Urban regional integrated energy system hierarchical control method

Abstract

This invention discloses a hierarchical control method for an integrated energy system in urban areas, relating to the field of energy operation control technology. The method includes the following steps: S1, collecting energy information required by equipment; S2, collecting energy information required by urban residents; S3, real-time recording of energy prices; S4, energy allocation and use; and S5, limiting energy use. This hierarchical control method prioritizes supplying production equipment with energy sources that are predicted to have low future prices and are environmentally friendly, based on the energy types available to the equipment. This reduces production costs and avoids environmental pollution. For energy sources that generate waste and potentially impact the environment during operation, a real-time updated limit table is established based on the energy type used, limiting the amount of energy used by the equipment to prevent pollution from exceeding the rate of environmental remediation.

Description

Technical Field

[0001] This invention relates to the field of energy operation and control technology, specifically to a hierarchical control method for an integrated energy system in an urban area. Background Technology

[0002] An integrated energy system refers to a new type of integrated energy system that utilizes advanced physical information technology and innovative management models within a certain area to integrate various energy sources such as coal, oil, natural gas, electricity, and heat. This system achieves coordinated planning, optimal operation, collaborative management, interactive feedback, and mutual support among various heterogeneous energy subsystems. While meeting the diversified energy needs within the system, it also effectively improves energy utilization efficiency and promotes sustainable energy development.

[0003] Existing integrated energy systems in urban areas have relatively weak planning for environmental pollution when purchasing, storing, distributing, and using energy, and their accuracy in predicting future energy price changes is not high, which can easily affect energy purchase costs.

[0004] Therefore, in view of this, we study and improve the existing structure and its shortcomings, and propose a hierarchical control method for urban regional integrated energy systems. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a hierarchical control method for integrated energy systems in urban areas, solving the problems mentioned in the background section.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a hierarchical control method for an integrated urban energy system, wherein the energy information acquisition system of the hierarchical control method includes an upper-level energy collection system and a lower-level energy collection system, and the hierarchical control method for the integrated urban energy system includes the following operational steps:

[0007] S1. Collection of energy requirements for the equipment:

[0008] The upper-level energy system collects the types of energy used by each production equipment in each industrial park within the city area and determines whether each production equipment has alternative energy sources. It also associates and records the energy carried by the shell with the corresponding production equipment. The upper-level energy system also calculates the daily energy consumption of each production equipment.

[0009] The types of energy used in industrial parks include gas, heat, water, and electricity.

[0010] S2. Collection of energy needs information for urban residents:

[0011] The lower-level energy system collects the types of energy used in residential areas within the city, then calculates and records the average daily consumption of each energy source in the residential areas. The lower-level energy system also records the peak energy consumption periods of the residential areas each day.

[0012] The types of energy used in residential areas include electricity, water, and gas.

[0013] S3, Real-time Energy Price Recording:

[0014] The lower-level energy system collects and records price changes of various energy sources in real time, and also collects and records relevant information of various energy suppliers in real time. It predicts the price change trends of various energy sources in the future, purchases and stores energy based on the prediction results, and also records the storage amount of each energy source.

[0015] The relevant information about the energy supplier includes the rise and fall of its brand reputation, the quality of its credibility, and technological updates. The forecast will also take into account future environmental and policy factors.

[0016] S4. Energy Allocation and Usage:

[0017] The upper-level energy system allocates energy based on the storage capacity of each energy source, the average daily consumption of each energy source in the residential area, the daily energy consumption of each production device, and the predicted price of each energy source in the future. The upper-level energy system provides the required energy to the residential area according to the average daily consumption of each energy source in the residential area, and the remaining energy is then supplied to the industrial park.

[0018] The energy required by the residential area is essential and should be allocated with priority.

[0019] S5, Energy Usage Limitations:

[0020] A real-time updated limit table is established based on low-quality energy types, and the amount of low-quality energy used by the production equipment is limited according to the limit table and the maximum environmental carrying capacity, which is obtained from the industrial park database.

[0021] The production equipment generates environmentally polluting waste when using low-quality energy.

[0022] Furthermore, in step S1, if the energy used by the production equipment is of multiple types, then the energy used by the production equipment using multiple types of energy is associated based on the production equipment using multiple types of energy.

[0023] Furthermore, in step S4, when the remaining stored energy is supplied to the industrial park, based on the type and price of energy, energy with low future predicted price and environmental friendliness is selected to supply the production equipment, and the selected energy is the energy that the production equipment can use.

[0024] Furthermore, the hierarchical control method for the urban area integrated energy system adjusts the production equipment based on information on alternative energy sources. The determination of whether the production equipment has alternative energy sources is based on a subjective and objective evaluation method. This subjective and objective evaluation method utilizes information collected by the upper-level energy system and information collected by the lower-level energy system to construct a subjective and objective evaluation matrix Y. η =[y αβ ] i×j ,in:

[0025]

[0026] In the formula, α represents the number of production equipment, β represents the number of alternative energy evaluation indicators, and y αβ Let represent the score of the βth alternative energy evaluation in the αth production equipment, where i represents the total number of production equipment, j represents the total number of alternative energy evaluation indicators, and α = 1, ..., i, β = 1, ..., j;

[0027] Using the subjective and objective evaluation matrix Y η Construct the constraint boundary matrix Z η =[z αβ ] i×j ,in:

[0028]

[0029] In the formula, z αβ This represents the score value for the alternative energy assessment of the β-th constraint boundary in the α-th production equipment;

[0030] For the constraint boundary matrix Z η After standardization, the normalized matrix T = [t] is obtained. αβ ] i×j The standardization process involves: processing the constraint boundary matrix Z... η Each element in the data is normalized, including:

[0031]

[0032]

[0033] In the formula, C ε D represents a positive indicator. ε Represents a negative indicator, t αβThe score z represents the alternative energy assessment score for the β-th constraint boundary in the α-th production facility. αβ The normalized value of z αβ To constrain the boundary matrix Z η The element, max(z) αβ ) represents z αβ The maximum value of the corresponding alternative energy evaluation index;

[0034] The normalized matrix T is subjected to a subjective and objective weighting process to obtain the weighted matrix. w αβ The calculation formula is:

[0035] w αβ =t αβ ×r β0 ;

[0036] Where, r β0 w represents the overall weight. αβ The weighted value represents the score of the alternative energy assessment for the β-th normalized constraint boundary in the α-th production equipment.

[0037] Using weighted matrices To calculate the effective index for each of the production equipment, first calculate the bias F of each of the production equipment. α Then, its effective index is calculated based on the bias, and the bias L is the bias L. α The calculation method is as follows:

[0038]

[0039]

[0040] In the formula, Sum e Represents the weighted matrix The sum of the elements in Sum eeα (α = 1, 2, ..., i) represents the weighting matrix The sum of the lower limits of the alternative energy evaluation indicators for each element, Sum eα (α = 1, 2, ..., i) represents the weighting matrix The sum of the upper limits of the alternative energy assessment indicators corresponding to each element, This indicates the degree of bias corresponding to the lower limit of the alternative energy evaluation index. This represents the bias corresponding to the upper limit of the evaluation index for alternative energy, and e represents the first e weighted matrices. The elements in the array are e = 1, 2, ..., i;

[0041] After the bias is calculated, the trade-off between the ideal and anti-ideal production equipment is calculated using the bias function;

[0042]

[0043]

[0044] In the formula, This represents the bias function associated with the anti-ideal solution, while The bias function is used to represent the relationship with the ideal solution; then, a compromise function is used to calculate the final effective index Rst of the number of production equipment. α The specific expression is as follows:

[0045]

[0046] The production equipment is based on the effective index Rst α The production equipment with the highest index is selected as the production equipment for alternative energy sources.

[0047] Furthermore, the use of the subjective and objective evaluation matrix Y η Construct the constraint boundary matrix Z η The specific steps include:

[0048] Step 1: Based on the alternative energy evaluation index data recorded in the existing database of alternative energy types for production equipment, where the number of alternative energy evaluation index data is no less than 100, sort the values ​​of each alternative energy evaluation index from smallest to largest. The average of the top 10% of alternative energy evaluation index values ​​is taken as the minimum boundary value min(y) of the alternative energy evaluation index. β The average value of the subsequent 10% of the alternative energy evaluation index is the maximum value of the alternative energy evaluation index boundary, max(y). β );

[0049] Step 2: Analyze the subjective and objective evaluation matrix Y η For each element, a maximum and minimum boundary value is set based on its corresponding alternative energy evaluation index value. If the alternative energy evaluation index value is greater than the corresponding maximum boundary value, then the corresponding maximum boundary value is used as the alternative energy evaluation index value; if the alternative energy evaluation index value is less than the corresponding minimum boundary value, then the corresponding minimum boundary value is used as the alternative energy evaluation index value.

[0050] Step 3: Replace the subjective and objective evaluation matrix Y with the elements after boundary constraints. η The corresponding elements are used to obtain the constraint boundary matrix Z. η .

[0051] Furthermore, the specific steps for performing subjective and objective weighted processing on the normalized matrix T include:

[0052] The weight of each alternative energy evaluation index is determined using the entropy weight method;

[0053] The weight of each alternative energy evaluation indicator is determined by using a graphical model index weighting method;

[0054] Calculate the overall weight of each alternative energy assessment indicator;

[0055] The normalized matrix T is weighted using a comprehensive weighting process to obtain the weighted matrix W = [w αβ ] i×j .

[0056] Furthermore, the specific steps for determining the weight of each replaceable energy evaluation index using the entropy weight method include:

[0057] Step 1: Normalize the alternative energy evaluation indicators for the production equipment, wherein the positive indicators are processed as follows:

[0058]

[0059] The handling method for negative indicators is as follows:

[0060]

[0061] In the formula, y αβ Represents matrix Y η The score value of the β-th alternative energy source in the α-th production equipment, where α = 1, ..., i, β = 1, ..., j, y′ αβ This represents the evaluation index after normalization, min(y) β ) represents the minimum boundary value of the alternative energy evaluation index, max(y) β () indicates the highest boundary value of the alternative energy evaluation index;

[0062] Step 2: Standardize the evaluation indicators after normalization:

[0063]

[0064] In the formula, I αβ Standardized indicator data;

[0065] Step 3: Calculate the information entropy of each alternative energy assessment indicator:

[0066]

[0067] Step 4: Calculate the weight of each alternative energy assessment indicator:

[0068]

[0069] Furthermore, the specific steps for determining the weight of each alternative energy evaluation index using the graphical model index weighting method include:

[0070] Step 1: Calculate the vector reflecting the alternative energy ratings of individual experts for production equipment. Where, when the i-th expert (i≤I) does not evaluate the k-th alternative energy indicator, When the i-th expert scores h for the k-th (k≤J) alternative energy evaluation index, the vector... The elements in the middle are:

[0071]

[0072] In the formula, For vectors The m-th element; n represents the scoring system; h represents the expert's score for the k-th indicator;

[0073] Step 2: Calculate a matrix containing individual expert ratings of alternative energy sources for production equipment:

[0074]

[0075] In the formula, This is a matrix of information on the ratings of the i-th expert regarding the alternative energy sources for production equipment. Let be the score information vector of the i-th expert;

[0076] Step 3: Calculate the scoring information matrix containing all alternative energy evaluation indicators to obtain a matrix containing overall scoring information:

[0077]

[0078] In the formula, A nJ×nJ This is a matrix summing up the scoring information for I alternative energy sources;

[0079] Step 4: Reduce the dimensionality of the matrix containing overall scoring information to obtain the evaluation scores reflecting the importance of each indicator, where A nJ×nJ The dimension reduction representation is as follows:

[0080]

[0081] In the formula, F is a one-dimensional vector projected from matrix A; f α Let α be the α-th element of vector F. Using the above formula, we can calculate the evaluation scores q1, q2, ..., q that reflect the importance of each indicator. n ;

[0082] Step 5: Determine the weight of each alternative energy evaluation index for the production equipment, as follows:

[0083]

[0084] In the formula, r k is the weight of the kth replaceable energy evaluation index of the production equipment; k takes values ​​of 1, 2, 3, ..., J.

[0085] Furthermore, the specific adjustment method for the production equipment based on the information on alternative energy sources in the hierarchical control method for the urban area integrated energy system is as follows:

[0086] Based on the neural network algorithm, a model considering the alternative energy sources of the production equipment is established.

[0087] Establish and train a training dataset. The training dataset consists of data from a large number of experts on alternative energy adjustment schemes based on different production equipment. The input to the training dataset consists of alternative energy adjustment schemes for multiple production equipment, and the output to the training dataset consists of alternative energy adjustment schemes for production equipment.

[0088] Using the trained alternative energy adjustment model for production equipment, an alternative energy adjustment scheme for production equipment in the industrial park is calculated based on the production equipment.

[0089] Based on neural network algorithms, a component adjustment model is established that considers the environmental impact, restriction level, and restriction factors of alternative energy sources for production equipment in industrial parks. The trained component adjustment model is then used to further adjust the components of alternative energy sources after the addition or subtraction of energy sources.

[0090] Furthermore, the specific steps for establishing a component adjustment model based on a neural network algorithm, considering the environmental impact, restriction level, and restriction factors of alternative energy sources for production equipment in industrial parks, and then using the trained component adjustment model to further adjust the added or subtracted alternative energy components are as follows:

[0091] Step 1: Construct training samples. Specifically, this involves collecting a large number of expert records on the environmental impact of alternative energy sources on production equipment in industrial parks and the increase or decrease of alternative energy components. The restriction level and restriction factor of alternative energy sources are used as training inputs, and the increase or decrease of alternative energy components are used as outputs to construct a training sample dataset.

[0092] The second step is to design and initialize the network architecture, specifically by building a convolutional neural network, which includes one input layer, three convolutional layers, three ReLU non-linear activation layers, three pooling layers, one fully connected layer, and one output layer.

[0093] Step 3: Train a component adjustment model using a convolutional neural network to further adjust the replaceable energy components.

[0094] This invention provides a hierarchical control method for an integrated energy system in an urban area, which has the following beneficial effects:

[0095] This hierarchical control method for the urban integrated energy system collects real-time price changes of various energy sources and relevant information from energy suppliers. It also predicts future price trends of various energy sources by considering future environmental and policy factors. Based on these predictions, it purchases and stores relatively affordable energy, thereby reducing energy purchase costs. Furthermore, when supplying energy, it prioritizes supplying production equipment with predicted low prices and environmentally friendly energy sources, based on the equipment's capacity. This reduces production costs and avoids environmental pollution. For energy sources that generate waste and are environmentally impactful, a real-time updated limit table is established based on the energy type used, restricting the amount of energy used by production equipment. The specific limits are set according to the environment's maximum carrying capacity to prevent pollution from exceeding the rate of environmental remediation. Attached Figure Description

[0096] Figure 1 This is a schematic diagram of the overall operation process of a hierarchical control method for an integrated energy system in an urban area according to the present invention;

[0097] Figure 2 This is a schematic diagram illustrating the process of predicting future energy prices using a hierarchical control method for an integrated urban energy system according to the present invention.

[0098] Figure 3 This is a schematic diagram of the energy allocation and usage process of a hierarchical control method for an integrated urban energy system according to the present invention. Detailed Implementation

[0099] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and should not be construed as limiting the scope of the invention.

[0100] like Figure 1 The diagram shown is a schematic representation of the overall operation flow of a hierarchical control method for an integrated urban energy system provided by the present invention. The hierarchical control method for an integrated urban energy system includes the following operational steps:

[0101] S1. Collection of energy requirements for the equipment

[0102] The goal of this step is to collect information on the energy requirements of production equipment in various industrial parks within the city.

[0103] The specific implementation is as follows:

[0104] (1) Establish a database of information on industrial parks and equipment in the region.

[0105] Detailed on-site surveys were conducted for each industrial park within the region to collect basic information on all production equipment within the industrial parks, including: equipment number n′, equipment name, equipment model, equipment category, equipment energy efficiency rating, and average daily output Q. n′ This includes information such as equipment status. All information is integrated into a database to establish an industrial park production equipment information management system. The database needs to be updated in real time to promptly reflect changes in equipment.

[0106] (2) Determine the energy type of the equipment

[0107] For each piece of equipment, based on its working principle and user manual, determine the type of energy it needs to consume and the corresponding parameters, including: Gas: Consumption parameter G n′ Electricity: Consumption parameter E n′ Heat: Consumption parameter H n′ If the equipment can use multiple energy sources, then the consumption parameters of each type of energy source need to be determined.

[0108] (3) Assess the alternative energy sources available for the equipment

[0109] For each device, assess its suitability for alternative energy sources. The assessment methodology can employ both subjective and objective evaluation methods, including expert scoring.

[0110] Industry experts were invited to score the replacement potential of each alternative energy source based on factors such as equipment type and working principle: Score a Score a The score ranges from 0 to 10, with 10 indicating that the item can be completely replaced.

[0111] If Score a If the value is greater than 6, then it is confirmed that device n′ can use the i-th type of alternative energy.

[0112] (4) Determine the daily energy consumption of the equipment

[0113] Based on the equipment output parameter Q n′ And equipment consumption parameter G n′ E n′ H n′ The daily energy consumption of the equipment can be determined: Gas consumption: G′ n′ =G n′ ×Q n′ Electricity consumption: E′ n′ =E n′ ×Q n′ Heat consumption: H′n′ =H n′ ×Q n′ .

[0114] (5) Construct an energy consumption database

[0115] Based on the equipment information database, an energy consumption database for industrial parks will be further constructed. The database mainly includes the following information: basic equipment information, equipment energy type and consumption parameters, average daily output of equipment, daily energy consumption of equipment, and assessment of alternative energy sources for equipment.

[0116] The energy consumption database can provide basic data support for subsequent energy allocation and replacement decisions. The database needs to be updated and maintained regularly to ensure the timeliness and effectiveness of the data.

[0117] In summary, this step, through exhaustive surveys and theoretical calculations, constructed an energy consumption database for production equipment in industrial parks within the region, providing fundamental data support for subsequent energy supply, scheduling, and management decisions, and achieving effective collection of energy information required by the equipment.

[0118] S2, Collection of Energy Needs of Urban Residents

[0119] The goal of this step is to collect information on the energy needs of residents within the urban area. It mainly consists of the following sub-steps:

[0120] (1) Dividing urban residential areas

[0121] Based on factors such as urban planning zoning and population distribution, the urban area is divided into I... γ A residential area, marked as

[0122] (2) Conduct a sample household survey

[0123] In each residential area Inside, randomly select J γ A questionnaire survey on energy usage was conducted among sample households. The questionnaire included information such as the number of household members. Number of home appliances (air conditioners, refrigerators, etc.), monthly power consumption Monthly water consumption Monthly gas consumption

[0124] (3) Determine the population of the residential area

[0125] Based on the most recent census data, each residential area was identified. Total population

[0126] (4) Calculate the energy consumption of residential areas

[0127] Based on the results of the sampling survey, the average energy consumption of each residential area can be estimated:

[0128] Average daily power consumption:

[0129] Average daily water consumption:

[0130] Average daily gas consumption:

[0131] (5) Determine the peak energy consumption period in residential areas

[0132] By analyzing historical statistical data on regional electricity load curves, the peak periods for residential electricity consumption were determined.

[0133] (6) Establish a residential area energy database

[0134] A database of energy consumption and peak-hour data from all residential areas will be compiled to provide data support for the supply and management of energy for residential use. The database needs to be updated regularly.

[0135] In summary, this step estimated the energy consumption of urban residential areas through sampling surveys and theoretical calculations, and constructed a database, thus effectively collecting information on residents' energy needs and providing a basis for subsequent energy supply and management decisions.

[0136] S3, Real-time Energy Price Recording

[0137] The goal of this step is to collect and predict the prices of various energy sources in real time, providing a basis for subsequent energy procurement. It mainly consists of the following sub-steps:

[0138] (1) Establish an energy price monitoring system

[0139] Using web crawling technology, we collect real-time energy price trends from multiple authoritative data platforms, including various energy types such as electricity, natural gas, and oil. The collection cycle is no more than one hour, and historical price data is saved.

[0140] (2) Establish an energy price forecasting model

[0141] An energy price prediction model is trained using deep learning models such as LSTM (Long Short-Term Memory) and historical price data. Factors that can be considered in the model input features include: past j... γ Price data within the day, future i γ Weather forecast data, holiday information, macroeconomic and policy factors.

[0142] Once trained, the model can be used to predict energy price trends over the next week.

[0143] In summary, this step establishes an energy price monitoring and forecasting system, enabling real-time tracking of energy price information and providing support for energy procurement management within the region.

[0144] S4, Energy Allocation and Use

[0145] The goal of this step is to optimize the distribution and use of energy within the region. The specific implementation process is as follows:

[0146] (1) Determine the energy supply

[0147] Based on the energy storage data collected in the previous steps, determine the current available supply of various energy sources: electricity: P, coal: C′, oil: O, natural gas: G.

[0148] (2) Establish an energy demand model

[0149] By combining the industrial and residential energy demand data collected in steps S1 and S2, an energy demand forecasting model is established.

[0150] The GM(1,1) grey prediction model can be used. Prediction models for industrial electricity and residential electricity consumption can be established separately.

[0151] For example, industrial electricity demand forecasting models:

[0152] Let the historical demand data sequence be: X γ = (x1, x2, ..., x n ),

[0153] Generate an accumulation sequence: Y γ = (y1, y2, ..., y n ),

[0154] in,

[0155] Establish the GM(1,1) model:

[0156] The predicted electricity demand is as follows:

[0157] Similarly, demand forecasting models for various types of energy can be established.

[0158] (3) Optimize energy allocation

[0159] Objective function: Minimize total energy cost

[0160] The constraints include: restrictions on the supply of various types of energy, restrictions on the demand of various types of energy, and priority for meeting the needs of residential areas.

[0161] Solve using methods such as linear programming to calculate the optimal energy allocation scheme that satisfies the constraints.

[0162] In summary, this step, through predictive models and optimization algorithms, provides a scientifically sound energy allocation scheme to meet the energy needs of industry and residents within the region.

[0163] S5, Energy Usage Limitations

[0164] The goal of this step is to restrict the use of certain energy sources that cause environmental pollution. The specific implementation process is as follows:

[0165] (1) Assess the energy and environmental impact

[0166] Experts were invited to conduct environmental impact assessments on the use of various energy sources, with scoring indicators including: dust pollution. Noise pollution exhaust gas pollution Wastewater pollution

[0167] Determining weights using the AHP method Calculate the overall score for energy and environmental impact:

[0168]

[0169] in, The overall score is for energy and environmental impact.

[0170] (2) Determine the restriction level

[0171] Based on the scoring results, the energy restriction level is determined: if Then its use is not strictly restricted, if This constitutes a moderate restriction on use. Then there are no restrictions.

[0172] (3) Establish a limiting factor model

[0173] For energy sources that require restriction, the main environmental impact factors are identified as limiting factors, along with the maximum permissible concentrations of each factor.

[0174] For example, the following limiting factors can be set for coal combustion: particulate matter concentration C1 and greenhouse gas concentration C2.

[0175] (4) Determine the unit energy environmental impact

[0176] By reviewing literature and conducting enterprise tests, the environmental impact per unit of energy was determined, such as the amount of soot (D1) and CO2 (D2) produced by burning 1 ton of standard coal.

[0177] (5) Calculate the upper limit of energy use

[0178] Calculate the upper limit of energy utilization based on the concentration of limiting factors and the environmental impact parameters per unit of energy:

[0179] Permissible coal consumption limit:

[0180] Permissible upper limit for coal consumption:

[0181] Where Q1 is the upper limit of allowed coal consumption, Q2 is the upper limit of allowed coal consumption, and the final upper limit of coal consumption is the minimum value of Q1 and Q2.

[0182] (6) Dynamically adjust the limiting factor

[0183] Monitor regional environmental quality, dynamically adjust the values ​​of limiting factors, and achieve closed-loop feedback control.

[0184] In summary, this step, based on the results of the energy and environmental impact assessment, reasonably limited the utilization of high-polluting energy sources, thus achieving the goals of energy conservation and emission reduction.

[0185] The hierarchical control method for the integrated energy system in this urban area first involves the upper-level energy system collecting the types of energy used by each production equipment in each industrial park within the urban area, and determining whether each piece of equipment has alternative energy sources. After determination, the energy information is associated with and recorded with the corresponding production equipment. If the production equipment uses multiple types of energy, then the energy sources that the production equipment can use are associated with it, meaning that the production equipment can use multiple types of energy simultaneously. The types of energy used in industrial parks include gas energy, heat energy, water energy, and electricity. The upper-level energy system also calculates the daily energy consumption of each production piece of equipment. The lower-level energy system collects the types of energy used in residential areas within the urban area, and then calculates and records the average daily consumption of each type of energy in residential areas. The types of energy used in residential areas include electricity, water energy, and gas energy. The lower-level energy system also records the daily peak energy consumption periods in residential areas.

[0186] Specifically, the hierarchical control method for the urban area integrated energy system adjusts the production equipment based on information on alternative energy sources. The determination of whether the production equipment has alternative energy sources is based on a subjective and objective evaluation method. This subjective and objective evaluation method utilizes information collected by the upper-level energy system and information collected by the lower-level energy system to construct a subjective and objective evaluation matrix Y. η =[y αβ ] i×j ,in:

[0187]

[0188] In the formula, α represents the number of production equipment, β represents the number of alternative energy evaluation indicators, and y αβ Let represent the score of the βth alternative energy evaluation in the αth production equipment, where i represents the total number of production equipment, j represents the total number of alternative energy evaluation indicators, and α = 1, ..., i, β = 1, ..., j;

[0189] Using the subjective and objective evaluation matrix Y η Construct the constraint boundary matrix Z η =[z αβ ] i×j ,in:

[0190]

[0191] In the formula, z αβ This represents the score value for the alternative energy assessment of the β-th constraint boundary in the α-th production equipment;

[0192] For the constraint boundary matrix Z η After standardization, the normalized matrix T = [t] is obtained. αβ ] i×j The standardization process involves: processing the constraint boundary matrix Z... η Each element in the data is normalized, including:

[0193]

[0194]

[0195] In the formula, C ε D represents a positive indicator. ε Represents a negative indicator, t αβ The score z represents the alternative energy assessment score for the β-th constraint boundary in the α-th production facility. αβ The normalized value of z αβ To constrain the boundary matrix Z η The element, max(z) αβ ) represents z αβ The maximum value of the corresponding alternative energy evaluation index;

[0196] The normalized matrix T is subjected to a subjective and objective weighting process to obtain the weighted matrix. w αβ The calculation formula is:

[0197] w αβ =t αβ ×r β0 ;

[0198] Where, r β0 w represents the overall weight.αβ This represents the weighted value of the score for the alternative energy assessment of the β-th normalized constraint boundary in the α-th production facility;

[0199] Using weighted matrices To calculate the effective index for each of the production equipment, first calculate the bias F of each of the production equipment. α Then, its effective index is calculated based on the bias, and the bias L is the bias L. α The calculation method is as follows:

[0200]

[0201]

[0202] In the formula, Sum e Represents the weighted matrix The sum of the elements in Sum eeα (α = 1, 2, ..., i) represents the weighting matrix The sum of the lower limits of the alternative energy evaluation indicators for each element, Sum eα (α = 1, 2, ..., i) represents the weighting matrix The sum of the upper limits of the alternative energy assessment indicators corresponding to each element, This indicates the degree of bias corresponding to the lower limit of the alternative energy evaluation index. This represents the bias corresponding to the upper limit of the evaluation index for alternative energy, and e represents the first e weighted matrices. The elements in the array are e = 1, 2, ..., i;

[0203] After the bias is calculated, the trade-off between the ideal and anti-ideal production equipment is calculated using the bias function;

[0204]

[0205]

[0206] In the formula, This represents the bias function associated with the anti-ideal solution, while The bias function is used to represent the relationship with the ideal solution; then, a compromise function is used to calculate the final effective index Rst of the number of production equipment. α The specific expression is as follows:

[0207]

[0208] The production equipment is based on the effective index Rst α The production equipment with the highest index is selected as the production equipment for alternative energy sources.

[0209] Among them, the use of subjective and objective evaluation matrix Y η Construct the constraint boundary matrix Z η The specific steps include:

[0210] Step 1: Based on the alternative energy evaluation index data recorded in the existing database of alternative energy types for production equipment, wherein the number of alternative energy evaluation index data is no less than 100, sort the values ​​of each alternative energy evaluation index from smallest to largest, and take the average of the first 10% of alternative energy evaluation index values ​​as the minimum boundary value min(y) of the alternative energy evaluation index. β The average value of the subsequent 10% of the alternative energy evaluation index is the maximum value of the alternative energy evaluation index boundary, max(y). β );

[0211] Step 2: Analyze the subjective and objective evaluation matrix Y η For each element, a maximum and minimum boundary value is set based on its corresponding alternative energy evaluation index value. If the alternative energy evaluation index value is greater than the corresponding maximum boundary value, then the corresponding maximum boundary value is used as the alternative energy evaluation index value; if the alternative energy evaluation index value is less than the corresponding minimum boundary value, then the corresponding minimum boundary value is used as the alternative energy evaluation index value.

[0212] Step 3: Replace the subjective and objective evaluation matrix Y with the elements after boundary constraints. η The corresponding elements are used to obtain the constraint boundary matrix Z. η .

[0213] The specific steps for performing subjective and objective weighted processing on the normalized matrix T include:

[0214] The weight of each alternative energy evaluation index is determined using the entropy weight method;

[0215] The weight of each alternative energy evaluation indicator is determined by using a graphical model index weighting method;

[0216] Calculate the overall weight of each alternative energy assessment indicator, where the overall weight is calculated using the following function:

[0217]

[0218] In the formula, r β1 For the weights obtained by the entropy weighting method, r β2 The weights, r, are obtained through a graph model-based index weighting method. β0 Assign weights to the combinations of indicators; solve the above equation to obtain r. β0 As a comprehensive weight;

[0219] The normalized matrix T is weighted using a comprehensive weighting process, as follows:

[0220] w αβ =t αβ ×r β0 ;

[0221] The weighted matrix W = [w αβ ] i×j .

[0222] The specific steps for determining the weight of each replaceable energy evaluation index using the entropy weight method include:

[0223] Step 1: Normalize the alternative energy evaluation indicators for the production equipment, wherein the positive indicators are processed as follows:

[0224]

[0225] The handling method for negative indicators is as follows:

[0226]

[0227] In the formula, y αβ Represents matrix Y η The score value of the β-th alternative energy source in the α-th production equipment, where α = 1, ..., i, β = 1, ..., j, y′ αβ This represents the evaluation index after normalization, min(y) β ) represents the minimum boundary value of the alternative energy evaluation index, max(y) β () indicates the highest boundary value of the alternative energy evaluation index;

[0228] Step 2: Standardize the evaluation indicators after normalization:

[0229]

[0230] In the formula, I αβ Standardized indicator data;

[0231] Step 3: Calculate the information entropy of each alternative energy assessment indicator:

[0232]

[0233] In the formula, E β Information entropy representing replaceable energy evaluation indicators;

[0234] Step 4: Calculate the weight of each alternative energy assessment indicator:

[0235]

[0236] The specific steps for determining the weight of each alternative energy evaluation index using the graph model index weighting method include:

[0237] Step 1: Calculate the vector reflecting the alternative energy ratings of individual experts for production equipment. Where, when the i-th expert (i≤I) does not evaluate the k-th alternative energy indicator, When the i-th expert scores h for the k-th (k≤J) alternative energy evaluation index, the vector... The elements in the middle are:

[0238]

[0239] In the formula, For vectors The m-th element; n represents the scoring system; h represents the expert's score for the k-th indicator;

[0240] Step 2: Calculate a matrix containing individual expert ratings of alternative energy sources for production equipment:

[0241]

[0242] In the formula, This is a matrix of information on the ratings of the i-th expert regarding the alternative energy sources for production equipment. Let be the score information vector of the i-th expert;

[0243] Step 3: Calculate the scoring information matrix containing all alternative energy evaluation indicators to obtain a matrix containing overall scoring information:

[0244]

[0245] In the formula, A nJ×nJ This is a matrix summing up the scoring information for I alternative energy sources;

[0246] Step 4: Reduce the dimensionality of the matrix containing overall scoring information to obtain the evaluation scores reflecting the importance of each indicator, where A nJ×nJ The dimension reduction representation is as follows:

[0247]

[0248] In the formula, F is a one-dimensional vector projected from matrix A; f α Let α be the α-th element of vector F. Using the above formula, we can calculate the evaluation scores q1, q2, ..., q that reflect the importance of each indicator. n ;

[0249] Step 5: Determine the weight of each alternative energy evaluation index for the production equipment, as follows:

[0250]

[0251] In the formula, r k is the weight of the kth replaceable energy evaluation index of the production equipment; k takes values ​​of 1, 2, 3, ..., J.

[0252] The specific adjustment method for the hierarchical control of the urban area integrated energy system based on information on alternative energy sources for adjusting the production equipment is as follows:

[0253] Based on the neural network algorithm, a model considering the alternative energy sources of the production equipment is established.

[0254] Establish and train a training dataset. The training dataset consists of data from a large number of experts on alternative energy adjustment schemes based on different production equipment. The input to the training dataset consists of alternative energy adjustment schemes for multiple production equipment, and the output to the training dataset consists of alternative energy adjustment schemes for production equipment.

[0255] Using the trained alternative energy adjustment model for production equipment, an alternative energy adjustment scheme for production equipment in the industrial park is calculated based on the production equipment.

[0256] Based on neural network algorithms, a component adjustment model is established that considers the environmental impact, restriction level, and restriction factors of alternative energy sources for production equipment in industrial parks. The trained component adjustment model is then used to further adjust the components of alternative energy sources after the addition or subtraction of energy sources.

[0257] The specific steps for establishing a component adjustment model based on a neural network algorithm, considering the environmental impact, restriction level, and restriction factors of alternative energy sources for production equipment in industrial parks, and further adjusting the adjusted alternative energy components using the trained component adjustment model are as follows:

[0258] Step 1: Construct training samples. Specifically, this involves collecting a large number of expert records on the environmental impact of alternative energy sources on production equipment in industrial parks and the increase or decrease of alternative energy components. The restriction level and restriction factor of alternative energy sources are used as training inputs, and the increase or decrease of alternative energy components are used as outputs to construct a training sample dataset.

[0259] The second step is to design and initialize the network architecture, specifically by building a convolutional neural network, which includes one input layer, three convolutional layers, three ReLU non-linear activation layers, three pooling layers, one fully connected layer, and one output layer.

[0260] Step 3: Train a component adjustment model using a convolutional neural network to further adjust the replaceable energy components.

[0261] like Figure 2 The diagram illustrates the process of predicting future energy prices using a hierarchical control method for an integrated urban energy system according to the present invention. The lower-level energy system collects real-time data on price changes for each energy source and also gathers relevant information from each energy supplier. It then combines this data with future environmental and policy factors to predict future price trends for each energy source. Based on the prediction results, it purchases and stores energy sources that are relatively affordable. Information about energy suppliers includes factors such as brand reputation, credibility, and technological updates. The lower-level energy system also records the storage volume of each energy source.

[0262] like Figure 3 The diagram illustrates the energy allocation and usage process of a hierarchical control method for an integrated urban energy system according to the present invention. The upper-level energy system allocates energy based on the storage capacity of each energy source, the average daily consumption of each energy source in residential areas, the daily energy consumption of each production device, and the predicted future prices of each energy source. The energy required by specific residential areas is considered essential energy. The upper-level energy system prioritizes providing sufficient energy to residential areas based on their average daily consumption. The remaining stored energy is then supplied to industrial parks. When supplying the industrial parks with the remaining stored energy, priority is given to using energy sources with lower predicted future prices and that are environmentally friendly, based on energy type and price. Furthermore, the selected energy source is the energy that the production equipment can utilize.

[0263] For energy sources that generate waste and are likely to impact the environment when used by production equipment, a real-time updated limit table is established based on the type of energy used, so that the amount of energy used by production equipment is limited. The specific setting of the limit on energy use is based on the maximum carrying capacity of the environment.

[0264] The embodiments of the present invention are given for illustrative and descriptive purposes only, and are not intended to be exhaustive or to limit the invention to the forms disclosed. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of the invention, and to enable those skilled in the art to understand the invention and to design various embodiments with various modifications suitable for a particular purpose.

Claims

1. A hierarchical control method for an integrated energy system in an urban area, characterized in that: The energy information collection system of the urban area integrated energy system hierarchical control method includes an upper-level energy collection system and a lower-level energy collection system. The urban area integrated energy system hierarchical control method includes the following operation steps: S1. Collection of energy requirements for the equipment: The upper-level energy collection system collects the types of energy used by each production equipment in each industrial park within the urban area, determines whether each production equipment has alternative energy sources, associates and records the alternative energy sources with the corresponding production equipment, and the upper-level energy collection system also calculates the daily energy consumption of each production equipment. S2. Collection of energy needs information for urban residents: The lower-level energy collection system collects the types of energy used in residential areas within the urban area, and then counts and records the average daily consumption of each energy source in the residential areas. The lower-level energy collection system also records the peak energy consumption periods of the residential areas each day. S3, Real-time Energy Price Recording: The lower-level energy collection system collects and records price changes of each energy source in real time, and also collects and records relevant information of each energy supplier in real time. It predicts future price trends of each energy source, purchases and stores energy based on the prediction results, and records the storage amount of each energy source. S4. Energy Allocation and Usage: The upper-level energy collection system allocates energy based on the storage capacity of each energy source, the average daily consumption of each energy source in the residential area, the daily energy consumption of each production device, and the predicted price of each energy source in the future. The upper-level energy collection system provides the required energy to the residential area according to the average daily consumption of each energy source in the residential area, and the remaining energy is then supplied to the industrial park. S5, Energy Usage Limitations: A real-time updated limit table is established based on the type of low-quality energy, and the amount of low-quality energy used by the production equipment is limited according to the limit table and the maximum environmental carrying capacity, wherein the maximum environmental carrying capacity is obtained from the industrial park database. The hierarchical control method for the urban area integrated energy system adjusts the production equipment based on information on alternative energy sources. The determination of whether the production equipment has alternative energy sources is based on a subjective and objective evaluation method. This subjective and objective evaluation method utilizes information collected by the upper-level energy collection system and the lower-level energy collection system to construct a subjective and objective evaluation matrix. ,in: ； In the formula, Indicates the number of production equipment. This indicates the number of indicators for evaluating alternative energy sources. Indicates the first The first of the production equipment The score for alternative energy assessment is given by i, where i represents the number of production facilities and j represents the number of alternative energy assessment indicators. ; Using subjective and objective evaluation matrices Construct the constraint boundary matrix ,in: ； In the formula, Indicates the first The production equipment mentioned above, the first The score value for the evaluation of alternative energy sources with limiting boundaries; For the constraint boundary matrix After standardization, the normalized matrix T is obtained. The standardization process involves: processing the constraint boundary matrix... Each element in the data is normalized, including: ； ； In the formula, Represents a positive indicator. This represents a negative indicator. Indicates the first The production equipment mentioned above, the first The score of the alternative energy assessment at the constraint boundary. The normalized value, To constrain the boundary matrix elements, express The maximum value of the corresponding alternative energy evaluation index; The normalized matrix T is subjected to a subjective and objective weighting process to obtain the weighted matrix. , The calculation formula is: ； in, Indicates the overall weight. Indicates the first The first of the production equipment The weighted average of the scores for the evaluation of alternative energy sources with normalized constraint boundaries; Using weighted matrices To calculate the effective index for each of the production equipment, the bias of each production equipment is first calculated. Then, its effective index is calculated based on the bias, and the bias is... The calculation method is as follows: ； ； In the formula, Represents the weighted matrix The sum of the elements in Represents the weighted matrix The sum of the lower limits of the alternative energy assessment indicators for each element, Represents the weighted matrix The sum of the upper limits of the alternative energy assessment indicators corresponding to each element, This indicates the degree of bias corresponding to the lower limit of the alternative energy evaluation index. e represents the bias corresponding to the upper limit of the alternative energy evaluation index. ; After the bias is calculated, the trade-off between the ideal and anti-ideal production equipment is calculated using the bias function; In the formula, This represents the bias function associated with the antiideal solution, while The bias function associated with the ideal solution is then used; subsequently, a compromise function is employed to calculate the final effective index of the number of production equipment. The specific expression is as follows: According to the effective index, the production equipment The production equipment with the highest index is selected as the production equipment for alternative energy sources.

2. The hierarchical control method for an integrated urban energy system according to claim 1, characterized in that: In step S1, if the energy used by the production equipment is of multiple types, then the energy used by the production equipment using multiple types of energy is associated with each other.

3. The hierarchical control method for an integrated urban energy system according to claim 1, characterized in that: In step S4, when the remaining stored energy is supplied to the industrial park, based on the type and price of energy, energy with low predicted future prices and environmental friendliness is selected to supply the production equipment, and the selected energy is the energy that the production equipment can use.

4. The hierarchical control method for an integrated urban energy system according to claim 1, characterized in that: The use of subjective and objective evaluation matrices Construct the constraint boundary matrix The specific steps include: Step 1: Based on the alternative energy evaluation index data recorded in the existing database of alternative energy types for production equipment, where the number of alternative energy evaluation index data is no less than 100, sort the values ​​of each alternative energy evaluation index from smallest to largest, and take the average of the top 10% of alternative energy evaluation index values ​​as the minimum boundary value of the alternative energy evaluation index. The average value of the subsequent 10% of the alternative energy assessment index will be the highest boundary value of the alternative energy assessment index. ; Step 2: Analyze the subjective and objective evaluation matrix For each element, a maximum and minimum boundary value is set based on its corresponding alternative energy evaluation index value. If the alternative energy evaluation index value is greater than the corresponding maximum boundary value, then the corresponding maximum boundary value is used as the alternative energy evaluation index value; if the alternative energy evaluation index value is less than the corresponding minimum boundary value, then the corresponding minimum boundary value is used as the alternative energy evaluation index value. Step 3: Replace the subjective and objective evaluation matrix with elements after boundary constraints. The corresponding elements are used to obtain the constraint boundary matrix. .

5. The hierarchical control method for an integrated energy system in an urban area according to claim 1, characterized in that: The normalization matrix The specific steps for performing a combined subjective and objective weighted processing include: The weight of each alternative energy evaluation index is determined using the entropy weight method; The weight of each alternative energy evaluation indicator is determined by using a graphical model index weighting method; Calculate the overall weight of each alternative energy assessment indicator; Applying comprehensive weights to the normalized matrix After weighting, the weighted matrix W is obtained. .

6. The hierarchical control method for an integrated energy system in an urban area according to claim 5, characterized in that: The specific steps for determining the weight of each alternative energy evaluation index using the entropy weight method include: Step 1: Normalize the alternative energy evaluation indicators for the production equipment, wherein the positive indicators are processed as follows: ； The handling method for negative indicators is as follows: ； In the formula, Representation matrix The Middle The production equipment mentioned above, the first The score values ​​for evaluating alternative energy sources, among which, This represents the evaluation index after normalization. This represents the minimum boundary value of the alternative energy assessment index. This indicates the highest boundary value of the alternative energy evaluation index; Step 2: Standardize the evaluation indicators after normalization: ； In the formula, Standardized indicator data; Step 3: Calculate the information entropy of each alternative energy assessment indicator: ； In the formula, Information entropy representing replaceable energy evaluation indicators; Step 4: Calculate the weight of each alternative energy assessment indicator: 。 7. The hierarchical control method for an integrated energy system in an urban area according to claim 6, characterized in that: The specific steps for determining the weight of each alternative energy evaluation indicator using the graphical model index weighting method include: Step 1: Calculate the vector reflecting the alternative energy ratings of individual experts for production equipment. , where, when the i-th ( No expert commented on the first one. When considering alternative energy indicators, When the first Experts on the first ( ) A number of alternative energy assessment indicators When scoring, vector The elements in the middle are: In the formula, For vectors No. One element; It uses a scoring system; For experts to review the first Scoring of each indicator; Step 2: Calculate a matrix containing individual expert ratings of alternative energy sources for production equipment: ； In the formula, This is a matrix of information on the ratings of the i-th expert regarding the alternative energy sources for production equipment. For the first A vector of scoring information from renowned experts; Step 3: Calculate the scoring information matrix containing all alternative energy evaluation indicators to obtain a matrix containing overall scoring information: ； In the formula, for A matrix summing up the score information of various alternative energy sources; Step 4: Reduce the dimensionality of the matrix containing overall scoring information to obtain evaluation scores reflecting the importance of each indicator. The dimension reduction representation is as follows: In the formula, For matrix The one-dimensional vector after projection; For vectors The The above formula calculates the evaluation score reflecting the importance of each indicator by considering each element. ; Step 5: Determine the weight of each alternative energy evaluation index for the production equipment, as follows: In the formula, For the first production equipment The weights of the alternative energy evaluation indicators; k takes values ​​of 1, 2, 3, ..., J.

8. The hierarchical control method for an integrated urban energy system according to claim 1, characterized in that: The specific adjustment method for the hierarchical control of the urban area integrated energy system based on information on alternative energy sources for adjusting the production equipment is as follows: Based on the neural network algorithm, a model considering the alternative energy sources of the production equipment is established. Establish and train a training dataset. The training dataset consists of data from a large number of experts on alternative energy adjustment schemes based on different production equipment. The input to the training dataset consists of alternative energy adjustment schemes for multiple production equipment, and the output to the training dataset consists of alternative energy adjustment schemes for production equipment. Using the trained production equipment alternative energy adjustment model, the production equipment alternative energy adjustment scheme of the industrial park is calculated based on the production equipment. Based on neural network algorithms, a component adjustment model is established that considers the environmental impact, restriction level, and restriction factors of alternative energy sources for production equipment in industrial parks. The trained component adjustment model is then used to further adjust the components of alternative energy sources after the addition or subtraction of energy sources.

9. A hierarchical control method for an integrated urban energy system according to claim 8, characterized in that: The specific steps for establishing a component adjustment model based on a neural network algorithm, considering the environmental impact, restriction level, and restriction factors of alternative energy sources for production equipment in industrial parks, and further adjusting the adjusted alternative energy components using the trained component adjustment model are as follows: Step 1: Construct training samples. Specifically, this involves collecting a large number of expert records on the environmental impact of alternative energy sources on production equipment in industrial parks and the increase or decrease of alternative energy components. The restriction level and restriction factor of alternative energy sources are used as training inputs, and the increase or decrease of alternative energy components are used as outputs to construct a training sample dataset. The second step is to design and initialize the network architecture, specifically by building a convolutional neural network, which includes one input layer, three convolutional layers, three ReLU non-linear activation layers, three pooling layers, one fully connected layer, and one output layer. Step 3: Train a component adjustment model using a convolutional neural network to further adjust the replaceable energy components.

Images