Park energy consumption diagnosis and optimization method

Abstract

The invention relates to a park energy consumption diagnosis and optimization method. The method comprises the following steps: S1, analyzing various systems and subordinate energy consumption equipment involved in a park production process flow; s2, determining parameter variables of various systems and equipment required by the energy consumption calculation diagnosis and optimization model; s3, determining an energy consumption calculation and diagnosis model of each type of equipment under the jurisdiction of each system of the park; s4, determining an objective function of the park overall energy consumption optimization model; s5, determining constraint conditions of the park overall energy consumption optimization model; and S6, comparing a plurality of optimization algorithms, comprehensively selecting an optimal algorithm, and outputting a park overall energy consumption optimization suggestion. According to the method, the current running state of the equipment can be intuitively known, all the equipment and systems in the park are used as a whole for energy consumption optimization, mutual influence among the equipment is avoided, and the optimization effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving management and control, and in particular to a method for diagnosing and optimizing energy consumption in a park. Background Art

[0002] The energy consumption optimization method of the park is to comprehensively monitor, analyze and evaluate the energy usage in the park through the comprehensive use of information technology, automation technology and energy management strategies, and propose improvement measures to achieve the purpose of reducing energy consumption. This process not only helps to improve energy efficiency and reduce operating costs, but also is beneficial to environmental protection.

[0003] The current energy-saving management and control methods for parks based on modern information technology mainly focus on monitoring various indicators of equipment operation, such as current, voltage, switch status, etc., but cannot provide an overall assessment and diagnosis of the equipment's operating conditions, energy consumption status, etc.; and the optimization strategies in the current energy-saving management and control methods for parks focus on optimizing a single device or system in the park, but in fact, the optimization space for a single device or system is limited, and most of the multiple devices or systems in the park affect each other. The optimization of a single device or system is likely to affect other devices or systems in the park, causing unnecessary losses.

[0004] Based on the above problems, it is necessary to propose a park energy consumption diagnosis and optimization method, which can intuitively understand the current operating status of the equipment and optimize the energy consumption of all equipment and systems in the park as a whole, avoid mutual influence between equipment, and improve the optimization effect. Summary of the invention

[0005] The purpose of the present invention is to provide a park energy consumption diagnosis and optimization method, which can intuitively understand the current operating status of the equipment, and optimize the energy consumption of all equipment and systems in the park as a whole, avoid mutual influence between equipment, and improve the optimization effect.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is that the energy consumption diagnosis and optimization method of the park specifically includes the following steps:

[0007] S1: Analyze various systems and energy-consuming equipment involved in the production process of the park;

[0008] S2: Determine the parameter variables of various systems and equipment required for energy consumption calculation diagnosis and optimization model;

[0009] S3: Determine the energy consumption calculation and diagnosis model of various equipment under each system in the park;

[0010] S4: Determine the objective function of the overall energy consumption optimization model of the park;

[0011] S5: Determine the constraints of the overall energy consumption optimization model of the park;

[0012] S6: Compare multiple optimization algorithms, comprehensively select the optimal algorithm, and output overall energy consumption optimization suggestions for the park.

[0013] By adopting the above technical solution, the current energy consumption and energy efficiency ratio of the equipment are calculated through real-time monitoring of the equipment operation information, and the equipment operation status is diagnosed in combination with the equipment operation time, equipment rated information, etc., so that users can intuitively understand the current operation status of the equipment and make corresponding improvement suggestions; through the evaluation and diagnosis of the equipment operation status and energy consumption status in the park, users can intuitively understand the current operation status of the equipment and take corresponding optimization measures; and all equipment and systems in the park are optimized for energy consumption as a whole to avoid mutual influence between equipment and improve the optimization effect.

[0014] Preferably, in step S1, the park energy consumption system is divided into a lighting system and an air-conditioning system according to the actual production conditions of the park. The lighting system includes various lighting equipment in various areas of the park, and the air-conditioning system includes various air-conditioning equipment in various areas of the park.

[0015] Preferably, in step S2, the required variables of the energy consumption calculation diagnosis model are the device status information monitored in real time in the lighting system and the air conditioning system. The device status information includes operating current, operating voltage, switch status, operating mode, set temperature, ambient temperature, etc.

[0016] Preferably, the specific steps of step S3 are:

[0017] S31 parameter input: collect the equipment status information in the lighting system and air conditioning system as the input parameter of the energy consumption calculation diagnosis model;

[0018] S32 Energy consumption calculation: Build energy consumption calculation models in lighting system and air conditioning system according to equipment type, and output equipment operation energy consumption;

[0019] S33 Energy Consumption Diagnosis: Select the corresponding energy consumption evaluation index according to the type of equipment. For lighting equipment, compare the current energy consumption calculation results of the equipment with the rated information on the equipment nameplate to determine whether the current operating status of the equipment meets the standard. If not, provide maintenance suggestions; that is, make maintenance, repair, replacement and other suggestions for equipment that does not meet the standard; for air-conditioning equipment, diagnose the current energy efficiency rating of the air-conditioning equipment based on the energy efficiency ratio (EER) of the air-conditioning equipment. According to industry experience, the EER of low-efficiency air-conditioning is usually 8.0 or below, the EER of standard-efficiency air-conditioning is usually between 8.0 and 10.0, the EER of high-efficiency air-conditioning is usually between 10.0 and 12.0, and the EER of ultra-high-efficiency air-conditioning is usually above 12.0.

[0020] Preferably, the calculation formula of the input power P of the equipment in the park in step S32 is:

[0021] P = U * I;

[0022] In the formula, U is the operating voltage of the equipment, and I is the operating current of the equipment. The calculation formula for the energy efficiency ratio EER of the air-conditioning equipment in the park is:

[0023]

[0024] Where c is the air density at room temperature of 20°C, ρ is the air specific heat at room temperature of 20°C, L is the air volume, ΔT is the absolute difference between the air conditioner set temperature and the ambient temperature, and P is the input electrical power.

[0025] Preferably, in step S33, if EER≥12, the device is considered to be at level 1 energy efficiency; if 10>EER≥12, the device is considered to be at level 2 energy efficiency; if 8>EER≥10, the device is considered to be at level 3 energy efficiency; if EER<8, the device energy efficiency is considered to be substandard, and corresponding suggestions are provided according to the energy efficiency status.

[0026] Preferably, in step S4, the objective function of the park energy consumption system optimization model is the unit production capacity energy consumption of the park, and the objective function of the park energy consumption optimization model is:

[0027]

[0028] Preferably, in step S5, the energy consumption of the park should be optimized on the basis of meeting daily production, and the constraints include the constraints of the lighting system and the air conditioning system. According to the actual situation, the optimization parameters are the controllable variables of the equipment in the lighting system and the air conditioning system in the actual production process.

[0029] Preferably, in step S6, the intelligent algorithms used for the park energy consumption optimization model include genetic algorithm (GA), particle swarm algorithm (PSO), and differential evolution algorithm (DE), and then the optimization effect, stability, convergence speed, and resource occupancy are compared to select the best performing optimization algorithm as the target optimization algorithm of the energy consumption optimization model.

[0030] Preferably, the specific steps of selecting the differential evolution algorithm in step S6 are:

[0031] S61 Initialize the population: Randomly initialize the genes of each individual in the population as:

[0032] X i =(x i1 , x i2 , ..., x id );

[0033] Where, X i represents the gene of the i-th individual in the population. The individual has d genes, and each gene represents a controllable variable;

[0034] S62 mutation: The mutation formula of each individual depending on the other three individuals is:

[0035] U i =X r1 +F(X r2 -X r3 ), i≠r1≠r2≠r3;

[0036] Where, X r1 , X r2 , X r3 represents three different individuals in the group, F is the scaling factor, U i is the target gene after the mutation of individual i;

[0037] S63 cross: for target gene U i =(u i1 ,u i2 , ..., u id ) to obtain V i =(v i1 , v i2 , ..., v id ), the processing formula is:

[0038]

[0039] In the formula, CR is the crossover probability. The larger its value, the greater the probability of crossover. rand is a random integer in {1,2,…,D}, which is used to ensure that at least one dimension of genes in the crossover operation comes from the genes generated by the mutation operation;

[0040] S64 selection: Use the fitness function to calculate the original gene X i and the final gene V i The fitness of gene X i The fitness of gene V i The fitness of the final gene V is retained. i , otherwise keep the original gene X i :

[0041] X i =fitness_best(X i ,V i ).

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] (1) By monitoring the equipment operation information in real time, the current energy consumption and energy efficiency ratio of the equipment are calculated. The equipment operation status is diagnosed based on the equipment operation time and equipment rating information. This allows users to intuitively understand the current operation status of the equipment and make corresponding improvement suggestions.

[0044] (2) Analyze the controllable variables of the equipment in the production process of the park, and use genetic algorithm, particle swarm algorithm, differential evolution algorithm and other intelligent optimization algorithms to establish an energy consumption optimization model for the park as a whole. Considering the optimization effect, optimization stability, convergence speed, resource occupancy and other aspects, the best optimization algorithm is comprehensively selected as the target optimization algorithm, and corresponding optimization suggestions are provided. In the process, there is no need to construct a large number of complex formulas, and the optimization process is short and the optimization effect is stable. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the overall process of the method for calculating, diagnosing and optimizing the energy consumption of a park in an embodiment of the present invention;

[0046] Figure 2 It is a schematic diagram of the implementation process of the three optimization algorithms of GA, PSO and DE in the method for calculating, diagnosing and optimizing the energy consumption of a park in an embodiment of the present invention;

[0047] Figure 3 It is a distribution diagram of the number of iterations of a single optimization process of the three optimization algorithms, GA, PSO, and DE, in the park energy consumption calculation diagnosis and optimization method in the embodiment of the present invention - the optimization result;

[0048] Figure 4 It is a distribution diagram of the optimization times and optimization results of the three optimization algorithms, GA, PSO and DE, in the park energy consumption calculation diagnosis and optimization method in the embodiment of the present invention. DETAILED DESCRIPTION

[0049] The technical solution is further described below in conjunction with the accompanying drawings.

[0050] Example: Figure 1 As shown, Figure 1 The flowchart of the park energy consumption diagnosis and optimization method proposed in the embodiment of the present invention is shown. The park energy consumption diagnosis and optimization method specifically includes the following steps:

[0051] S1: Analyze various systems and energy-consuming equipment involved in the production process of the park;

[0052] In step S1, according to the actual production status of the park, the park energy consumption system is divided into a lighting system and an air-conditioning system. The lighting system includes various types of lighting equipment in various areas of the park, and the air-conditioning system includes various types of air-conditioning equipment in various areas of the park. Specifically, due to the differences in the production process involved in different types of parks, and the monitoring conditions of the equipment in various systems are also different; therefore, when selecting the energy consumption equipment involved in the park energy consumption calculation diagnosis and optimization model, it should be adjusted according to the actual situation on site of the park; in this embodiment, the main energy consumption systems in the production process of the park are the lighting system and the air-conditioning system;

[0053] S2: Determine the parameter variables of various systems and equipment required for energy consumption calculation diagnosis and optimization model;

[0054] In step S2, the required variables of the energy consumption calculation diagnosis model are the equipment status information monitored in real time in the lighting system and the air-conditioning system; the equipment status information includes operating current, operating voltage, switch status, operating mode, set temperature, ambient temperature, etc.; in this embodiment, the energy consumption calculation diagnosis model is divided into the lighting system and the air-conditioning system according to the production process of the park, and the input parameters are the operating status information of the monitored lighting and air-conditioning equipment and the rated information on the equipment nameplate; the input parameters of the model in the energy consumption optimization model are controllable variables, that is, variables that can be controlled by humans, and the controllable variables of the model should be collected and analyzed from the actual system of the park;

[0055] Specifically, the following Table 1 shows the input parameters of each energy consumption system and energy consumption optimization model of the energy consumption calculation diagnosis model in this embodiment;

[0056] Table 1 Input parameters of each model and energy consumption system

[0057]

[0058] S3: Determine the energy consumption calculation and diagnosis model of various equipment under each system in the park;

[0059] The specific steps of step S3 are:

[0060] S31 parameter input: collect the equipment status information in the lighting system and air conditioning system as the input parameter of the energy consumption calculation diagnosis model;

[0061] S32 Energy consumption calculation: Build energy consumption calculation models in lighting system and air conditioning system according to equipment type, and output equipment operation energy consumption;

[0062] The calculation formula of the input power P of the equipment in the park in step S32 is:

[0063] P = U * I;

[0064] In the formula, U is the operating voltage of the equipment, and I is the operating current of the equipment. The calculation formula for the energy efficiency ratio EER of the air-conditioning equipment in the park is:

[0065]

[0066] In the formula, c is the air density at room temperature of 20°C, ρ is the air specific heat at room temperature of 20°C, L is the air volume, ΔT is the absolute difference between the air conditioner set temperature and the ambient temperature, and P is the input power;

[0067] S33 Energy consumption diagnosis: Select the corresponding energy consumption evaluation index according to the type of equipment. For lighting equipment, compare the current energy consumption calculation results of the equipment with the rated information on the equipment nameplate to determine whether the current operating status of the equipment meets the standard. If not, provide maintenance suggestions; that is, if the current operating status of the equipment is considered abnormal, provide corresponding maintenance suggestions, such as maintenance, repair, and replacement suggestions for equipment that does not meet the standard; for air-conditioning equipment, diagnose the current energy efficiency rating of the air-conditioning equipment based on the energy efficiency ratio (EER) of the air-conditioning equipment; according to industry experience, the EER of low-efficiency air-conditioning is usually 8.0 or below, the EER of standard-efficiency air-conditioning is usually between 8.0 and 10.0, the EER of high-efficiency air-conditioning is usually between 10.0 and 12.0, and the EER of ultra-high-efficiency air-conditioning is usually above 12.0;

[0068] In step S33, if EER≥12, the device is considered to be of level 1 energy efficiency; if 10>EER≥12, the device is considered to be of level 2 energy efficiency; if 8>EER≥10, the device is considered to be of level 3 energy efficiency; if EER<8, the device is considered to be energy-inefficient and corresponding suggestions are provided according to the energy efficiency status;

[0069] In this embodiment, the collected operating status data of a certain air conditioning device is shown in the following Table 2:

[0070] Table 2 Status information monitored by air conditioning equipment A

[0071]

[0072] From the above table, the input power of the air conditioner is:

[0073] P=I*U=10.2×205.6=2103.29w;

[0074] The energy efficiency ratio of air conditioner is:

[0075]

[0076] The calculated energy efficiency ratio EER of air conditioning equipment A is between (10,12], so the current energy efficiency rating of the equipment is considered to be level 2;

[0077] S4: Determine the objective function of the overall energy consumption optimization model of the park;

[0078] In step S4, the objective function of the park energy consumption system optimization model is the unit production capacity energy consumption of the park. The objective function of the park energy consumption optimization model is:

[0079]

[0080] In this embodiment, the total capacity of the park remains basically unchanged, so the objective function of the park energy consumption optimization model can be approximated as:

[0081] Total energy consumption of the park min =min(Energy consumption of lighting system 约束条件 +Energy consumption of air conditioning system 约束条件 );

[0082] S5: Determine the constraints of the overall energy consumption optimization model of the park;

[0083] Specifically, in this embodiment, the constraints of the park system mainly include lighting system constraints and air conditioning system constraints. Obviously, the energy consumption optimization of the park needs to be carried out on the basis of meeting the production process requirements and production capacity requirements. Otherwise, simply considering reducing the energy consumption of the park may result in a reduction in unit production capacity energy consumption, but the total production capacity and production process requirements are not up to standard. According to the relationship between the objective function and the controllable variables of each device, as well as the correlation between each device, the constraints of the model are determined; the constraints should be determined according to the actual situation, generally including the equipment operating current, operating voltage, operating time, etc.

[0084] In this embodiment, the controllable variables and value ranges of the equipment in the lighting system and the air conditioning system are shown in Table 3 below:

[0085] Table 3 Controllable variables and value ranges of equipment in lighting system and air conditioning system

[0086]

[0087] In this embodiment, the objective function of the park energy consumption optimization model is:

[0088]

[0089] In the formula, m and n are the total number of equipment in the lighting system and air conditioning system respectively, and the subscript i is the equipment number;

[0090] S6: Compare multiple optimization algorithms and comprehensively select the optimal algorithm to output the overall energy consumption optimization suggestions for the park;

[0091] In step S5, the energy consumption of the park should be optimized on the basis of meeting daily production, and the constraints include the constraints of the lighting system and the air-conditioning system; according to the actual situation, the optimization parameters are the controllable variables of the equipment in the lighting system and the air-conditioning system in the actual production process;

[0092] In step S6, the intelligent algorithms used for the park energy consumption optimization model include genetic algorithm (GA), particle swarm algorithm (PSO), and differential evolution algorithm (DE). Then, the optimization algorithm with the best performance is selected as the target optimization algorithm of the energy consumption optimization model by comparing the optimization effect, stability, convergence speed, and resource occupancy; Figure 2 As shown in the figure, it is a schematic diagram of the implementation process of the genetic algorithm, particle swarm algorithm, and differential evolution algorithm selected in the park energy consumption optimization model in this embodiment; these three optimization algorithms are used to solve the objective function of the park energy consumption optimization model under the constraints of controllable variables. Considering the optimization effect, optimization stability, convergence speed, resource occupation and other aspects of the three optimization algorithms, the best optimization algorithm is comprehensively selected as the target optimization algorithm of the park energy consumption optimization model;

[0093] like Figure 3 The figure shows the distribution diagram of the number of iterations of a single optimization process of the three optimization algorithms selected in the park energy consumption optimization model in this embodiment: genetic algorithm, particle swarm algorithm, and differential evolution algorithm - optimization result. Figure 3 It can be seen that when the number of iterations reaches 2000, the three algorithms all reach a stable state. At this time, the optimization effects of the three optimization algorithms are:

[0094] Differential evolution algorithm > genetic algorithm > particle swarm algorithm;

[0095] The convergence speed is:

[0096] Differential evolution algorithm < genetic algorithm ≈ particle swarm algorithm;

[0097] like Figure 4 The figure shows the optimization times-optimization result distribution diagram of the three optimization algorithms selected in the park energy consumption optimization model in this embodiment, namely, the genetic algorithm, the particle swarm algorithm, and the differential evolution algorithm. It can be seen from the figure that in the 30 repeated optimizations, the optimization effect stability of the three optimization algorithms is:

[0098] Differential evolution algorithm > genetic algorithm > particle swarm algorithm;

[0099] Table 4 below shows the energy consumption of the three optimization algorithms after 30 repeated optimizations, and the estimated energy consumption reduction ratio:

[0100] Table 4 Energy consumption after optimization of the optimization model and the estimated energy consumption reduction ratio

[0101]

[0102] From Table 4 above, it can be seen that the optimization effect of using the differential evolution algorithm is the most obvious. The average energy consumption after optimization is 1349.60, and it is expected to reduce energy consumption by 6.19%. The variances of energy consumption after optimization by the particle swarm algorithm, genetic algorithm, and differential evolution algorithm are 4.5066, 0.7133, and 0.0104, respectively. It can be seen that the optimization effect of the differential evolution algorithm is the most stable.

[0103] After comprehensive consideration of the above optimization results, the differential evolution algorithm was finally selected as the target algorithm for the park energy consumption optimization model;

[0104] Table 5 below shows the parameter settings of the differential evolution algorithm used in the park energy consumption optimization model in this embodiment:

[0105] Table 5 Differential evolution algorithm parameter settings

[0106] parameter value Population size 400 Maximum number of iterations 2000 Crossover rate CR 0.3 Scaling factor F 0.5

[0107] The specific steps of selecting the differential evolution algorithm in step S6 are:

[0108] S61 Initialize the population: Randomly initialize the genes of each individual in the population as:

[0109] X i =(x i1 , x i2 , ..., x id );

[0110] Where, X i represents the gene of the i-th individual in the population. The individual has d genes, and each gene represents a controllable variable;

[0111] S62 mutation: The mutation formula of each individual depending on the other three individuals is:

[0112] U i =X r1 +F(X r2 -X r3 ), i≠r1≠r2≠r3;

[0113] Where, X r1 , X r2 , X r3 represents three different individuals in the group, F is the scaling factor, U i is the target gene after the mutation of individual i;

[0114] S63 cross: for target gene U i =(u i1 ,u i2 , ..., u id ) to obtain V i =(vi1 , v i2 , ..., v id ), the processing formula is:

[0115]

[0116] In the formula, CR is the crossover probability. The larger its value, the greater the probability of crossover. rand is a random integer in {1, 2, ..., D}, which is used to ensure that at least one dimension of genes in the crossover operation comes from the genes generated by the mutation operation;

[0117] S64 selection: Use the fitness function to calculate the original gene X i and the final gene V i The fitness of gene X i The fitness of gene V i The fitness of the final gene V is retained. i , otherwise keep the original gene X i :

[0118] X i =fitness_best(X i , V i ).

[0119] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for diagnosing and optimizing energy consumption in a park, characterized in that: The specific steps include: S1: Analyze various systems and energy-consuming equipment involved in the production process of the park; S2: Determine the parameter variables of various systems and equipment required for energy consumption calculation diagnosis and optimization model; S3: Determine the energy consumption calculation and diagnosis model of various equipment under each system in the park; S4: Determine the objective function of the overall energy consumption optimization model of the park; S5: Determine the constraints of the overall energy consumption optimization model of the park; S6: Compare multiple optimization algorithms, comprehensively select the optimal algorithm, and output overall energy consumption optimization suggestions for the park.

2. The method for diagnosing and optimizing park energy consumption according to claim 1, characterized in that: In step S1, the park energy consumption system is divided into a lighting system and an air-conditioning system. The lighting system includes various lighting equipment in various areas of the park, and the air-conditioning system includes various air-conditioning equipment in various areas of the park.

3. The method for diagnosing and optimizing park energy consumption according to claim 1, characterized in that: In step S2, the required variables of the energy consumption calculation diagnosis model are the equipment status information monitored in real time in the lighting system and the air-conditioning system.

4. The method for diagnosing and optimizing park energy consumption according to claim 3, characterized in that: In the step S2, the specific steps of the step S3 are: S31 parameter input: collect the equipment status information in the lighting system and air conditioning system as the input parameter of the energy consumption calculation diagnosis model; S32 Energy consumption calculation: Build energy consumption calculation models in lighting system and air conditioning system according to equipment type, and output equipment operation energy consumption; S33 Energy consumption diagnosis: Select the corresponding energy consumption evaluation index according to the type of equipment. For lighting equipment, compare the current energy consumption calculation results of the equipment with the rated information on the equipment nameplate to determine whether the current operating status of the equipment meets the standard. If not, provide maintenance suggestions; For air-conditioning equipment, the current energy efficiency rating of the air-conditioning equipment is diagnosed according to the energy efficiency ratio EER of the air-conditioning equipment.

5. The method for diagnosing and optimizing park energy consumption according to claim 4, characterized in that: The calculation formula of the input power P of the equipment in the park in step S32 is: P = U * I; In the formula, U is the operating voltage of the equipment, and I is the operating current of the equipment. The calculation formula for the energy efficiency ratio EER of the air-conditioning equipment in the park is: Where c is the air density at room temperature of 20°C, ρ is the air specific heat at room temperature of 20°C, L is the air volume, ΔT is the absolute difference between the air conditioner set temperature and the ambient temperature, and P is the input electrical power.

6. The method for diagnosing and optimizing park energy consumption according to claim 5, characterized in that: In step S33, if EER≥12, the device is considered to be at level 1 energy efficiency; if 10>EER≥12, the device is considered to be at level 2 energy efficiency; if 8>EER≥10, the device is considered to be at level 3 energy efficiency; if EER<8, the device energy efficiency is considered to be substandard, and corresponding suggestions are provided based on the energy efficiency status.

7. The method for diagnosing and optimizing park energy consumption according to claim 5, characterized in that: In step S4, the objective function of the park energy consumption system optimization model is the unit production capacity energy consumption of the park. The objective function of the park energy consumption optimization model is:

8. The method for diagnosing and optimizing park energy consumption according to claim 5, characterized in that: In step S5, the energy consumption of the park and the constraints include the constraints of the lighting system and the air conditioning system.

9. The method for diagnosing and optimizing park energy consumption according to claim 5, characterized in that: In step S6, the intelligent algorithms used for the park energy consumption optimization model include genetic algorithm, particle swarm algorithm, and differential evolution algorithm. The optimization effect, stability, convergence speed, and resource occupancy are compared, and the best performing optimization algorithm is selected as the target optimization algorithm of the energy consumption optimization model.

10. The method for diagnosing and optimizing park energy consumption according to claim 9, characterized in that: The specific steps of selecting the differential evolution algorithm in step S6 are: S61 Initialize the population: Randomly initialize the genes of each individual in the population as: X i =(x i1 ,x i2 ,...,x id ); Where, X i represents the gene of the i-th individual in the population. The individual has d genes, and each gene represents a controllable variable; S62 mutation: The mutation formula of each individual depending on the other three individuals is: U i =X r1 +F(X r2 -X r3 ),i≠r1≠r2≠r3; Where, X r1 , X r2 , X r3 represents three different individuals in the group, F is the scaling factor, U i is the target gene after the mutation of individual i; S63 cross: for target gene U i =(u i1 ,u i2 ,...,u id ) to obtain V i =(v i1 ,v i2 ,...,v id ), the processing formula is: In the formula, CR is the crossover probability. The larger its value, the greater the probability of crossover. rand is a random integer in {1,2,…,D}; S64 selection: Use the fitness function to calculate the original gene X i and the final gene V i The fitness of gene X i The fitness of gene V i The fitness of the final gene V is retained. i , otherwise keep the original gene X i , the calculation formula is: X i =fitness_best(X i ,V i )。

Images