Smart park energy consumption management method and device, electronic equipment and storage medium

Abstract

The invention provides a smart park energy consumption management method and device, electronic equipment and a storage medium, and belongs to the technical field of energy intelligent management and control, and the method comprises the steps: dividing a smart park into a plurality of business state partitions according to the regional business state type; performing chromosome coding on the energy consumption equipment type, the operation time period and the energy distribution proportion of each business state partition based on the target energy consumption boundary constraint to generate an initial population; performing genetic manipulation on the initial population to obtain a target population, and taking chromosomes with fitness values greater than a first fitness threshold value in the target population as a target solution set; constructing an initial particle swarm based on the target solution set, and carrying out iterative updating on the initial particle swarm until an iterative convergence condition is met; and taking the particle with the highest fitness in the iterative updating process as a target particle, and performing energy consumption management on the smart park based on the parameter of the target particle. According to the invention, the suitability of the energy consumption management scheme and the parameter regulation and control precision can be improved, and the comprehensive energy consumption cost of the park is reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of energy intelligent management and control, and more specifically relates to a smart park energy consumption management method and device, an electronic device, and a storage medium. BACKGROUND

[0002] A smart park is a modern park form that realizes efficient energy saving, safety and convenience by relying on new generation information technologies such as the Internet of Things, artificial intelligence and cloud computing, and comprehensively sensing, integrating and intelligently scheduling various resources such as buildings, security and operation and maintenance in the park. With the expansion and diversification of the park, the number and types of energy consumption equipment have increased dramatically, and the energy consumption structure has shown multi-source and fragmented characteristics, which has intensified the complexity of park energy management. In the prior art, the energy consumption management of a smart park mostly adopts traditional zoning monitoring or single-dimensional optimization strategies, which still have poor adaptability of the scheme, are difficult to meet the complex requirements of multi-format parks, and have insufficient optimization precision of energy consumption parameters, which are difficult to cope with complex optimization scenarios, resulting in problems such as energy waste and cost overruns. SUMMARY

[0003] The purpose of the present application is to provide a smart park energy consumption management method and device, an electronic device and a storage medium to improve the adaptability and parameter control precision of the energy consumption management scheme and reduce the comprehensive energy consumption cost of the park.

[0004] The first aspect of the embodiment of the present application provides a smart park energy consumption management method, comprising: dividing the smart park into a plurality of format zones according to regional format types; the regional format types include industrial types, office types and commercial types; determining target energy consumption boundary constraints of the plurality of format zones; performing chromosome coding on the energy consumption equipment types, operation time periods and energy distribution proportions of each format zone based on the target energy consumption boundary constraints to generate an initial population; the chromosome includes a format zone identifier segment, an equipment type coding segment, an operation time period coding segment, an energy distribution proportion coding segment and a check segment; performing genetic operations on the initial population to obtain a target population, and regarding the chromosomes with fitness values greater than a first fitness threshold in the target population as a target solution set; constructing an initial particle swarm based on the target solution set, and iteratively updating the initial particle swarm until an iteration convergence condition is met; the particles in the constructed initial particle swarm correspond one-to-one to the chromosomes in the target solution set, and each particle constructed includes parameters such as the equipment operation power of each format zone, the charge and discharge power of energy storage equipment, the renewable energy access adjustment power and the energy distribution coefficient in the peak-valley period; taking the particle with the highest fitness in the iteration update process as a target particle, and performing energy consumption management on the smart park based on the parameters of the target particle.

[0005] In a second aspect, the embodiment of the present application provides a smart park energy consumption management device, comprising: a business format partition module, configured to divide the smart park into a plurality of business format partitions according to regional business format types, wherein the regional business format types include an industrial type, an office type and a commercial type; an initialization module, configured to determine target energy consumption boundary constraints of the plurality of business format partitions, perform chromosome coding on energy consumption equipment types, running time periods and energy distribution proportions of each business format partition based on the target energy consumption boundary constraints, and generate an initial population, wherein the chromosome includes a business format partition identifier segment, an equipment type coding segment, a running time period coding segment, an energy distribution proportion coding segment and a check segment; a genetic module, configured to perform genetic operations on the initial population to obtain a target population, and take chromosomes with fitness values greater than a first fitness threshold in the target population as a target solution set; an optimization parameter module, configured to construct an initial particle swarm based on the target solution set, and perform iterative updates on the initial particle swarm until an iterative convergence condition is met, wherein particles in the constructed initial particle swarm correspond to the chromosomes in the target solution set one by one, and each particle includes parameters such as equipment running power of each business format partition, charging and discharging power of energy storage equipment, renewable energy access adjustment power and energy distribution coefficient in peak-valley time periods; an energy consumption management module, configured to take a particle with the highest fitness value in the iterative update process as a target particle, and perform energy consumption management on the smart park based on parameters of the target particle.

[0006] In a third aspect, the embodiment of the present application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and running on the processor, and the processor implements the steps of the smart park energy consumption management method when executing the computer program.

[0007] In a fourth aspect, the embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the smart park energy consumption management method when executed by a processor.

[0008] The smart park energy consumption management method and device, the electronic device and the storage medium provided by the embodiment of the present application have the following advantages: The embodiment of the application first divides the zones according to the differences of industry, office and business, then formulates exclusive energy consumption constraint rules for each zone, and binds the zone identification with the device type, running period and other key information through chromosome coding, so as to realize accurate matching of the energy consumption characteristics of different zones and solve the problem of insufficient adaptability of the traditional scheme. The embodiment of the application first determines the feasible basic scheme through reasonable screening, and then accurately optimizes the device running power, energy storage scheduling and other detailed parameters, so that the complex scene with multi-link coupling can be effectively coped with, and the parameters of each energy consumption link are in the optimal state, thereby reducing energy waste from the source.

[0009] In summary, through the design of zone adaptation and accurate regulation, the embodiment of the application can not only ensure that the energy consumption of the park meets various constraint requirements, but also maximally reduce the comprehensive energy consumption cost, realize the dual goals of efficient energy consumption and reasonable cost control, and provide a simple, feasible and effective energy consumption management solution for the smart park. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0011] Figure 1 The flowchart of the smart park energy consumption management method provided by an embodiment of the present application; Figure 2 The structural block diagram of the smart park energy consumption management device provided by an embodiment of the present application; Figure 3 The schematic block diagram of the electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures, techniques, etc. are presented in order to thoroughly understand the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits and methods are omitted to avoid unnecessary details that hinder the description of the present application.

[0013] It can be understood that in the embodiments of the present application, user information and other related data are involved, and when the embodiments of the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards.

[0014] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0015] Reference should be made to Figure 1 , Figure 1 The flowchart of the energy consumption management method of the smart park provided by an embodiment of the present application is shown. The method can be executed by an electronic device. Specifically, the method can include S101-S105.

[0016] S101: dividing the smart park into multiple industry sub-zones according to the regional industry type; the regional industry type includes industrial type, office type and commercial type.

[0017] In the present embodiment, the regional industry type is a type divided according to the functional positioning of the park area, which is used to distinguish the energy demand difference of different areas. The industrial type is an industry sub-zone type with production and manufacturing as the core function, the office type is an industry sub-zone type with daily office as the core function, and the commercial type is an industry sub-zone type with business service as the core function. The industry sub-zone is a management unit formed after the smart park is divided according to the regional industry type, which is used to realize performance energy consumption management.

[0018] Considering that the energy consumption characteristics of different functional areas of the smart park are significantly different, the industrial type area focuses on continuous energy consumption, the office type area focuses on stable energy consumption during office hours, and the commercial type area has the characteristics of concentrated business hours and large energy consumption fluctuations. However, the prior art adopts a unified management mode, which cannot adapt to the complex energy consumption demand of multiple industries, resulting in poor energy consumption management effect. Therefore, the present embodiment divides the industry sub-zone according to the regional industry type, formulates exclusive management strategies according to the energy consumption characteristics of different sub-zones, lays a foundation for subsequent precise setting of energy consumption constraints and optimization of energy consumption parameters, and solves the poor adaptability problem of traditional solutions from the root, improving the pertinence and effectiveness of energy consumption management.

[0019] Exemplarily, the embodiment can first determine the regional function layout, existing facility purpose, and operation activity type of the smart park, and establish a park regional information file. The embodiment can determine each region of the park according to a preset industry format classification standard, divide a region mainly engaged in production and manufacturing and configured with industrial production equipment as an industrial type region, divide a region mainly engaged in office work and configured with office equipment as an office type region, and divide a region mainly engaged in commercial operation and configured with commercial service facilities as a commercial type region. The embodiment can combine factors such as the physical boundary of the park and the distribution of pipelines to clearly define the specific range and boundary coordinates of each industry format partition. Finally, a unique identifier is assigned to each industry format partition to form an industry format partition management list containing information such as partition type, range, and identifier, thereby providing a basis for subsequent determination of target energy use boundary constraints.

[0020] S102: Determine the target energy use boundary constraints of the plurality of industry format partitions; encode the energy consumption device type, operation time period, and energy distribution proportion of each industry format partition based on the target energy use boundary constraints to generate an initial population; the chromosome includes an industry format partition identifier segment, a device type encoding segment, an operation time period encoding segment, an energy distribution proportion encoding segment, and a verification segment.

[0021] In the embodiment, the target energy use boundary constraints of the plurality of industry format partitions are determined, specifically including: Obtain device data, energy consumption curves, energy use boundary data, and energy resource data of the plurality of industry format partitions. For each industry format partition, divide the energy consumption curve corresponding to the industry format partition into a first energy consumption curve set and a second energy consumption curve set according to the scene identifier; the scene identifier of the first energy consumption curve set is a weekday scene, and the scene identifier of the second energy consumption curve set is a holiday scene; obtain a first energy use feature based on the first energy consumption curve set and a second energy use feature based on the second energy consumption curve set; determine the target energy use boundary constraints of the industry format partition based on the first energy use feature, the second energy use feature, the device data, the energy use boundary data, and the energy resource data.

[0022] In the embodiment, the target energy use boundary constraints of the industry format partition are determined based on the first energy use feature, the second energy use feature, the device data, the energy use boundary data, and the energy resource data, specifically including: determining a first energy use boundary constraint based on the first energy use feature, the device data, the energy use boundary data, and the energy resource data; determining a second energy use boundary constraint based on the second energy use feature, the device data, the energy use boundary data, and the energy resource data; and taking the first energy use boundary constraint and the second energy use boundary constraint as the target energy use boundary constraints.

[0023] In the embodiment, the target energy use boundary constraint is a constraint rule set by a smart park in combination with differences between different formats and scenes to ensure the device operation parameter range, energy consumption upper limit and energy use priority of the core energy use demand bottom line. The energy consumption device type is a device category that consumes energy in each format partition, which is configured according to the functional requirements of the partition. The operation period is the working time interval of the energy consumption device, which is determined according to the operation requirements of the format. The energy allocation ratio is the proportion of different energy types in the total energy consumption, which is used to balance energy utilization. The chromosome coding is to convert the energy consumption management related parameters into a coding form that can be processed by the algorithm. The initial population is the first set of candidate solutions for algorithm optimization. The format partition identification segment is the coding part of the chromosome that identifies the corresponding format partition, the device type coding segment is the coding part that records the energy consumption device type, the operation period coding segment is the coding part that represents the device operation period, the energy allocation ratio coding segment is the coding part that represents the energy allocation ratio, and the verification segment is the coding part that verifies the effectiveness of the chromosome.

[0024] The device data is the parameter information of the device in the format partition, including rated power, energy efficiency, etc. The energy consumption curve is a curve reflecting the change of the partition energy consumption with time. The energy use boundary data is the energy use upper limit, lower limit and compliance standard data of the park or partition. The energy resource data is the relevant information of various energy resources available in the park. The scene identification is the identification information that distinguishes the energy use scene. The first energy consumption curve set is the energy consumption curve set of the working day scene, and the second energy consumption curve set is the energy consumption curve set of the holiday scene. The working day scene is the energy use scene corresponding to the working day of the normal operation of the format, and the holiday scene is the energy use scene corresponding to the statutory or agreed holiday. The first energy use feature is used to represent the working day energy use rule, and the second energy use feature is used to represent the holiday energy use rule. The first energy use boundary constraint is the energy use limit adapted to the working day scene, and the second energy use boundary constraint is the energy use limit adapted to the holiday scene.

[0025] Considering that the energy use demand of each format partition is significantly different between working days and holidays, a single energy use constraint cannot adapt to the energy use characteristics of different scenes, which is easy to lead to unreasonable constraints or energy waste. Therefore, the embodiment can comprehensively master the partition energy use basic information by obtaining multi-dimensional data; the embodiment can accurately capture the energy use rules of different scenes by dividing the energy consumption curve set according to the scene identification and extracting the energy use features, which provides a basis for scene-specific constraints. The embodiment divides the constraints into the first energy use boundary constraint and the second energy use boundary constraint, which can make the constraints more suitable for the actual energy use scene. The embodiment codes the related parameters into chromosomes, which is to convert the abstract energy consumption management requirements into a form that can be processed by the algorithm. The initial population provides a variety of candidate solutions for subsequent genetic algorithm optimization, avoiding the optimization from falling into local optimum, and ensuring the scientificity and effectiveness of energy consumption management optimization from the source.

[0026] Exemplarily, the embodiment can obtain equipment data of each format partition through a park energy management platform, an equipment monitoring system and the like, including rated power, operating energy efficiency and service life of production equipment, office equipment and commercial facilities and the like. The embodiment can obtain hourly energy consumption data of the past 12 months to generate an energy consumption curve of each partition. The embodiment can obtain boundary data of energy consumption, such as an energy consumption upper limit and a power grid access standard set by the park, and energy resource data, such as a photovoltaic installed capacity and wind power output characteristics.

[0027] The embodiment can determine a scene identifier according to a date attribute, and classify energy consumption curves corresponding to Monday to Friday into a first energy consumption curve set, and classify energy consumption curves corresponding to Saturday, Sunday and statutory holidays into a second energy consumption curve set. The embodiment can calculate indexes such as average energy consumption, peak-valley period energy consumption proportion and maximum load of weekdays based on the first energy consumption curve set to form a first energy consumption feature. The embodiment can calculate indexes such as average energy consumption and load fluctuation amplitude of holidays based on the second energy consumption curve set to form a second energy consumption feature.

[0028] The embodiment can determine first energy consumption boundary constraints, such as a working day peak period energy consumption upper limit and a renewable energy access proportion lower limit, in combination with the first energy consumption feature, equipment rated power, a park energy consumption upper limit and a maximum accessible amount of photovoltaic and wind power. The embodiment can determine second energy consumption boundary constraints, such as a holiday energy consumption reduction proportion and a storage energy charging and discharging boundary, in combination with the second energy consumption feature, equipment operation and maintenance requirements, energy consumption boundary data and energy resource data, and the two are combined as target energy consumption boundary constraints.

[0029] The embodiment can construct a chromosome according to a preset coding rule. Specifically, a format partition identifier segment uses 4-digit numbers to identify partition types and numbers, a device type coding segment uses 6-digit numbers to record device categories and models, a running period coding segment uses 8-digit numbers to represent start and end times, an energy distribution proportion coding segment uses 6-digit numbers to represent proportions of various types of energy, and a verification segment uses 3-digit numbers to verify the validity of the code. All coded chromosomes are integrated to generate an initial population of appropriate size.

[0030] The embodiment extracts energy consumption features and determines target energy consumption boundary constraints by scene, so that the constraint rules accurately adapt to the energy consumption rules of different scenes of each format partition, solving the poor adaptability problem of traditional single constraints. Chromosome coding normalizes energy consumption management parameters, providing a clear object for subsequent algorithm optimization, and the initial population guarantees the diversity of optimization. The overall design improves the rationality of energy consumption constraints and the pertinence of energy consumption management, lays a foundation for subsequent precise optimization, and effectively reduces energy consumption waste and compliance risks.

[0031] S103: Perform genetic operations on the initial population to obtain a target population, and take chromosomes with an adaptability value greater than a first adaptability threshold in the target population as a target solution set.

[0032] In this embodiment, genetic operations are performed on the initial population to obtain the target population, specifically including: Calculate the fitness of all chromosomes in the initial population, and select the parent population based on the fitness of all chromosomes to obtain the parent population; Under the constraint of the target energy consumption boundary, crossover operation is performed on the parent population to obtain the offspring population; Determine the mutation probability of the coding segment, perform segmented mutation on the offspring population based on the mutation probability of the coding segment, verify the mutated chromosomes, and take the mutated chromosomes that pass the verification as the mutated population. The target population is obtained based on elite individuals and variant populations in the parent population.

[0033] In this embodiment, the fitness of all chromosomes in the initial population is calculated, specifically including: All chromosomes were analyzed and the overall energy utilization efficiency of the park, the total actual energy consumption cost of the park, and the actual access ratio of renewable energy were calculated. Based on the park's comprehensive energy utilization efficiency, the park's actual total energy consumption cost, and the actual proportion of renewable energy access, the fitness of all chromosomes in the initial population is calculated using a fitness function. The fitness function is:

[0034] in, This represents the fitness value corresponding to chromosome x. , and All are weighting coefficients, where the weighting coefficients are... , and All are real numbers in the interval 0 to 1, and satisfy the following conditions: The specific value can be determined based on the park's energy management needs (such as prioritizing cost control). The value is higher than other weighting coefficients, emphasizing the use of renewable energy. The value is higher than other weighting coefficients, and is determined in combination with the scores from park operation and maintenance experts; The overall energy utilization efficiency of the park for chromosome X. To achieve the theoretically optimal comprehensive energy utilization efficiency of the park, The total energy consumption budget preset for the park, Let X be the total actual energy consumption cost of the campus for chromosome X. This represents the actual proportion of renewable energy connected to the grid corresponding to chromosome x. Let be the penalty weight for the t-th constraint. The total number of boundary constraints for the target energy consumption. Let be the violation coefficient of the energy boundary constraint on chromosome x for the t-th item, where the constraint is not violated. =0, for partial violations, linearly mapped to the 0~1.0 interval according to the actual degree of violation. The maximum constraint violation benchmark value, representing the upper limit threshold of the coefficient when the constraint is completely violated, is set to 1.0. In this embodiment, the parent population is a high-quality population selected from the initial population for genetic crossover, obtained based on the chromosome fitness. The offspring population is a new population generated from the parent population through crossover, inheriting some gene characteristics from the parent. The mutated population is the offspring population after segmented mutation and verification, possessing new gene combinations. Elite individuals are chromosomes with high fitness rankings (greater than the preset fitness threshold) in the parent population, used to retain high-quality genes. The coding segment mutation probability is a mutation probability set for different coding segments of chromosomes, adapting to the characteristics of each coding segment. The first fitness threshold is a critical value for selecting the target solution set; chromosomes with a value higher than this are selected. The fitness function is a mathematical model that quantifies the quality of chromosomes, calculating fitness by comprehensively considering multiple dimensions. The weighting coefficient is a coefficient that balances comprehensive energy utilization efficiency, cost, and other indicators to ensure balanced multi-objective optimization. The maximum constraint violation benchmark value is a benchmark value with unified dimensions for the constraint violation penalty term.

[0035] Genetic operations must balance population diversity with the preservation of high-quality genes to avoid optimization getting trapped in local optima. Fitness calculations can accurately assess chromosome quality, providing a basis for population selection. Selecting parental populations focuses on high-quality individuals, ensuring a solid genetic foundation; crossover operations introduce new gene combinations, enriching population diversity; segmented mutation sets probabilities for different coding segments to avoid excessive mutation of critical codes; verification steps ensure that mutated chromosomes meet constraints, avoiding invalid solutions. Preserving elite individuals prevents the loss of high-quality genes; the fitness function integrates multiple objectives and constraint penalties, ensuring that the optimization direction aligns with core energy management needs. Through multi-step collaborative improvements, the quality of the target population is enhanced, providing support for subsequent selection of high-quality target solutions.

[0036] For example, in this embodiment, each chromosome in the initial population can be analyzed first to extract parameters such as the equipment type operating time and energy allocation ratio of each business zone. Combined with basic information such as the energy consumption curve of the park equipment data, the comprehensive energy utilization efficiency of the park, the total actual energy consumption cost of the park, and the actual access ratio of renewable energy corresponding to each chromosome can be calculated.

[0037] In this embodiment, the three indicators mentioned above can be substituted into the fitness function, combined with preset weight coefficients and the maximum constraint violation benchmark value, to calculate the fitness of all chromosomes. Based on fitness, an elite retention strategy and roulette wheel selection are adopted to retain the top 10% of chromosomes in terms of fitness as elite individuals, and then the remaining individuals are selected according to their fitness percentage to form the parent population.

[0038] Under the constraint of the target energy use boundary, the present embodiment can perform a crossover operation on the parent population, for example, keeping the format partition identification segment and the verification segment unchanged, performing random segmentation and recombination on the device type code segment, and generating a child population. The difference coding segment mutation probability is set, the device type coding segment is set to 0.02, the running time coding segment is set to 0.05, and the energy distribution ratio coding segment is set to 0.08. The child population is subjected to segmented mutation.

[0039] After mutation, the present embodiment can verify whether the chromosome conforms to the target energy use boundary constraint through the verification segment, eliminate illegal individuals, and form a mutation population. Finally, the elite individuals in the parent population are combined with the mutation population, and duplicate chromosomes are removed to form a target population with the same size as the initial population. Chromosomes with an adaptability value greater than the first adaptability threshold value are selected as the target solution set.

[0040] The present embodiment constructs an adaptability function through multi-dimensional indexes to ensure comprehensive and accurate evaluation of the quality of chromosomes, and avoid optimization deviation guided by a single index. In genetic operation, the parent selection focuses on high-quality genes, the crossover and mutation enrich the diversity of the population, the segmented mutation and verification guarantee the effectiveness of the solution, and the elite individuals are retained to prevent loss of high-quality features. The final generated target population has high quality, the target solution set has strong adaptability and compliance, and provides a high-quality basis for subsequent particle swarm optimization, improving the scientificity and efficiency of energy consumption management optimization.

[0041] S104: Based on the target solution set, an initial particle swarm is constructed, and the initial particle swarm is iteratively updated until the iteration convergence condition is met. The particles in the constructed initial particle swarm correspond one-to-one to the chromosomes in the target solution set, and each particle constructed includes parameters such as the device running power of each format partition, the charge and discharge power of the energy storage device, the renewable energy access adjustment power, and the energy distribution coefficient in the peak and valley periods.

[0042] In the present embodiment, the initial particle swarm is the first generation particle set of the particle swarm optimization algorithm based on the target solution set, which is used for subsequent continuous parameter optimization. The particle is the basic optimization unit of the particle swarm optimization algorithm, which carries specific energy consumption control parameters. The device running power is the power value of the energy consumption device working in each format partition, which is directly related to the energy consumption level. The charge and discharge power of the energy storage device is the power parameter in the charging and discharging process of the energy storage system, which is used to balance the energy supply and demand. The renewable energy access adjustment power is the power value of real-time adjustment of renewable energy such as photovoltaic and wind power access to the park, which is adapted to energy output fluctuation. The peak and valley period energy distribution coefficient is a parameter for dividing the energy consumption proportion of peak and valley segments, which is adapted to the difference between peak and valley electricity prices. Iterative updating is a cyclic process of adjusting particle parameters through an algorithm to approximate the optimal solution. The iteration convergence condition is a standard for judging whether the iteration is stopped, which ensures that the optimization reaches a stable effect.

[0043] The chromosome of the target solution set has determined the macro feasible scheme (device type, operation period, etc.), but lacks accurate regulation of continuous parameters, while the particle swarm algorithm is good at handling continuous space optimization. The particles correspond one-to-one to the chromosomes, and can be refined and regulated within the macro feasible framework to avoid parameter optimization from deviating from the constraints. The parameters contained in the particles are all core continuous variables of energy management, which directly affect energy efficiency, cost, and energy balance. Iterative updating can gradually optimize parameter values, and the iterative convergence condition can prevent ineffective iteration, balancing optimization effect and efficiency, and further improving the scientificity and practicality of the energy management scheme through accurate regulation of continuous parameters.

[0044] For example, the embodiment can first analyze each chromosome in the target solution set, extract the corresponding industry format partition device type, operation period, and energy allocation ratio, etc. macro parameters, and use them as the parameter constraint boundary of the corresponding particle to ensure that the particle parameter optimization does not deviate from the feasible framework.

[0045] The embodiment can construct a corresponding particle for each chromosome. Specifically, the device operation power is set to an initial value in the range of 60%-100% of the rated power of the corresponding device, combined with the energy consumption characteristics of the industry format partition; the charge and discharge power of the energy storage device is set to an initial value of 30%-70% of the rated power of the energy storage device and historical load fluctuation data of the park, and the initial value of the discharge power is set to 20%-60% of the rated power; the initial value of the renewable energy access adjustment power is set according to the power range corresponding to the allocation ratio based on the energy allocation ratio and the installed capacity of renewable energy; the energy consumption distribution coefficient of the peak valley period is combined with the historical peak valley energy consumption proportion, and the initial coefficient of the peak segment is set to 0.3-0.5, and the initial coefficient of the valley segment is set to 0.5-0.7.

[0046] All the constructed particles are integrated to form an initial particle swarm. The embodiment can start the iterative updating process. In each iteration, the parameters are dynamically adjusted according to the particle fitness calculation result. Specifically, the device operation power is optimized based on the real-time load of the park, the energy storage charge and discharge power is adjusted according to the energy supply and demand gap, the access power is adjusted according to the real-time output of renewable energy, and the energy consumption distribution coefficient is optimized according to the peak valley price difference. After each update, it is judged whether the iterative convergence condition is met. If the global optimal particle parameter fluctuation of the last 5 iterations is less than a preset threshold, the iteration is stopped; if not, the cycle is continued until the iterative convergence condition is met.

[0047] S105: Take the particle with the highest fitness in the iterative updating process as the target particle, and perform energy management on the smart park based on the parameters of the target particle.

[0048] In this embodiment, the target particle is the particle with the highest fitness in the initial particle swarm iteration update process, carries the optimal continuous parameters of energy consumption management of the smart park, is the core output of algorithm optimization, and is used to directly guide the actual energy consumption management of the park to ensure the optimality of the management strategy. The iteration update has realized accurate parameter optimization through the particle swarm algorithm, and the particle with the highest fitness corresponds to the optimal scheme of energy consumption management. Taking it as the target particle can convert the algorithm optimization results into a feasible management strategy, so that each industry partition uses energy according to the optimal parameters, and ensures that the energy consumption management achieves the core goal of high efficiency, low cost and compliance.

[0049] For example, the embodiment can collect the fitness records of all particles in the iteration process after the initial particle swarm iteration update meets the convergence condition, and select the particle with the highest fitness value as the target particle. The embodiment can analyze the parameters of the target particle to determine the specific values of the device operating power, the charging and discharging power of the energy storage device, the adjustable power of the renewable energy source and the energy distribution coefficient of the peak and valley period of each industry partition. The embodiment can synchronize these parameters to the park energy management platform and execute them according to the industry partition. For example, the industrial partition schedules production energy consumption equipment according to the optimal device operating power, the office partition adjusts the operating power of air conditioning and lighting according to the parameters, and the commercial partition optimizes the power structure according to the peak and valley energy distribution coefficient. The parameter execution effect is monitored in real time throughout the process to ensure that the energy consumption management is implemented according to the optimal strategy.

[0050] From the above, the embodiment first divides the partitions according to the differences of the industry types of industry, office and commerce, then formulates exclusive energy consumption constraints for each partition, and binds the partition identifier with the device type, operating period and other key information through chromosome coding to accurately match the energy consumption characteristics of different partitions and solve the problem of insufficient adaptability of traditional schemes. The embodiment first determines a feasible basic scheme through reasonable screening, and then accurately optimizes the device operating power, energy storage scheduling and other detailed parameters, so that the two-step cooperation can effectively cope with the complex scene of multi-link coupling and make each energy consumption link in the optimal state to reduce energy waste from the source.

[0051] In summary, the embodiment can ensure that the park energy consumption meets various constraint requirements and maximally reduce the comprehensive energy consumption cost through the design of partition adaptation and accurate regulation, realizes the dual goals of efficient energy consumption and reasonable cost control, and provides a simple, feasible and effective energy consumption management solution for smart parks.

[0052] In an embodiment of the present application, all chromosomes are analyzed and the park comprehensive energy utilization efficiency and the park actual energy consumption total cost are calculated, including: The industry partition identifier segment and the device type coding segment of all chromosomes are analyzed to obtain all industry partitions of the park and the energy consumption devices of each industry partition, respectively. Retrieve the device operation parameters corresponding to each energy-consuming device from the device parameter database, the device operation parameters including load rate and energy efficiency curve, energy conversion efficiency; Parse the runtime period encoding segment and the energy allocation proportion encoding segment of all chromosomes to obtain the device runtime period of each energy-consuming device and the proportion of each energy type, respectively; For each energy-consuming device, calculate the theoretical total input energy based on the device runtime period corresponding to the energy-consuming device, determine the energy loss coefficient based on the proportion of each energy type corresponding to the energy-consuming device, calculate the actual total input energy of the energy-consuming device based on the energy loss coefficient and the theoretical total input energy, and calculate the effective utilization energy of the energy-consuming device based on the actual total input energy and the device operation parameters corresponding to the energy-consuming device; Calculate the comprehensive energy utilization efficiency of the park based on the effective utilization energy and the actual total input energy of all devices corresponding to all format partitions; For each format partition, obtain the electricity consumption and electricity price of all energy-consuming devices in the format partition during the device runtime period, calculate the grid electricity cost based on the electricity consumption and the electricity price, and calculate the renewable energy cost and the energy storage cost according to the device runtime period and the proportion of each energy type of each energy-consuming device in the format partition, respectively; Calculate the actual total energy consumption cost of the park based on the grid electricity cost, the renewable energy cost, and the energy storage cost corresponding to all format partitions.

[0053] In this embodiment, all chromosomes are parsed and the actual renewable energy access proportion is calculated, specifically including: Parse the energy allocation proportion encoding segment of all chromosomes to obtain the renewable energy allocation proportion interval of each format partition; Select the renewable energy main period from the device runtime period of each energy-consuming device, and calculate the actual renewable energy access amount of each renewable energy main period based on the renewable energy installed capacity of all format partitions and the renewable energy allocation proportion interval of all format partitions; Calculate the actual renewable energy access proportion based on the actual total input energy and the actual renewable energy access amount.

[0054] In this embodiment, the device operating parameter is the core technical parameter of the energy consumption device, including the load rate and energy efficiency curve, energy conversion efficiency, which is used to calculate the energy utilization related indicators. The load rate and energy efficiency curve is a curve reflecting the relationship between device load and energy efficiency, and the energy conversion efficiency is the proportion of input energy converted into effective energy by the device. The theoretical total input energy is the energy input amount in the ideal state based on the device operating period, the energy loss coefficient is the loss proportion in the energy transmission and conversion process, and the actual total input energy is the actual energy input amount after deducting the loss from the theoretical value. The effective energy utilization amount is the energy amount actually utilized by the device. The electricity consumption is the electricity consumption in the device operating period, the electricity price is the price standard of electricity, and the grid electricity cost is the cost of using grid electricity. The renewable energy cost is the related cost of using renewable energy, and the energy storage cost is the cost of using the energy storage system. The renewable energy distribution proportion interval is the range of the proportion of renewable energy in each subzone, the renewable energy main period is the period with stable renewable energy output and high proportion, the renewable energy installed capacity is the total installed power of the renewable energy device in the park, and the actual renewable energy access amount is the actual renewable energy access amount in the park in the period.

[0055] The park comprehensive energy utilization efficiency, the actual total energy consumption cost, and the actual renewable energy access proportion are the core indicators for evaluating the pros and cons of the energy consumption scheme, and their calculation needs to be based on the key parameters of the chromosome analysis and the actual characteristics of the device to ensure the accuracy and reliability of the data. By analyzing the chromosome to obtain the basic decision parameters, and combining with the device parameter database to retrieve the device core parameters, the pertinence of the calculation can be ensured. The introduction of the energy loss coefficient can reflect the actual loss of energy transmission and conversion, making the total input energy calculation more practical; screening the renewable energy main period can match the renewable energy output characteristics, ensuring the accuracy of the access proportion calculation. Multi-dimensional cost splitting and comprehensive summary can fully reflect the energy consumption cost composition, provide comprehensive and accurate input data for the fitness function, and support subsequent optimization decisions.

[0056] For example, in this embodiment, each chromosome in the initial population can be analyzed first. From the business zoning identification segment and the device type coding segment, the industrial, office and commercial business zoning and corresponding energy consumption devices in the park are determined, such as air compressors in industrial zoning, central air conditioners in office zoning; from the operating period coding segment, the air compressor operating period 8:00-22:00 and the central air conditioner operating period 9:00-18:00 are obtained, and from the energy distribution proportion coding segment, the industrial zoning grid electricity proportion 60%, renewable energy proportion 25%, and energy storage proportion 15% are obtained.

[0057] The embodiment can call the load rate and energy efficiency curve of the air compressor from the device parameter database, and the corresponding parameters of the central air conditioner. For the air compressor, the embodiment can calculate the theoretical total input energy 1400 kWh according to the rated power 100 kW and the running time 14 hours. The embodiment can determine the energy loss coefficient 5% according to the transmission loss of renewable energy and energy storage, calculate the actual total input energy 1400* (1+5%) =1470 kWh, and calculate the effective utilization energy 1470*82%=1205.4 kWh according to the energy efficiency 82% corresponding to the load rate 70%. Similarly, the relevant data of all devices is calculated, and the total effective utilization energy and the actual total input energy of all format partition devices are summarized to obtain the comprehensive energy utilization efficiency of the park.

[0058] For the industrial partition, the embodiment can count the electricity consumption 1000 kWh of the air compressor and other devices during the running period, calculate the grid electricity cost according to the peak-valley electricity price; calculate the renewable energy cost according to the renewable energy proportion 25% and the operation and maintenance rate 0.05 yuan / kWh, and calculate the energy storage cost according to the energy storage proportion 15% and the depreciation + loss rate 0.1 yuan / kWh; and summarize the total cost of all partitions to obtain the actual total energy consumption cost of the park.

[0059] The embodiment can analyze the renewable energy distribution proportion interval of each partition, select the main period 9:00-16:00 with stable photovoltaic output, calculate the actual renewable energy access amount 100*0.8*7=560 kWh according to the park photovoltaic installed capacity 100 kW and the output coefficient 0.8, and calculate the actual renewable energy access proportion according to the actual total input energy of all devices.

[0060] In the embodiment, the comprehensive energy utilization efficiency of the park is calculated based on the effective utilization energy and the actual total input energy of all devices corresponding to all format partitions, specifically including: The comprehensive energy utilization efficiency of the park is calculated based on the effective utilization energy and the actual total input energy of all devices corresponding to all format partitions by the first formula; The first formula is:

[0061] Wherein, is the comprehensive energy utilization efficiency of the park, is the effective utilization energy of the e-th energy consumption device in the p-th format partition corresponding to the chromosome x, is the input energy of the e-th energy consumption device in the p-th format partition corresponding to the chromosome x, and P is the total number of format partitions covered by the chromosome x, is the number of core energy consumption devices in the p-th format partition.

[0062] In the embodiment, the total actual energy consumption cost of the park is calculated based on the grid electricity cost, renewable energy cost and energy storage cost corresponding to all format partitions, specifically including: Based on the grid electricity cost, renewable energy cost and energy storage cost corresponding to all format partitions, the total actual energy consumption cost of the park is calculated by a second formula; The second formula is:

[0063] Among them, the total actual energy consumption cost of the park, the grid electricity use cost of the pth format partition corresponding to the chromosome x, the renewable energy operation and maintenance cost of the pth format partition corresponding to the chromosome x, the energy storage system use cost of the pth format partition corresponding to the chromosome x, the energy consumption equipment operation and maintenance cost of the pth format partition corresponding to the chromosome x.

[0064] In the embodiment, the actual renewable energy access ratio is calculated based on the total actual input energy and the actual renewable energy access amount, specifically including: Based on the total actual input energy and the actual renewable energy access amount, the actual renewable energy access ratio is calculated by a third formula; The third formula is:

[0065] Among them, the actual renewable energy access ratio, the actual renewable energy access amount of the pth format partition corresponding to the chromosome x, the total energy consumption amount of the pth format partition corresponding to the chromosome x.

[0066] The embodiment realizes accurate calculation of core indicators by hierarchical analysis of key coding segments of chromosomes, combined with device parameter database and actual operation characteristics. The consideration of energy loss coefficient and renewable energy main period makes the calculation result fit the actual scene, and the cost splitting calculation comprehensively covers various energy expenditures. The calculation logic of the three indicators is rigorous and the data source is reliable, providing high-quality input for the fitness function and ensuring that the genetic algorithm can accurately select high-quality chromosomes, laying a solid foundation for subsequent optimization and helping to achieve the management goal of efficient energy consumption, controllable cost and high green electricity proportion.

[0067] The smart park energy consumption management method corresponding to the above embodiment, Figure 2 is a structural block diagram of a smart park energy consumption management device provided by an embodiment of the present application. For ease of illustration, only parts related to the embodiments of the present application are shown.Figure 2 The smart park energy consumption management device 20 comprises an industry format partition module 21, an initialization module 22, a genetic module 23, an optimization parameter module 24, and an energy consumption management module 25.

[0068] The industry format partition module 21 is configured to divide the smart park into multiple industry format partitions according to regional industry format types; the regional industry format types include industrial types, office types, and commercial types. The initialization module 22 is configured to determine target energy consumption boundary constraints of the multiple industry format partitions; perform chromosome coding on energy consumption equipment types, operation time periods, and energy distribution proportions of each industry format partition based on the target energy consumption boundary constraints to generate an initial population; the chromosome includes an industry format partition identifier segment, an equipment type coding segment, an operation time period coding segment, an energy distribution proportion coding segment, and a check segment. The genetic module 23 is configured to perform genetic operations on the initial population to obtain a target population, and take chromosomes with fitness values greater than a first fitness threshold in the target population as a target solution set. The optimization parameter module 24 is configured to construct an initial particle swarm based on the target solution set, and iteratively update the initial particle swarm until an iteration convergence condition is met; the particles in the constructed initial particle swarm one-to-one correspond to the chromosomes in the target solution set, and each particle includes parameters such as equipment operation power of each industry format partition, charging and discharging power of energy storage equipment, renewable energy access adjustment power, and energy distribution coefficient in peak and valley time periods. The energy consumption management module 25 is configured to take a particle with the highest fitness in the iteration update process as a target particle, and perform energy consumption management on the smart park based on parameters of the target particle.

[0069] In an embodiment of the present application, when determining the target energy consumption boundary constraints of the multiple industry format partitions, the initialization module 22 is specifically configured to: obtain device data, energy consumption curves, energy consumption boundary data, and energy resource data of the multiple industry format partitions. For each industry format partition, the energy consumption curve corresponding to the industry format partition is divided into a first energy consumption curve set and a second energy consumption curve set according to the scene identifier; the scene identifier of the first energy consumption curve set is a weekday scene, and the scene identifier of the second energy consumption curve set is a holiday scene; a first energy consumption feature is obtained based on the first energy consumption curve set, and a second energy consumption feature is obtained based on the second energy consumption curve set; and the target energy consumption boundary constraints of the industry format partition are determined based on the first energy consumption feature, the second energy consumption feature, the device data, the energy consumption boundary data, and the energy resource data.

[0070] In an embodiment of the present application, the initialization module 22, when determining the target energy use boundary constraint of the industry format partition based on the first energy use feature, the second energy use feature, the device data, the energy use boundary data and the energy resource data, is specifically configured to: determine the first energy use boundary constraint based on the first energy use feature, the device data, the energy use boundary data and the energy resource data; determine the second energy use boundary constraint based on the second energy use feature, the device data, the energy use boundary data and the energy resource data; and take the first energy use boundary constraint and the second energy use boundary constraint as the target energy use boundary constraint.

[0071] In an embodiment of the present application, the genetic module 23, when performing genetic operations on the initial population to obtain the target population, is specifically configured to: calculate the fitness of all chromosomes in the initial population, perform parent population selection based on the fitness of all chromosomes to obtain a parent population; perform cross operations on the parent population under the target energy use boundary constraint to obtain a child population; determine a coding segment mutation probability, perform segment mutation on the child population based on the coding segment mutation probability, and perform verification on the mutated chromosomes, taking the mutated chromosomes that pass the verification as a mutation population; obtain the target population based on the elite individuals in the parent population and the mutation population.

[0072] In an embodiment of the present application, the genetic module 23, when calculating the fitness of all chromosomes in the initial population, is specifically configured to: analyze all chromosomes and calculate the park comprehensive energy utilization efficiency, the park actual total energy consumption cost and the actual renewable energy access ratio; calculate the fitness of all chromosomes in the initial population through a fitness function based on the park comprehensive energy utilization efficiency, the park actual total energy consumption cost and the actual renewable energy access ratio; The fitness function is:

[0073] wherein, is the fitness value corresponding to the chromosome x, , and are weight coefficients, , is the park comprehensive energy utilization efficiency of the chromosome x, is the theoretical optimal comprehensive energy utilization efficiency of the park, is the preset total energy consumption budget of the park, is the park actual total energy consumption cost of the chromosome x, is the actual renewable energy access ratio corresponding to the chromosome x, a violation coefficient of a chromosome x to a tthtarget energy boundary constraint, a penalty weight of a tthconstraint, a total number of target energy boundary constraints, a maximum constraint violation benchmark value.

[0074] In an embodiment of the present application, the genetic module 23 is specifically used for: parsing the format partition identifier segment and the equipment type code segment of all chromosomes to obtain all format partitions of the park and energy-consuming equipment of each format partition, respectively; obtaining the equipment operation parameters of each energy-consuming equipment from the equipment parameter database, wherein the equipment operation parameters include load rate and energy efficiency curve, and energy conversion efficiency; parsing the operation period code segment and the energy distribution proportion code segment of all chromosomes to obtain the equipment operation period of each energy-consuming equipment and the proportion of each energy type, respectively; for each energy-consuming equipment, calculating the theoretical total input energy based on the equipment operation period corresponding to the energy-consuming equipment, determining the energy loss coefficient based on the proportion of each energy type corresponding to the energy-consuming equipment, calculating the actual total input energy of the energy-consuming equipment based on the energy loss coefficient and the theoretical total input energy, and calculating the effective utilization energy of the energy-consuming equipment based on the actual total input energy and the equipment operation parameters corresponding to the energy-consuming equipment; calculating the comprehensive energy utilization efficiency of the park based on the effective utilization energy and the actual total input energy of all equipment corresponding to all format partitions; for each format partition, obtaining the electricity consumption and electricity price of all energy-consuming equipment in the equipment operation period, calculating the grid electricity cost based on the electricity consumption and the electricity price, and calculating the renewable energy cost and the energy storage cost based on the equipment operation period and the proportion of each energy type of each energy-consuming equipment of the format partition, respectively; calculating the actual total energy consumption cost of the park based on the grid electricity cost, the renewable energy cost, and the energy storage cost corresponding to all format partitions.

[0075] In an embodiment of the present application, the genetic module 23 is specifically used for: parsing the energy distribution proportion code segment of all chromosomes to obtain the renewable energy distribution proportion interval of each format partition; obtaining the renewable energy main period from the equipment operation period of each energy-consuming equipment, calculating the actual renewable energy access amount of each renewable energy main period based on the renewable energy installed capacity of all format partitions and the renewable energy distribution proportion interval of all format partitions, and The actual renewable energy integration ratio is calculated based on the actual total energy input and the actual renewable energy integration volume.

[0076] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned device embodiments, for example... Figure 2 The functions of the business format partitioning module 21, initialization module 22, genetic module 23, optimization parameter module 24, and energy consumption management module 25 are shown.

[0077] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), but it may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0078] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0079] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information about smart campus devices.

[0080] In specific implementations, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present application can perform the implementation manners described in the embodiments of the energy consumption management method of the smart park provided by the embodiments of the present application, and can also perform the implementation manners of the electronic device 300 described in the embodiments of the present application, which will not be described here.

[0081] In another embodiment of the present application, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which are executed by a processor to implement all or part of the processes of the above-mentioned embodiments. The computer program can also be used to instruct related hardware to complete the processes. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0082] The computer readable storage medium can be an internal storage unit of the electronic device of any of the above-mentioned embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0083] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the electronic device and the unit described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0084] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the electronic device and the unit described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0085] In several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the modules / units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules / units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed each other can be indirect coupling or communication connection through some interfaces or modules / units, and can also be electrical, mechanical or other form of connection.

[0086] The modules / units described as separate components can or can not be physically separated, and the components shown as modules / units can or can not be physical modules / units, that is, can be located in one place, or can be distributed on a plurality of network modules / units. Part or all of the modules / units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0087] In addition, each functional module / unit in each embodiment of the present application can be integrated in one processing module / unit, or each module / unit can exist physically, or two or more modules / units can be integrated in one module / unit. The integrated module / unit can be realized in the form of hardware or in the form of a software functional module / unit.

[0088] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A smart park energy consumption management method, characterized in that, include: The smart park is divided into multiple business type zones based on the regional business type; the regional business type includes industrial, office and commercial types. Determine the target energy consumption boundary constraints for multiple business type zones; based on the target energy consumption boundary constraints, perform chromosome encoding on the energy-consuming equipment type, operating period, and energy allocation ratio of each business type zone to generate an initial population; the chromosome includes a business type zone identifier segment, equipment type encoding segment, operating period encoding segment, energy allocation ratio encoding segment, and verification segment; Genetic operations are performed on the initial population to obtain the target population, and chromosomes in the target population with fitness values ​​greater than a first fitness threshold are used as the target solution set; An initial particle swarm is constructed based on the target solution set, and the initial particle swarm is iteratively updated until the iterative convergence condition is met. The particles in the constructed initial particle swarm correspond one-to-one with the chromosomes in the target solution set. The parameters included in each constructed particle are the equipment operating power of each business zone, the charging and discharging power of energy storage equipment, the renewable energy access regulation power, and the peak and valley time energy consumption allocation coefficient. The particle with the highest fitness during the iterative update process is used as the target particle, and energy consumption management is performed on the smart park based on the parameters of the target particle.

2. The smart park energy consumption management method as described in claim 1, characterized in that, The determination of target energy consumption boundary constraints for multiple business type zones includes: Acquire equipment data, energy consumption curves, energy consumption boundary data, and energy resource data from multiple business sectors; For each business type zone, the energy consumption curves corresponding to that business type zone are divided into a first energy consumption curve set and a second energy consumption curve set according to the scene identifier; the scene identifier of the first energy consumption curve set is a weekday scene, and the scene identifier of the second energy consumption curve set is a holiday scene; a first energy consumption feature is obtained based on the first energy consumption curve set, and a second energy consumption feature is obtained based on the second energy consumption curve set; the target energy consumption boundary constraint of that business type zone is determined based on the first energy consumption feature, the second energy consumption feature, the equipment data, the energy consumption boundary data, and the energy resource data.

3. The smart park energy consumption management method as described in claim 2, characterized in that, The determination of the target energy consumption boundary constraint for the business type zone based on the first energy consumption characteristic, the second energy consumption characteristic, the equipment data, the energy consumption boundary data, and the energy resource data includes: The first energy consumption boundary constraint is determined based on the first energy consumption characteristic, the equipment data, the energy consumption boundary data, and the energy resource data; The second energy consumption boundary constraint is determined based on the second energy consumption characteristic, the equipment data, the energy consumption boundary data, and the energy resource data; The first energy consumption boundary constraint and the second energy consumption boundary constraint are used as the target energy consumption boundary constraints.

4. The smart park energy consumption management method as described in claim 1, characterized in that, The genetic operation performed on the initial population to obtain the target population includes: Calculate the fitness of all chromosomes in the initial population, and select the parent population based on the fitness of all chromosomes to obtain the parent population; Under the constraint of the target energy consumption boundary, a crossover operation is performed on the parent population to obtain the offspring population; Determine the mutation probability of the coding segment, perform segmented mutation on the offspring population based on the mutation probability of the coding segment, verify the mutated chromosomes, and take the mutated chromosomes that pass the verification as the mutated population. The target population is obtained based on the elite individuals in the parent population and the mutant population.

5. The smart park energy consumption management method as described in claim 4, characterized in that, The calculation of the fitness of all chromosomes in the initial population includes: All chromosomes were analyzed and the overall energy utilization efficiency of the park, the total actual energy consumption cost of the park, and the actual access ratio of renewable energy were calculated. Based on the comprehensive energy utilization efficiency of the park, the actual total energy consumption cost of the park, and the actual access ratio of renewable energy, the fitness of all chromosomes in the initial population is calculated using a fitness function. The fitness function is: in, This represents the fitness value corresponding to chromosome x. , and All are weighting coefficients. , The overall energy utilization efficiency of the park for chromosome X. To achieve the theoretically optimal comprehensive energy utilization efficiency of the park, The total energy consumption budget preset for the park, Let X be the total actual energy consumption cost of the campus for chromosome X. This represents the actual proportion of renewable energy connected to the grid corresponding to chromosome x. Let be the violation coefficient of the energy boundary constraint applied to chromosome x for item t. Let be the penalty weight for the t-th constraint. The total number of boundary constraints for the target energy use. The maximum constraint violation of the benchmark value.

6. The smart park energy consumption management method as described in claim 5, characterized in that, All chromosomes were analyzed, and the overall energy utilization efficiency of the park and the total actual energy consumption cost of the park were calculated, including: The business type partition identifier segment and equipment type code segment of all chromosomes are parsed to obtain the energy consumption equipment of all business type partitions in the park and each business type partition. Retrieve the equipment operating parameters corresponding to each energy-consuming device from the equipment parameter database. The equipment operating parameters include load rate and energy efficiency curve, and energy conversion efficiency. The runtime segment coding segment and energy allocation ratio coding segment of all chromosomes are parsed to obtain the device runtime segment and the proportion of each energy type for each energy-consuming device. For each energy-consuming device, the theoretical total input energy is calculated based on the device's operating period; the energy loss coefficient is determined based on the proportion of each energy type corresponding to the energy-consuming device; the actual total input energy is calculated based on the energy loss coefficient and the theoretical total input energy; and the effective energy utilization is calculated based on the actual total input energy and the device's operating parameters. The overall energy efficiency of the park is calculated based on the effective energy utilization and actual total energy input of all equipment corresponding to all business zones. For each business segment, obtain the electricity consumption and electricity price of all energy-consuming devices in that business segment during the device's operating period; calculate the grid electricity cost based on the electricity consumption and the electricity price; calculate the renewable energy cost and energy storage cost according to the operating period of each energy-consuming device in that business segment and the proportion of each energy type. The total actual energy consumption cost of the park is calculated based on the grid electricity cost, renewable energy cost, and energy storage cost corresponding to all business zones.

7. The smart park energy consumption management method as described in claim 6, characterized in that, All chromosomes were analyzed and the actual renewable energy integration ratio was calculated, including: The energy allocation ratio coding segments of all chromosomes are analyzed to obtain the renewable energy allocation ratio ranges for each business sector. The main renewable energy periods are selected from the operating periods of various energy-consuming equipment; the actual renewable energy access volume for each main renewable energy period is calculated based on the renewable energy installed capacity of all business sectors and the renewable energy allocation ratio range of all business sectors. The actual renewable energy access ratio is calculated based on the actual total input energy and the actual renewable energy access volume.

8. A smart park energy management device, characterized in that, include: The business type zoning module is used to divide the smart park into multiple business type zones according to the regional business type; the regional business type includes industrial type, office type and commercial type; An initialization module is used to determine the target energy consumption boundary constraints for multiple business type zones; based on the target energy consumption boundary constraints, the energy-consuming equipment type, operating period, and energy allocation ratio of each business type zone are encoded using chromosomes to generate an initial population; the chromosomes include a business type zone identifier segment, an equipment type encoding segment, an operating period encoding segment, an energy allocation ratio encoding segment, and a verification segment; The genetic module is used to perform genetic operations on the initial population to obtain the target population, and to take the chromosomes in the target population whose fitness values ​​are greater than a first fitness threshold as the target solution set. The optimization parameter module is used to construct an initial particle swarm based on the target solution set, and iteratively update the initial particle swarm until the iterative convergence condition is met. The particles in the constructed initial particle swarm correspond one-to-one with the chromosomes in the target solution set. The parameters included in each constructed particle are the equipment operating power of each business zone, the charging and discharging power of the energy storage equipment, the renewable energy access regulation power, and the peak and valley time energy consumption allocation coefficient. The energy management module is used to manage the energy consumption of the smart park based on the parameters of the target particle, with the particle having the highest fitness during the iterative update process as the target particle.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images