function value, the larger the corresponding fitness value.

[0112] Initialize the population Q1, which contains multiple individuals, each of which represents a feasible supply equipment configuration solution.

[0113] Based on the Q-Learning algorithm, the individuals in the population are selected to form population Q2.

[0114] The gene space constructed by the population is used as the action strategy space of the Q-Learning algorithm. The change in fitness value after performing a random selection action is used as the immediate reward for performing the selection action. The population is randomly selected and the Q matrix of the Q-Learning algorithm is updated. Then, the selection at the next iteration can be made based on the updated Q matrix:

[0115] Q(S t ,A t )=εQ(S t ,A t )+(1-ε)(R t+1 +μmaxQ(S t+1 ,a)-Q(S t ,A t ))

[0116] Among them, S t represents the state at the tth iteration, A t represents the randomly selected action at the tth iteration, Q(S t,A t ) indicates that in state S t Execute randomly selected action A t Q value, ε represents the learning rate, R t+1 Indicates that in state S t Execute randomly selected action A t The instant reward, μ represents the discount factor, maxQ(S t+1 ,a) represents the next state S t+1 The maximum Q value of the action a that can be selected in , also known as the long-term reward.

[0117] In the present invention, through the Q-Learning algorithm, the population can adaptively adjust the selection strategy according to the historical selection experience, so as to better adapt to the current environment. As the iteration proceeds, the immediate reward and long-term reward information stored in the Q matrix can guide the population to make more appropriate decisions in each selection, thereby improving the efficiency and accuracy of the selection. At the same time, the Q-Learning algorithm combines the strategies of exploration and utilization. By randomly selecting actions and selecting the optimal action based on the Q value, it can continuously explore new selection strategies while utilizing existing experience knowledge to achieve a balance between exploration and utilization and avoid falling into a local optimal solution.

[0118] Perform a crossover operation on population Q2, randomly select two individuals from population Q2 as parents, generate a random number, and compare the random number with the crossover probability P e Compare the size, if the random number is less than the crossover probability P e , then the parent is cross-operated to generate new individuals to form population Q3. The generation of new individuals y1 and y2 is as follows:

[0119] y1=rand×x1+(1-rand)×x2y2=rand×x2+(1-rand)×x1

[0120] Among them, x1 and x2 represent the parent, and rand represents a random number between 0 and 1.

[0121] In the present invention, the crossover operation recombines the genetic information of the two parents to produce new individuals, which helps to introduce new gene combinations and increase the diversity of the population. This helps the population to explore more widely in the search space and prevents the population from falling into a local optimal solution. Through the crossover operation, the excellent characteristics between the parent individuals can be used to exchange and combine genetic information, thereby quickly obtaining new individuals. This helps to accelerate the optimization process, improve the convergence speed of the algorithm, and make the population approach the global optimal solution faster.

[0122] Among them, the crossover probability P e Specifically:

[0123]

[0124] Among them, P e represents the crossover probability, P e,max represents the maximum crossover probability, P e,min represents the minimum crossover probability, δ represents the fitness value of the current individual, δ avg represents the average fitness value of the population, δ max Represents the maximum fitness value among individuals.

[0125] In the present invention, by dynamically adjusting the crossover probability according to the fitness value of current individual, the crossover probability can be adaptively adjusted in the optimization process. The individual with higher fitness may have a more excellent gene combination, so the possibility of crossover operation should be higher, and the individual with lower fitness may need more exploration space, so the crossover probability can be lowered accordingly. In the optimization process, the individual with higher fitness may be more easily selected as the parent to cross over, which helps to keep the excellent gene combination in the population, and accelerates the propagation and retention of excellent characteristics. The individual with lower fitness may need more exploration opportunities, and by lowering the crossover probability, their genetic information can be retained more, which helps the diversity of the population to maintain.

[0126] Perform a mutation operation on population Q3, randomly select a parent x3 from population Q3, generate a random number, and compare the random number with the mutation probability P m Compare the size. If the random number is less than the mutation probability P, m , then the parent x3 is mutated to generate a new individual y3 to replace the original individual to form a population Q4. The generation method of the new individual y3 is as follows:

[0127]

[0128] Among them, x3 represents the parent, and rand represents a random number between 0 and 1.

[0129] In the present invention, the mutation operation can increase the diversity of the population to a certain extent, introduce new gene combinations, and help avoid falling into the local optimal solution. By introducing random mutations, a wider search can be performed in the gene space, which helps to explore other potential solutions in the solution space. At the same time, the mutation operation helps to maintain the diversity of the population and prevent the population from converging to the local optimal solution too early. During the optimization process, if the individuals in the population are too similar, it may lead to falling into the local optimal solution. Through the mutation operation, random differences can be introduced between individuals, which helps to maintain the diversity of the population and promote global search.

[0130] Among them, the mutation probability P m Specifically:

[0131]

[0132] Among them, P m represents the mutation probability, P m,max represents the maximum mutation probability, P m,min represents the minimum mutation probability, δ represents the fitness value of the current individual, δ avg represents the average fitness value of the population, δ max Represents the maximum fitness value among individuals.

[0133] In the present invention, by dynamically adjusting the probability of mutation according to the fitness value of the current individual, the probability of mutation can be adaptively adjusted during the optimization process. Individuals with higher fitness may have better gene combinations, so the possibility of performing mutation operations on them should be higher, while individuals with lower fitness may need more exploration space, so the probability of mutation can be lowered accordingly. During the optimization process, individuals with higher fitness may be more likely to be selected as parents to mutate, which helps to maintain the excellent gene combination in the population and accelerate the spread and retention of excellent characteristics. Individuals with lower fitness may need more exploration opportunities, and by lowering the probability of mutation, their genetic information can be retained more, which helps the diversity of the population to maintain.

[0134] Determine whether the number of iterations has reached the maximum number of iterations. If so, determine the individual with the highest fitness value as the optimal supply equipment configuration solution. Otherwise, return to the step of selecting individuals in the population and continue iterating.

[0135] In the present invention, with the goal of minimizing the total annual cost, the supply equipment configuration plan is determined, and the types and quantities of various supply equipment are determined. The types and quantities of various supply equipment can be flexibly determined according to the planning data and energy demand characteristics of the park. By configuring and combining different supply equipment such as gas equipment, thermal equipment, power grid equipment, photovoltaic power generation equipment and wind power generation equipment, the energy supply of the park can be diversified and optimized, and the reliability and stability of the energy supply can be improved. By optimizing the supply equipment configuration plan, the energy cost of the park can be effectively reduced, and the impact on the environment can be reduced to a certain extent.

[0136] S4: Build the campus energy network according to the supply equipment configuration plan.

[0137] Among them, the park energy network includes power network, heating network and cooling network.

[0138] It should be noted that building a park energy network according to the supply equipment configuration scheme determined by the upper-level park energy optimization model can achieve effective integration and mutual utilization of various energy sources. For example, using waste heat to heat water source heat pumps, using the surplus electricity generated by power equipment to supply other equipment, etc. This can maximize the efficiency of energy utilization and reduce energy waste.

[0139] S5: Obtain the actual power generation of the photovoltaic power generation equipment and the wind power generation equipment.

[0140] S6: Based on the premise of giving priority to the use of clean energy generated by photovoltaic power generation equipment and wind power generation equipment, and with multiple goals of minimizing operating costs, minimizing carbon emissions, and maximizing clean energy utilization, the lower-level park energy optimization model is used to conduct multi-objective optimization to determine the energy scheduling plan between each supply equipment and load equipment to supply energy to the park.

[0141] Optionally, the energy scheduling scheme is specifically expressed as:

[0142] L=YE

[0143]

[0144] Where L represents the energy demand vector of the load device, Y represents the energy scheduling plan, E represents the energy supply vector of the supply device, and y ij It represents the energy demand of the i-th load device that is supplied by the j-th supply device, L i represents the energy demand of the i-th load device, i = 1, 2, ..., m, m represents the total number of load devices, E j Represents the energy supply of the jth supply device, j = 1, 2, …, n, and n represents the total number of supply devices.

[0145] Reference Manual Attached Figure 4 , showing a flow chart of a method for solving a lower-level park energy optimization model provided by an embodiment of the present invention.

[0146] In a possible implementation, S6 specifically includes sub-steps S601 to S603:

[0147] S601: Construct the lower objective function of the lower park energy optimization model with the minimum operating cost, the minimum carbon emission and the maximum clean energy utilization as multiple goals.

[0148] Optionally, the lower layer objective function is specifically:

[0149]

[0150] Among them, F d() represents the lower-level objective function, Y represents the energy scheduling plan, min represents minimization, f1 represents the operating cost objective function, f2 represents the carbon emission objective function, and f3 represents the clean energy utilization objective function.

[0151] It should be noted that by taking into account operating costs, carbon emissions and clean energy utilization, the pros and cons of energy scheduling solutions can be comprehensively evaluated. This helps to not only focus on economic efficiency in the energy scheduling process, but also consider environmental and sustainability factors, making the decision more comprehensive and reasonable.

[0152] Optionally, the lower layer objective function is specifically:

[0153]

[0154] Among them, F d () represents the lower-level objective function, Y represents the energy scheduling plan, min represents minimization, f1 represents the operating cost objective function, f2 represents the carbon emission objective function, f3 represents the clean energy utilization objective function, μ1 represents the scaling factor of the operating cost objective function, μ2 represents the scaling factor of the carbon emission objective function, and μ3 represents the scaling factor of the clean energy utilization objective function.

[0155] Among them, those skilled in the art can set the scaling coefficient μ1 of the operating cost objective function, the scaling coefficient μ2 of the carbon emission objective function, and the scaling coefficient μ3 of the clean energy utilization objective function according to actual conditions, and the present invention does not limit them.

[0156] It should be noted that the introduction of scaling factors can flexibly adjust the relative importance of each objective in the optimization process. If a certain objective is more important to the system, its corresponding scaling factor can be increased, so that the optimization result is more biased towards this objective. This flexibility enables the optimization results to be adjusted according to specific needs and preferences. Furthermore, for multi-objective optimization problems, different objectives usually have mutual constraints and contradictions. By adjusting the scaling factor, a balance can be achieved between different objectives. For example, a balance can be achieved between operating costs and environmental impacts, or between economy and sustainability. This helps to find an optimal solution that takes into account the needs of multiple aspects.

[0157] The specific operating cost objective function is:

[0158]

[0159] Among them, C op represents the equipment operating cost, d i represents the purchase quantity of the i-th type of supply equipment, a i represents the unit maintenance cost of the i-th supply equipment, Pi represents the output power of the i-th supply device, and I represents the set of supply devices.

[0160] The carbon emission objective function is as follows:

[0161]

[0162] Among them, n i represents the number of purchased supply equipment using the i-th type of raw energy, λ i represents the carbon emission coefficient of the i-th type of supply equipment using original energy, P i represents the output power of the i-th supply device using the original energy, and I1 represents the set of supply devices using the original energy.

[0163] The specific objective function of clean energy utilization is:

[0164]

[0165] Among them, η represents the utilization rate of clean energy, Q in represents the clean energy power generation, Q out Indicates the amount of clean energy used.

[0166] The specific amount of clean energy used is:

[0167] Q out =LQ e*

[0168] Where L represents the total load, Q e* Indicates the amount of electricity purchased from the power grid.

[0169] S602: Setting lower-level constraints of the lower-level park energy optimization model.

[0170] Optionally, the lower-level constraints specifically include:

[0171] Clean energy priority constraint: Priority is given to the use of clean energy generated by photovoltaic power generation equipment and wind power generation equipment.

[0172] It should be noted that the clean energy priority constraint emphasizes the priority use of clean energy, that is, in the energy scheduling process, priority is given to the use of clean energy generated by photovoltaic power generation equipment and wind power generation equipment, so as to minimize dependence on traditional fossil energy, reduce carbon emissions, and improve the environmental friendliness of energy supply.

[0173] Power balance constraints:

[0174] P out =P r

[0175] Among them, P outIndicates the output power of the supply equipment, P r Indicates the working power of the load device.

[0176] It should be noted that the power balance constraint ensures the balance between the energy supply and load demand of the park, that is, the energy supplied meets the needs of the load equipment, avoiding energy waste or energy shortage caused by the mismatch between energy supply and demand.

[0177] Device power constraints:

[0178] P j,min ≤P j ≤P j,max

[0179] Among them, P j represents the power of the jth supply device, P j,min represents the lower power limit of the jth supply device, P j,max Indicates the power upper limit value of the jth supply device.

[0180] It should be noted that the device power constraint ensures that the power of the selected supply device is within a reasonable range. By limiting the power of each supply device between the preset lower limit and upper limit, this helps to avoid over-investment or under-investment, while ensuring that the supply device operates in a safe and efficient state.

[0181] Equipment capacity constraints:

[0182] Q j,min ≤Q j ≤Q j,max

[0183] Among them, Q j represents the capacity of the jth supply device, Q j,min represents the lower limit of the capacity of the jth supply device, Q j,max Represents the upper capacity limit of the j-th supply device.

[0184] It should be noted that the equipment capacity constraint ensures that the capacity of the selected supply equipment is within a reasonable range. By limiting the capacity of each supply equipment between the preset lower and upper limits, this helps to avoid insufficient or wasted equipment capacity and ensures that the supply equipment has the appropriate size and capacity to meet the energy needs of the park.

[0185] S603: Perform multi-objective optimization on the lower-level park energy optimization model through a genetic algorithm to determine an energy scheduling plan between various supply devices and load devices to supply energy to the park.

[0186] Traditional genetic algorithms are often used for single-objective optimization. The present invention provides a new genetic algorithm for multi-objective optimization.

[0187] The inverse of multiple sub-objective functions is used as the sub-fitness function of the genetic algorithm, and the function value of the sub-fitness function is called the sub-fitness value. The sum of the sub-fitness functions is used as the fitness function of the genetic algorithm, and the function value of the fitness function is called the fitness value.

[0188] Among them, the sub-objective functions specifically refer to the operating cost objective function, the carbon emissions objective function and the clean energy utilization rate objective function.

[0189] Initialize the population Q1, which contains multiple individuals, each of which represents a feasible energy scheduling solution.

[0190] Based on the Q-Learning algorithm, the individuals in the population are selected to form population Q2.

[0191] The gene space constructed by the population is used as the action strategy space of the Q-Learning algorithm. The change in fitness value after performing a random selection action is used as the immediate reward for performing the selection action. The population is randomly selected and the Q matrix of the Q-Learning algorithm is updated. Then, the selection at the next iteration can be made based on the updated Q matrix:

[0192] Q(S t ,A t )=εQ(S m ,A t )+(1-ε)(R t+1 +μmaxQ(S t+1 ,a)-Q(S t ,A t ))

[0193] Among them, S t represents the state at the tth iteration, A t represents the randomly selected action at the tth iteration, Q(S t ,A t ) indicates that in state S t Execute randomly selected action A t Q value, ε represents the learning rate, R t+1 Indicates that in state S t Execute randomly selected action A t The instant reward, μ represents the discount factor, maxQ(S t+1 ,a) represents the next state S t+1 The maximum Q value of the action a that can be selected in , also known as the long-term reward.

[0194] Perform a crossover operation on population Q2, randomly select two individuals from population Q2 as parents, generate a random number, and compare the random number with the crossover probability Pe Compare the size, if the random number is less than the crossover probability P e , then the parent is cross-operated to generate new individuals to form population Q3. The generation of new individuals y1 and y2 is as follows:

[0195] y1=rand×x1+(1-rand)×x2y2=rand×x2+(1-rand)×x1

[0196] Among them, x1 and x2 represent the parent, and rand represents a random number between 0 and 1.

[0197] In the present invention, the crossover operation recombines the genetic information of the two parents to produce new individuals, which helps to introduce new gene combinations and increase the diversity of the population. This helps the population to explore more widely in the search space and prevents the population from falling into a local optimal solution. Through the crossover operation, the excellent characteristics between the parent individuals can be used to exchange and combine genetic information, thereby quickly obtaining new individuals. This helps to accelerate the optimization process, improve the convergence speed of the algorithm, and make the population approach the global optimal solution faster.

[0198] Perform a mutation operation on population Q3, select a parent x3 from the mutation set, generate a random number, and compare the random number with the mutation probability P m Compare the size. If the random number is less than the mutation probability P, m , then the parent x3 is mutated to generate a new individual y3 to replace the original individual to form a population Q4. The generation method of the new individual y3 is as follows:

[0199]

[0200] Among them, x3 represents the parent, and rand represents a random number between 0 and 1.

[0201] In the present invention, the mutation operation can increase the diversity of the population to a certain extent, introduce new gene combinations, and help avoid falling into the local optimal solution. By introducing random mutations, a wider search can be performed in the gene space, which helps to explore other potential solutions in the solution space. At the same time, the mutation operation helps to maintain the diversity of the population and prevent the population from converging to the local optimal solution too early. During the optimization process, if the individuals in the population are too similar, it may lead to falling into the local optimal solution. Through the mutation operation, random differences can be introduced between individuals, which helps to maintain the diversity of the population and promote global search.

[0202] Specifically, the mutation set is formed as follows:

[0203] Determine the average ranking parameter for each individual:

[0204]

[0205] Among them, RA(x i ) represents the average ranking parameter of the i-th individual, x i represents the i-th individual, RA k (x i ) represents the ranking of the i-th individual in the sub-fitness function constructed with the k-th sub-objective function.

[0206] Determine the difference parameter between each individual and the worst individual:

[0207]

[0208] Among them, BD(x i ) represents the difference parameter between the ith individual and the worst individual, f k (x i ) represents the sub-fitness value of the i-th individual in the sub-fitness function constructed with the k-th sub-objective function, f k,max represents the sub-fitness value of the best individual in the sub-fitness function constructed with the kth sub-objective function, f k,min Represents the sub-fitness value of the worst individual in the sub-fitness function constructed with the kth sub-objective function.

[0209] According to the average ranking parameters of each individual and the difference parameters between them and the worst individual, the comprehensive evaluation parameters of the individual are determined:

[0210] Z(x i )=ρ1RA(x i )+ρ2BD(x i )

[0211] Among them, Z(x i ) represents the comprehensive evaluation parameter of the ith individual, ρ1 represents the weight coefficient of the average ranking parameter, and ρ2 represents the weight coefficient of the difference parameter between the worst individual and the ith individual.

[0212] It should be noted that the comprehensive evaluation parameter takes into account both the average ranking of the individual and the difference parameter with the worst individual. The average ranking parameter represents the comprehensive performance of the individual in each sub-objective function, while the difference parameter with the worst individual represents the degree of difference between the individual and the entire population. This comprehensive evaluation method more comprehensively reflects the performance of the individual under multiple objectives and can better guide the mutation operation.

[0213] Individuals whose comprehensive evaluation parameters are less than the preset parameter values ​​are put into the mutation set.

[0214] Among them, those skilled in the art can set the size of the preset parameter value according to actual conditions, and the present invention does not limit it.

[0215] It should be noted that only individuals whose comprehensive evaluation parameters are less than the preset parameter values ​​are selected to be included in the mutation set, and those relatively poor or less typical individuals are selected for change. On the one hand, better genes can be directly retained, and on the other hand, unnecessary computing overhead can be reduced, the efficiency of the mutation operation can be improved, which helps to speed up the operation of the algorithm and make the optimization process more efficient.

[0216] Determine whether the number of iterations has reached the maximum number of iterations. If so, determine the individual with the highest fitness value as the optimal energy scheduling solution. Otherwise, return to the step of selecting individuals in the population and continue iterating.

[0217] In the present invention, multi-objective optimization is carried out with the minimum operating cost, the minimum carbon emissions, and the maximum clean energy utilization rate as multiple goals to determine the energy scheduling plan between each supply equipment and load equipment to supply energy to the park. Not only the economic goal of minimizing the energy use cost of the park is considered, but also the two environmental protection goals of minimizing carbon emissions and maximizing the clean energy utilization rate are additionally considered to reduce carbon emissions, increase the clean energy utilization rate, and improve the operating efficiency of the park's energy system, further promote the development and utilization of renewable energy, and promote the transformation of the energy structure to a clean and low-carbon direction.

[0218] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0219] (1) In the present invention, the supply equipment configuration plan is determined with the goal of minimizing the total annual cost, and the types and quantities of various supply equipment are determined. The types and quantities of various supply equipment can be flexibly determined according to the planning data and energy demand characteristics of the park. By configuring and combining different supply equipment such as gas equipment, thermal equipment, power grid equipment, photovoltaic power generation equipment and wind power generation equipment, the energy supply of the park can be diversified and optimized, and the reliability and stability of the energy supply can be improved. By optimizing the supply equipment configuration plan, the energy cost of the park can be effectively reduced, and the impact on the environment can be reduced to a certain extent.

[0220] (2) In the present invention, multi-objective optimization is carried out with the minimum operating cost, the minimum carbon emission and the maximum clean energy utilization rate as multiple goals to determine the energy scheduling plan between each supply equipment and load equipment to supply energy to the park. Not only the economic goal of minimizing the energy use cost of the park is considered, but also the two environmental protection goals of minimizing carbon emission and maximizing the clean energy utilization rate are considered. Carbon emissions are reduced, the utilization rate of clean energy is increased, the operating efficiency of the park's energy system is improved, the development and utilization of renewable energy is further promoted, and the energy structure is transformed towards a clean and low-carbon direction.

[0221] Reference Manual Attached Figure 5 , showing a structural schematic diagram of a park energy optimization system based on a multi-objective optimization algorithm provided by the present invention.

[0222] The present invention further provides a park energy optimization system 20 based on a multi-objective optimization algorithm, which is applied to the above-mentioned park energy optimization method based on a multi-objective optimization algorithm, comprising:

[0223] Processor 201.

[0224] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, a campus energy optimization method based on a multi-objective optimization algorithm as in the method embodiment is implemented.

[0225] The campus energy optimization system 20 based on a multi-objective optimization algorithm provided by the present invention can execute the above-mentioned campus energy optimization method based on a multi-objective optimization algorithm and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0226] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0227] (1) In the present invention, the supply equipment configuration plan is determined with the goal of minimizing the total annual cost, and the types and quantities of various supply equipment are determined. The types and quantities of various supply equipment can be flexibly determined according to the planning data and energy demand characteristics of the park. By configuring and combining different supply equipment such as gas equipment, thermal equipment, power grid equipment, photovoltaic power generation equipment and wind power generation equipment, the energy supply of the park can be diversified and optimized, and the reliability and stability of the energy supply can be improved. By optimizing the supply equipment configuration plan, the energy cost of the park can be effectively reduced, and the impact on the environment can be reduced to a certain extent.

[0228] (2) In the present invention, multi-objective optimization is carried out with the minimum operating cost, the minimum carbon emission and the maximum clean energy utilization rate as multiple goals to determine the energy scheduling plan between each supply equipment and load equipment to supply energy to the park. Not only the economic goal of minimizing the energy use cost of the park is considered, but also the two environmental protection goals of minimizing carbon emission and maximizing the clean energy utilization rate are considered. Carbon emissions are reduced, the utilization rate of clean energy is increased, the operating efficiency of the park's energy system is improved, the development and utilization of renewable energy is further promoted, and the energy structure is transformed towards a clean and low-carbon direction.

[0229] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0230] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0231] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0232] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0233] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0234] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0235] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0236] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0237] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0238] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0239] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0240] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0241] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method for optimizing campus energy based on a multi-objective optimization algorithm as described in the method embodiment is implemented.

[0242] A computer-readable storage medium provided by the present invention can implement the steps and effects of the campus energy optimization method based on a multi-objective optimization algorithm of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0243] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0244] (1) In the present invention, the supply equipment configuration plan is determined with the goal of minimizing the total annual cost, and the types and quantities of various supply equipment are determined. The types and quantities of various supply equipment can be flexibly determined according to the planning data and energy demand characteristics of the park. By configuring and combining different supply equipment such as gas equipment, thermal equipment, power grid equipment, photovoltaic power generation equipment and wind power generation equipment, the energy supply of the park can be diversified and optimized, and the reliability and stability of the energy supply can be improved. By optimizing the supply equipment configuration plan, the energy cost of the park can be effectively reduced, and the impact on the environment can be reduced to a certain extent.

[0245] (2) In the present invention, multi-objective optimization is carried out with the minimum operating cost, the minimum carbon emission and the maximum clean energy utilization rate as multiple goals to determine the energy scheduling plan between each supply equipment and load equipment to supply energy to the park. Not only the economic goal of minimizing the energy use cost of the park is considered, but also the two environmental protection goals of minimizing carbon emission and maximizing the clean energy utilization rate are considered. Carbon emissions are reduced, the utilization rate of clean energy is increased, the operating efficiency of the park's energy system is improved, the development and utilization of renewable energy is further promoted, and the energy structure is transformed towards a clean and low-carbon direction.

[0246] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0247] There are a few points to note:

[0248] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0249] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0250] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0251] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A park energy optimization method based on a multi-objective optimization algorithm, characterized in that: include: S1: constructing a two-layer park energy optimization model, wherein the two-layer park energy optimization model includes: an upper-layer park energy optimization model and a lower-layer park energy optimization model; S2: Obtain planning data of load equipment in the park, which includes power load, heat load and cooling load; S3: on the premise of meeting the energy demand of the load equipment and taking the annual total cost as the minimum, a supply equipment configuration plan is determined through the upper-level park energy optimization model, and the supply equipment configuration plan includes the types and quantities of various supply equipment; S4: constructing a campus energy network according to the supply equipment configuration plan, wherein the campus energy network includes a power network, a heating network, and a cooling network; S5: Obtaining the actual power generation of photovoltaic power generation equipment and wind power generation equipment; S6: On the premise of giving priority to the use of clean energy generated by photovoltaic power generation equipment and wind power generation equipment, multiple goals are set, and multi-objective optimization is performed through the lower-level park energy optimization model to determine the energy scheduling plan between each supply equipment and load equipment to supply energy to the park.

2. The park energy optimization method based on a multi-objective optimization algorithm according to claim 1 is characterized in that: The S3 specifically includes: S301: constructing an upper objective function of the upper park energy optimization model with the goal of minimizing the annual total cost; S302: Setting upper-level constraint conditions of the upper-level park energy optimization model; S303: Solving the upper-level park energy optimization model by means of a genetic algorithm to determine the type and quantity of supply equipment.

3. The park energy optimization method based on a multi-objective optimization algorithm according to claim 2 is characterized in that: The upper layer objective function is specifically: F u (X)=min{C y } Among them, F u () represents the upper objective function, X represents the supply equipment configuration plan, min represents minimization, C y represents the annual total cost function; The annual total cost function is specifically: C y =C pur +C op +C e +C f +C pol +C ab Among them, C pur Indicates the equipment purchase cost, C op represents the equipment operating cost, C e Indicates the electricity purchase cost, C f represents the natural gas purchase cost, C pol represents the cost of pollutant treatment, C ab represents the cost of abandoning clean energy.

4. The park energy optimization method based on a multi-objective optimization algorithm according to claim 3 is characterized in that: The equipment purchase cost is specifically: Among them, γ i represents the value retention rate of the i-th type of supply equipment, d i represents the purchase quantity of the i-th type of supply equipment, c i represents the purchase cost of the i-th supply equipment, and I represents the supply equipment set; The equipment operating costs are specifically: Among them, a i represents the unit maintenance cost of the i-th supply equipment, P i represents the output power of the i-th supply device; The specific cost of electricity purchase is: C e =Q e c e Among them, Q e represents the annual power grid purchase, c e represents the annual average electricity price; The purchase cost of natural gas is as follows: C f =Q f c f Among them, Q f represents the annual natural gas purchase volume, c f represents the annual average unit price of natural gas; The pollutant treatment costs are specifically: C pol =toilet pol Where W represents the annual pollutant emissions, c pol It represents the unit pollutant treatment cost; The clean energy abandonment cost is specifically: C ab =c ab Q a (1-η) Among them, Q a represents the annual clean energy power generation, η represents the clean energy utilization rate, c ab represents the unit clean energy abandonment cost; The annual clean energy power generation is specifically: Among them, Q k represents the annual power generation of the kth power generation equipment, K1 represents the set of photovoltaic power generation equipment, and K2 represents the set of wind power generation equipment.

5. The park energy optimization method based on a multi-objective optimization algorithm according to claim 2 is characterized in that: The upper layer constraints include: Power demand constraints: α(Q a +Q e )≥Q min Among them, Q e represents the annual power grid purchase, Q a represents the annual clean energy power generation, Q min represents the energy demand of the electric load, and α represents the power supply coefficient; Heat demand constraints: H a ≥H min Among them, H a Indicates the annual heat output of gas equipment and thermal equipment, H min represents the energy demand of thermal load; Cooling demand constraints: (1-a)b(Q a +Q e )≥L min Among them, (1-α) represents the cooling coefficient, β represents the cooling power conversion coefficient, and L min Indicates the energy demand of cooling load; Device power constraints: P j,min ≤P j ≤P j,max Among them, P j represents the power of the jth supply device, P j,min represents the lower power limit of the jth supply device, P j,max represents the power upper limit value of the jth supply device; Equipment capacity constraints: Q j,min ≤Q j ≤Q j,max Among them, Q j represents the capacity of the jth supply device, Q j,min represents the lower limit of the capacity of the jth supply device, Q j,max Represents the upper capacity limit of the j-th supply device.

6. The park energy optimization method based on a multi-objective optimization algorithm according to claim 1 is characterized in that: The S6 specifically includes: S601: constructing a lower objective function of the lower park energy optimization model with the minimum operating cost, the minimum carbon emission, and the maximum clean energy utilization rate as multiple objectives; S602: Setting lower-level constraint conditions of the lower-level park energy optimization model; S603: Perform multi-objective optimization on the lower-level park energy optimization model through a genetic algorithm to determine an energy scheduling plan between various supply devices and load devices to supply energy to the park.

7. The park energy optimization method based on a multi-objective optimization algorithm according to claim 6 is characterized in that: The energy scheduling scheme is specifically expressed as follows: L=YE Where L represents the energy demand vector of the load device, Y represents the energy scheduling plan, E represents the energy supply vector of the supply device, and y ij It represents the energy demand of the i-th load device that is supplied by the j-th supply device, L i represents the energy demand of the i-th load device, i = 1, 2, ..., m, m represents the total number of load devices, E j Represents the energy supply of the jth supply device, j = 1, 2, …, n, and n represents the total number of supply devices.

8. The park energy optimization method based on a multi-objective optimization algorithm according to claim 6 is characterized in that: The lower layer objective function is specifically: Among them, F d () represents the lower layer objective function, Y represents the energy scheduling scheme, min represents minimization, f1 represents the operating cost objective function, f2 represents the carbon emission objective function, f3 represents the clean energy utilization objective function, μ1 represents the scaling factor of the operating cost objective function, μ2 represents the scaling factor of the carbon emission objective function, and μ3 represents the scaling factor of the clean energy utilization objective function; The operating cost objective function is specifically: Among them, C op represents the equipment operating cost, d i represents the purchase quantity of the i-th type of supply equipment, a i represents the unit maintenance cost of the i-th supply equipment, P i represents the output power of the i-th supply device, and I represents the set of supply devices; The carbon emission objective function is specifically: Among them, n i represents the number of purchased supply equipment using the i-th type of raw energy, λ i represents the carbon emission coefficient of the i-th type of supply equipment using raw energy, P i represents the output power of the i-th supply device using the original energy, and I1 represents the set of supply devices using the original energy; The clean energy utilization rate objective function is specifically: Among them, η represents the utilization rate of clean energy, Q in represents the clean energy power generation, Q out Indicates the amount of clean energy used; The specific amount of clean energy used is: Where L represents the total load, Indicates the amount of electricity purchased by the power grid.

9. The park energy optimization method based on a multi-objective optimization algorithm according to claim 6 is characterized in that: The lower-level constraints specifically include: Clean energy priority constraint: give priority to the use of clean energy generated by photovoltaic power generation equipment and wind power generation equipment; Power balance constraints: P out =P r Among them, P out Indicates the output power of the supply equipment, P r Indicates the working power of the load equipment; Device power constraints: P j,min ≤P j ≤P j,max Among them, P j represents the power of the jth supply device, P j,min represents the lower power limit of the jth supply device, P j,max represents the power upper limit value of the jth supply device; Equipment capacity constraints: Q j,min ≤Q j ≤Q j,max Among them, Q j represents the capacity of the jth supply device, Q j,min represents the lower limit of the capacity of the jth supply device, Q j,max Represents the upper capacity limit of the j-th supply device.

10. A park energy optimization system based on a multi-objective optimization algorithm, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the park energy optimization method based on a multi-objective optimization algorithm as described in any one of claims 1 to 9 is implemented.

Images