Park energy collaborative energy-saving optimization model construction method and device
By collecting full data, setting dual objectives, and optimizing the NSGA-II algorithm, the problems of insufficient data and reliance on experience in park energy management have been solved, achieving efficient energy optimization and scientific decision-making, reducing costs and energy consumption, and improving the accuracy and adaptability of decision-making.
Patent Information
- Application Number
- CN202511010459.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-22
- Publication Date
- 2025-11-25
AI Technical Summary
The current energy management system in industrial parks suffers from insufficient data collection and analysis, lacks consideration of dynamic characteristics, lacks scientific optimization models, and relies on experience for decision-making, leading to energy waste and increased costs.
By collecting full data, setting dual objectives, constructing cost and energy consumption models, and using the NSGA-II algorithm for multi-objective optimization, an interactive decision support system is established to achieve accurate data, optimized cost and energy consumption, and scientific decision-making.
It achieves a data acquisition frequency increase to the minute level, reduces energy costs by 15%-25%, reduces energy consumption by 12%-20%, improves decision-making efficiency by 50%, and improves accuracy by 40%. The solution is highly adaptable and meets long-term effectiveness requirements.
Smart Images
Figure CN121010286A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of energy management, more particularly, it relates to a park energy collaborative energy-saving optimization model construction method and device. BACKGROUND
[0002] As a concentrated area of energy consumption and carbon emissions, the scientificity and efficiency of park energy management are increasingly critical. However, the current park energy management generally has the following problems: At the data collection and analysis level, the traditional method relies on manual input or single type sensors, with low data collection frequency and single dimension, making it difficult to reflect the energy system operation state in real time and comprehensively. For example, the manually statistical energy consumption data has a lag, and cannot be associated with meteorological conditions, production plans and other influencing factors, making it difficult to accurately mine energy consumption rules and locate energy-saving potential points. At the same time, the data processing capacity is insufficient, and it is difficult to conduct in-depth analysis on massive data and provide strong support for energy management. In terms of model construction and optimization, existing energy management models are mostly based on static data and simple algorithms, lacking consideration of dynamic characteristics of energy systems. These models cannot accurately simulate changes in device operating parameters, energy price fluctuations, and energy cost and energy consumption changes under the influence of environmental factors, resulting in a disconnect between the energy-saving plans developed and the actual situation, making it difficult to achieve efficient collaborative optimization of energy. For example, when the device performance declines or the energy market price fluctuates, the traditional model cannot adjust the strategy in time, causing energy waste and cost increase. In the optimization scheme development and decision-making link, the traditional method often relies on experience judgment, lacking a scientific quantitative evaluation system. In the decision-making process of device updating and operation strategy adjustment, it is difficult to comprehensively consider multiple targets such as cost, energy consumption and environment, making it difficult to balance short-term benefits and long-term development, resulting in unreasonable resource allocation and low energy management efficiency. In addition, the lack of effective decision support tools makes it difficult to intuitively show the pros and cons of different schemes, making it difficult for managers to make scientific decisions. SUMMARY
[0003] The purpose of the present application is to provide a park energy collaborative energy-saving optimization model construction method and device, which realizes accurate data, cost and energy consumption optimization, scientific decision-making and scheme system adaptation through full-quantity data collection, double-target setting, construction of cost and energy consumption model, multi-objective optimization and scheme evaluation.
[0004] The above technical purpose of the present application is realized by the following technical scheme: a park energy collaborative energy-saving optimization model construction method, comprising the following steps: S1, collect data and analyze, including: real-time acquisition of equipment operation data, collection of energy consumption data, combination of meteorological data, production scheduling plan data, construction of multi-dimensional energy consumption data set, and construction of park energy status evaluation report; S2, according to the park energy status evaluation report, construct a target system, set economic targets and energy saving targets, and decompose them into quantifiable secondary indicators; S3, according to the target system, construct a cost model and an energy consumption model, and calibrate the model parameters; S4, according to the constructed cost model and energy consumption model and model parameters, from the perspective of equipment level, operation strategy and perception network, construct an optimization scheme database; S5, according to the optimization scheme database, construct a multi-objective optimization model, and solve the Pareto optimal solution set by using NSGA-II algorithm; S6, quantitatively evaluate the optimization scheme, and visually support the decision-making through an interactive decision-making interface.
[0005] As a preferred technical solution of the present application, the equipment operation data includes the operation parameters, cumulative running time, maintenance cycle and historical failure data of power generation equipment, heating equipment and gas facilities; the energy consumption data is collected according to user type, energy type and time dimension.
[0006] As a preferred technical solution of the present application, the economic targets include annual energy comprehensive cost reduction rate and device full life cycle cost minimization; the energy saving targets include unit GDP energy consumption reduction rate and renewable energy proportion improvement target.
[0007] As a preferred technical solution of the present application, the cost items of the cost model include energy procurement cost, equipment operation and maintenance cost, equipment replacement cost and penalty cost; the energy consumption items of the energy consumption model include basic energy consumption, variable energy consumption, transmission loss and equipment self-consumption.
[0008] As a preferred technical solution of the present application, the objective function of the multi-objective optimization model is minF (X)=[w1C(X),w2E (X)], wherein w1 is the cost target weight coefficient, w2 is the energy consumption target weight coefficient, w1+w2=1; the decision variable X includes equipment replacement decision and operation parameter setting; the constraint conditions include energy supply and demand balance, equipment performance limitation and investment budget constraint.
[0009] As a preferred technical solution of the present application, in the optimization scheme database, the equipment level optimization includes equipment replacement scheme and equipment capacity expansion scheme; the operation strategy optimization includes load scheduling scheme and energy conversion scheme; the perception network upgrade includes different density of sensor deployment scheme.
[0010] As a preferred technical solution of the present invention, the quantitative evaluation includes cost indicators, energy-saving indicators and risk indicators; the visual decision support includes scheme comparison radar chart, sensitivity analysis and dynamic simulation.
[0011] As a preferred technical solution of the present invention, in the model parameter calibration, the fixed parameters are determined by the equipment manual, and the dynamic parameters are obtained by prediction or fitting of historical data; the initial population of the NSGA-II algorithm is a randomly generated combination of equipment configuration and operation strategy, and terminates after 100 iterations or when the objective function converges through fitness evaluation and evolutionary operation.
[0012] A device for constructing a collaborative energy-saving optimization model for a park includes a processor and a memory. The memory stores a computer program executable by the processor, and the processor executes the computer program to implement the above-mentioned method.
[0013] In summary, the present invention has the following beneficial effects: Advantages in data acquisition and analysis: A comprehensive data acquisition system is built, enabling high-frequency, real-time collection of equipment operation and energy consumption data through API interfaces and smart meters, integrating multi-dimensional information to form rich datasets. Advanced data processing technologies are used to deeply mine value, increasing data acquisition frequency from monthly to minute-level, with accuracy exceeding 95%, laying a data foundation for energy optimization.
[0014] Cost and energy consumption optimization results: A cost and energy consumption model is constructed to accurately quantify various cost and energy consumption indicators. Combining a multi-objective optimization model and the NSGA-II algorithm, the optimal balance point is found under the constraints of supply and demand, equipment performance, and budget. It is expected to reduce overall energy costs by 15%-25%, reduce energy consumption by 12%-20%, improve utilization efficiency, and optimize the total life cycle cost of equipment to extend its lifespan and reduce replacement frequency.
[0015] Scientific visualization for decision support: A multi-dimensional quantitative evaluation system is established, and an interactive interface is developed to display the effectiveness of solutions through visualization methods such as radar charts, sensitivity analysis, and dynamic simulations. This avoids the blindness of experience-based decision-making, improving decision-making efficiency by over 50% and accuracy by 40%, providing intuitive and scientific decision-making basis.
[0016] System adaptability optimization: The optimization solution database covers dimensions such as equipment, operation strategies, and sensing networks. At the equipment level, indicators such as payback period guide replacement and capacity expansion; operation strategies optimize scheduling based on electricity prices and the characteristics of the combined heat and power (CHP) system; and the sensing network is designed and deployed based on a comprehensive consideration of costs, benefits, and self-consumption. The solution can be flexibly adjusted and expanded according to the dynamic changes in the park's energy system, ensuring long-term effectiveness. Attached Figure Description
[0017] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation
[0018] The present invention will be further described in detail below with reference to the accompanying drawings.
[0019] like Figure 1 As shown, the present invention provides a method and apparatus for constructing a collaborative energy-saving optimization model for industrial parks, comprising the following steps: S1. Data Collection and Current Status Analysis. This includes: S11. Full Data Acquisition: Equipment Operation Data: Through the park's energy management system API interface, real-time operating parameters of power generation equipment (thermal power unit load rate, photovoltaic panel power generation efficiency), heating equipment (boiler thermal efficiency, pipeline temperature distribution), and gas facilities (pipeline pressure fluctuations, pressure regulating station start-up and shutdown records) are acquired. Accumulated equipment runtime, maintenance cycles, and historical fault data are recorded simultaneously. Energy Consumption Data: Energy consumption data is collected from smart meters according to user type (industrial / commercial / residential), energy type (electricity / gas / heat), and time dimension (year / quarter / month / day / hour). Combined with meteorological data (temperature, sunlight, wind speed) and production scheduling plans, a multi-dimensional energy consumption dataset is constructed.
[0020] S12. Current Status Assessment: Based on the collected data, construct a current status assessment report for the park's energy sector. Energy Flow Map: Draws the production, transmission, and consumption paths of electricity, gas, and heat within the park, and marks the loss rate at each stage.
[0021] Cost structure analysis: Break down the proportion of energy procurement costs, equipment operation and maintenance costs, and labor management costs to identify cost-sensitive points.
[0022] Energy efficiency diagnosis: Calculate the energy efficiency ratio of key equipment (such as boiler thermal efficiency and photovoltaic conversion efficiency), compare it with industry benchmark values, and mark inefficient equipment.
[0023] S2. Target System Construction: S21. Dual Objectives: Economic Objectives: Set an annual overall energy cost reduction rate (e.g., 15%) and minimize the total life-cycle cost of equipment. Energy Conservation Objectives: Determine a reduction rate in energy consumption per unit of GDP (e.g., 8%) and a target for increasing the proportion of renewable energy (e.g., increasing the proportion of photovoltaic power generation from 20% to 30%).
[0024] S22. Indicator decomposition: Decompose the overall target into quantifiable secondary indicators: Economic categories: Energy procurement unit price fluctuation coefficient, annual growth rate of equipment operation and maintenance costs.
[0025] Energy-saving categories: peak-valley load difference rate, waste heat recovery and utilization rate, and carbon emission intensity.
[0026] S3, Core Model Construction, including Cost Model and Energy Consumption Model.
[0027] S31. Cost Model: The energy management cost of the park mainly consists of four core modules: energy procurement cost, equipment operation and maintenance cost, equipment replacement cost, and penalty cost. Each module is further subdivided into multiple sub-costs, forming a complete cost calculation system. Energy procurement costs: The calculation formula is: ; Total energy procurement cost; : No. Price per unit of energy (yuan / unit); : No. Energy consumption (units). : No. Energy price volatility coefficient (the range of values is determined based on historical data statistics); Equipment maintenance costs: The calculation formula is: ; Cmaintain: Daily maintenance costs; Cmaintain = T × β × M (T is the equipment running time, β is the maintenance coefficient per unit time, and M is the unit price of maintenance labor). Crepair: Fault Repair Costs ( (The cost of repairing the j-th fault). Cconsume: Consumable replacement cost (Sk is the quantity of the k-th type of consumable used, and Pk is the unit price of the k-th type of consumable). Equipment replacement cost: Calculation formula: Replacement = Cpurchase + Cinstall; Cpurchase: Equipment purchase cost, including the price of the equipment itself, transportation costs, etc. Cinstall: Installation and debugging costs, including labor costs, debugging material costs, etc. Cost of punishment: Calculation formula: Cpenalty = Ccarbon + Creliability; Ccarbon: Fines for exceeding carbon emission limits, Ccarbon=(Eactual−Elimit)×F (Eactual is the actual carbon emissions, Elimit is the carbon emission limit, and F is the fine per unit of excess emission). Creliability: Penalty for breach of power supply reliability, calculated based on the power outage duration and compensation standards stipulated in the contract; S32. Energy Consumption Model: The park's energy consumption is mainly composed of four modules: basic energy consumption, variable energy consumption, transmission loss, and equipment self-consumption. Each module is further subdivided into specific energy consumption items, forming a complete energy consumption calculation system.
[0028] Basic energy consumption: The calculation formula is: ; Ebase: Basic total energy consumption (units: kWh, m³, GJ, etc., depending on the energy type); Pratedi: Rated power of the i-th device (kW, m³ / h, GJ / h, etc.); Ti: Running time of the i-th device (h); Variable energy consumption: Calculation formula: ; Evariable: Total variable energy consumption; Ebasej: Basic energy consumption of equipment affected by the environment; The influence coefficient of environmental parameter X (such as temperature, light intensity, etc.) on the energy consumption of the j-th device is obtained through regression analysis of historical data.
[0029] Transmission loss: Calculation formula: ; Eloss: Total transmission loss; Etransmitk: Transmission energy of the k-th transmission line segment; ηk: The loss rate of the k-th transmission line segment, which can be determined through line parameters and historical data statistics; Equipment self-consumption: Calculation formula: ; Total self-consumption of equipment; : The operating power of the sth device; Ts: The running time of the s-th device; S33. Model parameter calibration: Fixed parameters include: rated power of the equipment, carbon emission factor, etc., which are determined by the equipment manual.
[0030] Dynamic parameters include: Price volatility coefficient αi: Based on historical data from the past 3 years, predicted using the ARIMA model.
[0031] Equipment aging factor βi: fitted by combining equipment running time, maintenance records, and Weibull distribution.
[0032] Environmental impact factors: Establish regression models for temperature-air conditioning energy consumption, light intensity-photovoltaic efficiency, etc.
[0033] S4. Optimize the database construction.
[0034] S41. Equipment-level optimization: Equipment replacement plan: Calculate the payback period and net present value of different energy-saving equipment (such as high-efficiency heat pumps replacing traditional boilers); Equipment capacity expansion plan: Assess the impact of expanding distributed energy (photovoltaic / wind power) capacity on cost and energy saving.
[0035] S42. Operation strategy optimization: Load scheduling scheme: Based on peak and valley electricity prices, formulate equipment start-up and shutdown schedules to minimize electricity purchase costs; Energy conversion scheme: Optimize the operating parameters of the combined electricity-heat-cooling system to improve the efficiency of energy cascade utilization.
[0036] S43. Sensing Network Upgrade: Design sensor deployment schemes with different densities, and calculate: Investment costs: procurement of sensing equipment + network construction costs.
[0037] Increased profitability: Energy savings resulting from precise equipment control.
[0038] Self-energy consumption: Energy consumed by the operation of the sensing network. S5. Optimization Model and Solution.
[0039] S51. Multi-objective optimization model:
[0040] Here, F(X) is a multi-objective optimization function, aiming to simultaneously optimize the two core objectives of cost and energy consumption in park energy management. The expression is: minF(X)=[w1*C(X),w2*E(X)]. This function is presented in vector form. By adjusting the decision variable X, the cost objective C(X) and the energy consumption objective E(X) reach an optimal balance under the influence of weights w1 and w2.
[0041] w1: Cost target weighting coefficient, with a value range of [0,1], representing the relative importance of the comprehensive energy cost C(X) target in the multi-objective optimization process. For example, when the park is in a critical stage of cost control, w1 can be set to a larger value (such as 0.7) to highlight the priority of cost reduction.
[0042] w2: Energy consumption target weighting coefficient, with a value range of [0,1], and satisfying w1+w2=1. It is used to measure the importance of the total energy consumption E(X) target. If the park focuses on energy conservation and emission reduction, the value of w2 can be appropriately increased (e.g., 0.6) to increase the optimization efforts to reduce energy consumption.
[0043] Decision variables: (Equipment replacement decisions, operating parameter settings, etc.)
[0044] Each component xi corresponds to a specific decision factor, mainly including: Equipment replacement decisions: For example, x1 can indicate whether to replace a certain model of boiler (x1=1 means replacement, x1=0 means no replacement); x2 indicates whether to add more distributed photovoltaic panels, etc.
[0045] Operating parameter settings: For example, x3 represents adjusting the operating power of the heat pump unit, and x4 represents setting the supply water temperature of the heating network. These decision variables directly affect the operation mode, cost consumption, and energy consumption level of the park's energy system, and are the core adjustment objects of the optimization model. Constraints: Energy supply and demand balance:
[0046] Si(X): Under decision variable X, the total supply of the i-th type of energy (such as electricity, gas, heat, etc.). Its calculation is related to the operating status and energy conversion efficiency of power generation equipment, heating equipment, gas facilities, etc. For example, for electricity supply, Si(X) needs to consider factors such as the power generation of thermal power units, the power generation of photovoltaic panels, and the purchased electricity.
[0047] Dj(X): Under decision variable X, the total energy demand of the j-th type of user (industrial, commercial, residential, etc.) or the j-th energy-consuming link is calculated based on the user's production activities, living needs, and equipment operating parameters. This constraint ensures that the park's energy supply can meet user needs and avoids energy shortages that could affect normal production and daily life.
[0048] Equipment performance limitations:
[0049] Pmin: The minimum power limit for equipment operation, determined by the equipment's technical parameters and safe operation requirements. For example, the minimum stable operating power of a certain type of fan is 10kW; operating below this power may lead to equipment failure or unstable operation.
[0050] Pmax: The maximum power limit for equipment operation, which also depends on the equipment's rated power and performance upper limit. For example, the maximum power of a boiler is 50t / h; exceeding this power will affect the equipment's lifespan and heating quality.
[0051] Pi(X): Under decision variable X, the actual operating power of the i-th device. This value must be within the minimum and maximum power limits of the device to ensure safe, stable and efficient operation of the device.
[0052] Investment budget constraints:
[0053] Ik(X): Under decision variable X, the cost input of the k-th investment project (such as equipment purchase, installation and commissioning, energy system transformation, etc.), which is related to equipment price, engineering cost, material cost, etc.
[0054] B: The total budget for energy management investment set by the park is determined based on the park's financial situation and development plan. This constraint ensures that the implementation cost of the energy optimization solution is within an affordable range, avoiding excessive investment that could put economic pressure on the park. S52, Solution Algorithm: The Pareto optimal solution set is obtained using NSGA-II (Non-dominated sorting genetic algorithm). Initialize the population: Randomly generate 100 combinations of device configurations and operating strategies.
[0055] Fitness assessment: Calculate the cost and energy consumption target values for each individual.
[0056] Evolutionary operations: generating a new generation of population through selection, crossover, and mutation.
[0057] Termination condition: 100 iterations or convergence of the objective function.
[0058] S6. Solution Evaluation and Decision Support: S61. Quantitative Evaluation: Substitute the optimized solution into the model established in step three, and calculate: Cost indicators: total cost, unit energy cost, and investment payback period.
[0059] Energy saving indicators: energy savings, carbon emission reduction, and the proportion of renewable energy.
[0060] Risk indicators: technology maturity, equipment reliability, and policy adaptability.
[0061] S62, Visualized Decision Support: Develop an interactive decision-making interface to display: Radar chart comparing different options: visually presents the performance of each option on different indicators.
[0062] Sensitivity analysis: Demonstrates the impact of changes in parameters such as electricity price fluctuations and equipment lifespan on the effectiveness of the solution.
[0063] Dynamic simulation: Using digital twin technology, preview the energy flow distribution after the solution is implemented.
[0064] The technical advantages of this invention are: 1. Comprehensiveness and accuracy of data collection and analysis: This invention constructs a comprehensive data acquisition system. Through the park's energy management system API interface and smart meters, it achieves high-frequency, real-time acquisition of equipment operation data and energy consumption data. Simultaneously, it integrates multi-dimensional information such as meteorological data and production scheduling plans to build a rich energy dataset. Employing advanced data cleaning, fusion, and analysis technologies, it can deeply mine data value and accurately reveal the correlation between energy production and consumption and factors such as time, weather, and production activities. Compared to traditional methods, the data acquisition frequency is increased from monthly to minute-level, and data accuracy is improved to over 95%, providing a solid data foundation for energy optimization. 2. High-efficiency optimization of cost and energy consumption: This invention constructs detailed cost and energy consumption models to accurately quantify costs related to energy procurement, equipment operation and maintenance, and equipment replacement, as well as energy consumption indicators such as basic and variable energy consumption. Combining a multi-objective optimization model and the NSGA-II algorithm, it can find the optimal balance between cost and energy consumption under conditions that satisfy energy supply and demand balance, equipment performance limitations, and investment budget constraints. In practical applications, it is expected to reduce overall energy costs by 15%-25% and energy consumption by 12%-20%, significantly improving energy utilization efficiency in industrial parks and reducing operating costs. Simultaneously, by optimizing the entire lifecycle cost of equipment, it extends equipment lifespan, reduces equipment replacement frequency, and further reduces total costs. 3. Scientific nature and visualization of decision support: This invention establishes a comprehensive scheme evaluation and decision support system. It quantitatively evaluates different energy-saving schemes from multiple dimensions, including cost, energy saving, and risk. Through the development of an interactive decision-making interface, it visualizes the effectiveness of schemes using radar charts for scheme comparison, sensitivity analysis, and dynamic simulation. Managers can intuitively compare the advantages and disadvantages of different schemes across various indicators, quickly understand the impact of parameter changes on scheme effectiveness, and preview the energy flow distribution after scheme implementation. This scientific quantitative evaluation and visualization avoids the blindness and subjectivity of experience-based decision-making, improving decision-making efficiency by over 50% and accuracy by 40%, providing managers with intuitive and scientific decision-making basis. 4. The systematic nature and adaptability of the optimization scheme: This invention's optimization database encompasses multiple dimensions, including equipment level, operational strategies, and sensing networks, providing comprehensive energy-saving optimization directions. Equipment-level optimization schemes, through calculations of payback period and net present value, provide a scientific basis for equipment replacement and capacity expansion. Operational strategy optimization, based on peak-valley electricity pricing and the characteristics of combined energy supply systems, formulates reasonable equipment start-up and shutdown schedules and operating parameters to improve energy cascade utilization efficiency. Sensing network upgrade schemes comprehensively consider investment costs, revenue improvement, and their own energy consumption to design optimal sensor deployment plans. Furthermore, the solutions exhibit good adaptability, enabling flexible adjustments and expansion based on the dynamic changes and development needs of the park's energy system, ensuring the long-term effectiveness of energy management.
[0065] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.
Claims
1. A method for constructing an energy-coordinated energy-saving optimization model for industrial parks, characterized by: Includes the following steps: S1. Collect and analyze data, including: real-time acquisition of equipment operation data, collection of energy consumption data, and construction of a multi-dimensional energy consumption dataset by combining meteorological data and production scheduling data, and construction of an energy status assessment report for the park. S2. Based on the energy status assessment report of the park, construct a target system, set economic and energy-saving targets, and decompose them into quantifiable secondary indicators; S3. Based on the target system, construct the cost model and energy consumption model, and calibrate the model parameters; S4. Based on the constructed cost model, energy consumption model, and model parameters, construct an optimization scheme database from the perspectives of equipment, operation strategy, and sensing network. S5. Based on the optimization scheme database, construct a multi-objective optimization model and use the NSGA-II algorithm to solve for the Pareto optimal solution set; S6. Quantitatively evaluate the optimization scheme and provide visual decision support through an interactive decision-making interface.
2. The method for constructing a park energy synergy and energy-saving optimization model according to claim 1, characterized in that: The equipment operation data includes the operating parameters, cumulative operating time, maintenance cycle, and historical fault data of power generation equipment, heating equipment, and gas facilities; the energy consumption data is collected according to user type, energy type, and time dimension.
3. The method for constructing a collaborative energy-saving optimization model for industrial parks according to claim 2, characterized in that: The economic targets include the annual rate of reduction in overall energy costs and the minimization of equipment lifecycle costs; the energy conservation targets include the rate of reduction in energy consumption per unit of GDP and the target for increasing the proportion of renewable energy.
4. The method for constructing a park energy synergy and energy-saving optimization model according to claim 3, characterized in that: The cost items in the cost model include energy procurement costs, equipment operation and maintenance costs, equipment replacement costs, and penalty costs; the energy consumption items in the energy consumption model include basic energy consumption, variable energy consumption, transmission loss, and equipment self-consumption.
5. The method for constructing a park energy synergy and energy-saving optimization model according to claim 4, characterized in that: The objective function of the multi-objective optimization model is minF (X)=[w1C(X),w2E (X)], where w1 is the cost target weight coefficient, w2 is the energy consumption target weight coefficient, and w1+w2=1; the decision variable X includes equipment replacement decisions and operating parameter settings; the constraints include energy supply and demand balance, equipment performance limitations, and investment budget constraints.
6. The method for constructing a park energy synergy and energy-saving optimization model according to claim 5, characterized in that: The optimization scheme database includes equipment-level optimization schemes such as equipment replacement schemes and equipment capacity expansion schemes; operation strategy optimization schemes such as load scheduling schemes and energy conversion schemes; and sensing network upgrade schemes such as sensor deployment schemes at different densities.
7. The method for constructing a park energy synergy and energy-saving optimization model according to claim 6, characterized in that: The quantitative assessment includes cost indicators, energy-saving indicators, and risk indicators; the visual decision support includes scheme comparison radar charts, sensitivity analysis, and dynamic simulation.
8. The method for constructing a park energy synergy and energy-saving optimization model according to claim 7, characterized in that: In the model parameter calibration, fixed parameters are determined by the equipment manual, and dynamic parameters are obtained by prediction or fitting of historical data; the initial population of the NSGA-II algorithm is a randomly generated combination of equipment configuration and operation strategy, and terminates after 100 iterations or when the objective function converges, through fitness evaluation and evolutionary operations.
9. A device for constructing a collaborative energy-saving optimization model for industrial parks, characterized in that: include: A processor and a memory, the memory storing a computer program executable by the processor, wherein the processor, when executing the computer program, implements the method of any one of claims 1-8.