Multi-energy complementary based zero-carbon park comprehensive energy optimization management method and system
Patent Information
- Application Number
- CN202611179314.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-05
- Publication Date
- 2026-11-03
AI Technical Summary
The existing energy system in the park cannot achieve zero-carbon operation. It suffers from problems such as decoupling of multiple energy subsystems, lack of carbon quantification and control, low level of intelligent scheduling, high equipment redundancy, and system response lag, and cannot meet the long-term operation requirements of refined, intelligent and low-cost operation.
By collecting real-time data and using predictive models to forecast load and renewable energy output, and combining carbon emission accounting standards to construct a multi-energy flow collaborative optimization model, dynamic carbon emission constraints are generated to achieve multi-energy flow collaborative scheduling of electricity, heat, cooling, gas, and storage. Furthermore, an adaptive closed-loop optimization adjustment strategy is adopted to adapt to dynamic fluctuations in load and weather.
It has improved the absorption rate of new energy sources, reduced energy costs and carbon emissions, and achieved long-term, stable and intelligent energy dispatching in the zero-carbon park.
Smart Images
Figure CN123034355A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of energy management technology in industrial parks, and in particular relates to a comprehensive energy optimization management method and system for zero-carbon industrial parks based on multi-energy complementarity. Background Technology
[0002] Currently, the integrated energy systems of various parks, such as industrial parks, commercial parks, campuses, and data centers, generally adopt a distributed and decentralized energy supply architecture. At the energy management level, the existing park energy management mainly uses traditional energy management systems (EMS) and supervisory control systems (SCADA) as the core management carriers. At the scheduling and control strategy level, existing technologies generally adopt an independent control mode for each device, configuring independent control logic for photovoltaic, energy storage, heat pump, and gas equipment.
[0003] Existing technologies have many core flaws and cannot meet the long-term operational needs of zero-carbon industrial parks, which require precision, intelligence, low carbon emissions, and low costs. The specific problems and their causes are as follows: 1. The multi-energy subsystems operate in a decoupled manner, resulting in low energy complementarity utilization and poor renewable energy absorption.
[0004] 2. The lack of carbon quantification management and carbon constraint scheduling mechanisms makes it impossible to stably achieve the goal of zero-carbon operation.
[0005] 3. The dispatching and control system has a low level of intelligence, resulting in slow system response and weak anti-interference capabilities. The existing dispatching mode relies heavily on manual experience or fixed timing strategies, lacking the ability to predict meteorological data, load data, and energy output data in advance. It is unable to adapt to fluctuations in electricity, heat, and cooling loads in the park, as well as the random changes in wind and solar power output.
[0006] 4. The energy equipment configuration has high redundancy, resulting in high system investment and operating energy consumption costs.
[0007] 5. Without a closed-loop optimization and control system, it is difficult to achieve long-term stable operation in an engineered manner.
[0008] The purpose of this invention is to provide a comprehensive energy optimization management method and system for zero-carbon industrial parks based on multi-energy complementarity, so as to solve the problems existing in the prior art. Summary of the Invention
[0009] To achieve the above objectives, the present invention provides the following solution: The present invention provides a comprehensive energy optimization management method for zero-carbon industrial parks based on multi-energy complementarity, the method comprising: S1. Collect real-time data through preset sensing devices. The real-time data includes renewable energy output data of the park, operation data of conventional energy equipment, energy consumption data of various loads, environmental meteorological data, real-time electricity price and carbon price data, and equipment carbon emission data. S2. Based on the real-time data and historical database, the prediction model is used to complete the ultra-short-term prediction of the park's cooling, heating and power load, wind and solar renewable energy output, and real-time electricity price and carbon price dynamic prediction, and output accurate prediction results. S3. Based on the energy consumption type and real-time output parameters of various energy supply equipment in the park, and combined with carbon emission accounting standards, the park’s real-time carbon emissions are quantified and calculated for each equipment and each time period to generate dynamic carbon emission constraints for the park. S4. Based on the accurate prediction results and combined with the dynamic carbon emission constraints of the park, with the core optimization objectives of the lowest energy operating cost, the lowest overall carbon emission, and the highest renewable energy absorption rate of the park, and combined with equipment operation constraints, energy storage state of charge constraints, carbon emission threshold constraints, and energy supply and demand balance constraints, a multi-energy flow collaborative optimization mathematical model is constructed, and the optimal multi-energy scheduling strategy for the future time period is obtained by solving it. S5. The optimal multi-energy scheduling strategy for the future time period is transformed into standardized equipment control instructions and sent to each energy execution equipment in the park to simultaneously adjust the real-time output of photovoltaic, wind power, gas turbine, heat pump, energy storage, and cold and heat source equipment, so as to realize the coordinated scheduling of multiple energy flows such as electricity, heat, cold, gas, and storage. S6. Real-time collection of actual operating condition data after executing the standardized equipment control commands, comparison of the accurate prediction results with the actual operating condition data, iterative correction of the prediction model and the multi-objective optimization model parameters within the multi-energy flow collaborative optimization mathematical model, the multi-objective optimization model parameters including equipment operation constraint parameters, energy storage state of charge constraint parameters, carbon emission threshold parameters, energy supply and demand balance constraint parameters, periodically rolling update of the scheduling strategy, to achieve adaptive closed-loop optimization operation of the system.
[0010] Optionally, in S2, the prediction model predicts over a time period of 15 minutes. By incorporating a time-series prediction algorithm, it completes the prediction of park cooling, heating, and power loads, wind and solar renewable energy output, and real-time electricity and carbon price dynamics.
[0011] Optionally, in S4, the constraints of the multi-energy flow collaborative optimization model also include constraints on the reliability of park energy supply, constraints on equipment start-up and shutdown frequency, and constraints on energy transmission loss.
[0012] Optionally, in S6, the system's adaptive closed-loop optimization operation cycle and prediction cycle are synchronously set to 15 minutes, completing data feedback, model correction, and strategy updates cycle by cycle to adapt to dynamic fluctuations in load and weather.
[0013] To achieve the above objectives, the present invention also provides the following solution: a multi-energy complementary zero-carbon park integrated energy optimization management system, used to implement the above-mentioned multi-energy complementary zero-carbon park integrated energy optimization management method, the system comprising: The data acquisition unit is used to collect real-time data, including renewable energy output data of the park, operation data of conventional energy equipment, energy consumption data of various loads, environmental meteorological data, real-time electricity price and carbon price data, and equipment carbon emission data. The prediction processing unit is communicatively connected to the data acquisition unit and is used to complete ultra-short-term park cooling, heating and power load prediction, wind and solar renewable energy output prediction, and real-time electricity price and carbon price dynamic prediction based on the real-time data and historical database, and output accurate prediction results. The precise accounting unit is used to quantify and calculate the real-time carbon emissions of the park on a device-by-device and time-by-time basis, based on the energy consumption type and real-time output parameters of various energy supply equipment in the park, combined with carbon emission accounting standards, and to generate dynamic carbon emission constraints for the park. The modeling and solving unit is communicatively connected to the prediction processing unit and the accurate calculation unit, respectively. It is used to construct a multi-energy flow collaborative optimization mathematical model based on the accurate prediction results and combined with the dynamic carbon emission constraints of the park. The core optimization objectives are to minimize the park's energy operating costs, minimize overall carbon emissions, and maximize the renewable energy absorption rate. It also combines equipment operation constraints, energy storage state of charge constraints, carbon emission threshold constraints, and energy supply and demand balance constraints to solve for the optimal multi-energy scheduling strategy for future periods. The instruction execution unit is communicatively connected to the modeling and solving unit. It is used to convert the optimal multi-energy scheduling strategy for the future time period into standardized equipment control instructions and send them to each energy execution device in the park. It synchronously adjusts the real-time output of photovoltaic, wind power, gas turbine, heat pump, energy storage, and cold and heat source equipment to achieve coordinated scheduling of multiple energy flows such as electricity, heat, cold, gas, and storage. The adaptive optimization unit is communicatively connected to the data acquisition unit and the modeling and solving unit, respectively. It is used to compare the actual operating condition data after the data acquisition unit collects and executes the standardized equipment control commands with the accurate prediction results, and iteratively correct the prediction model and the multi-objective optimization model parameters inside the multi-energy flow collaborative optimization mathematical model. The multi-objective optimization model parameters include equipment operation constraint parameters, energy storage state of charge constraint parameters, carbon emission threshold parameters, and energy supply and demand balance constraint parameters. The scheduling strategy is periodically updated to achieve adaptive closed-loop optimization operation of the system.
[0014] The present invention discloses the following technical effects: This method collects real-time data on renewable energy output, equipment operation, load, weather, electricity and carbon prices, and carbon emissions in the industrial park. Combined with historical data, it outputs accurate predictions of load, wind and solar output, and prices through a predictive model. Based on equipment energy consumption parameters, it calculates the park's carbon emissions in real time, generating dynamic carbon constraints. With the goals of lowest cost, minimum carbon emissions, and highest absorption rate, it constructs a multi-energy flow collaborative optimization model by incorporating multiple constraints. This model solves for the optimal scheduling strategy and translates it into control commands for execution, achieving coordinated scheduling of electricity, heat, cooling, gas, and energy storage. This invention iteratively corrects the prediction model and optimizes its constraint parameters by comparing the predicted data with actual operating conditions, continuously updating the scheduling strategy to achieve adaptive closed-loop optimization operation. This effectively improves renewable energy absorption rate, reduces energy costs and carbon emissions, and is suitable for long-term stable and intelligent energy scheduling scenarios in zero-carbon industrial parks. Attached Figure Description
[0015] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation
[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0018] like Figure 1 As shown, a comprehensive energy optimization management method for zero-carbon industrial parks based on multi-energy complementarity is proposed, the method comprising: S1. Collect real-time data through preset sensing devices. The real-time data includes renewable energy output data of the park, operation data of conventional energy equipment, energy consumption data of various loads, environmental meteorological data, real-time electricity price and carbon price data, and equipment carbon emission data. S2. Based on the real-time data and historical database, the prediction model is used to complete the ultra-short-term prediction of the park's cooling, heating and power load, wind and solar renewable energy output, and real-time electricity price and carbon price dynamic prediction, and output accurate prediction results. S3. Based on the energy consumption type and real-time output parameters of various energy supply equipment in the park, and combined with carbon emission accounting standards, the park’s real-time carbon emissions are quantified and calculated for each equipment and each time period to generate dynamic carbon emission constraints for the park. S4. Based on the accurate prediction results and combined with the dynamic carbon emission constraints of the park, with the core optimization objectives of the lowest energy operating cost, the lowest overall carbon emission, and the highest renewable energy absorption rate of the park, and combined with equipment operation constraints, energy storage state of charge constraints, carbon emission threshold constraints, and energy supply and demand balance constraints, a multi-energy flow collaborative optimization mathematical model is constructed, and the optimal multi-energy scheduling strategy for the future time period is obtained by solving it. S5. The optimal multi-energy scheduling strategy for the future time period is transformed into standardized equipment control instructions and sent to each energy execution equipment in the park to simultaneously adjust the real-time output of photovoltaic, wind power, gas turbine, heat pump, energy storage, and cold and heat source equipment, so as to realize the coordinated scheduling of multiple energy flows such as electricity, heat, cold, gas, and storage. S6. Real-time collection of actual operating condition data after executing the standardized equipment control commands, comparison of the accurate prediction results with the actual operating condition data, iterative correction of the prediction model and the multi-objective optimization model parameters within the multi-energy flow collaborative optimization mathematical model, the multi-objective optimization model parameters including equipment operation constraint parameters, energy storage state of charge constraint parameters, carbon emission threshold parameters, energy supply and demand balance constraint parameters, periodically rolling update of the scheduling strategy, to achieve adaptive closed-loop optimization operation of the system.
[0019] This embodiment is applied to a typical industrial and commercial zero-carbon demonstration park. The park is equipped with rooftop photovoltaics, small wind turbines, lithium battery energy storage, hot water storage tanks, ice storage, gas heat pumps, and heating, cooling, and electrical load equipment. Smart meters, heat meters, weather sensors, and carbon monitoring terminals are deployed throughout the area. The specific implementation steps are as follows: S1. The park's full-area sensing equipment collects real-time operational data, including photovoltaic and wind power renewable energy output data, gas turbine and heat pump conventional equipment operating parameters, office building and factory electricity, cooling and heating load data, ambient temperature, irradiance, wind speed and meteorological data, time-of-use electricity price, carbon trading carbon price data, and real-time carbon emission data of each device, achieving synchronous collection of data from all dimensions.
[0020] S2. The system retrieves the local historical operation database and uses the built-in prediction model to make ultra-short-term predictions on the park's power load, heating and cooling load, wind and solar power output, real-time electricity price and carbon price, and outputs high-precision prediction results for future periods, providing advance data support for optimized scheduling.
[0021] S3. Based on the energy consumption type and real-time output of various equipment such as photovoltaics, wind turbines, gas heat pumps, and energy storage, and in accordance with the park's carbon emission accounting standards, the system calculates the carbon emissions of each device and each moment, dynamically generates the park's real-time carbon emission constraint upper limit, and forms zero-carbon dispatch constraints.
[0022] S4. Using the predicted load, new energy, and price data as inputs, and superimposed with dynamic carbon emission constraints, establish a multi-energy flow collaborative optimization mathematical model; with the objectives of minimizing operating costs, minimizing carbon emissions, and maximizing wind and solar energy absorption rates, and combining the maximum and minimum output of equipment, the upper and lower limits of energy storage SOC, carbon emission thresholds, and supply and demand balance constraints, solve for the optimal scheduling scheme of electricity, heat, cooling, gas, and storage in the future period.
[0023] S5. Convert the optimal scheduling strategy into standardized control commands and send them to the controllers of each energy device to dynamically adjust the grid-connected output of photovoltaic power, wind turbine output, start-up and shutdown of gas heat pumps and load, energy storage charging and discharging power, and energy storage and release status of thermal and cold storage equipment, so as to achieve coordinated and complementary operation of multiple energy flows.
[0024] S6. After the equipment executes the control command, the system transmits the actual operating condition data back in real time, compares the actual load, actual wind and solar power output, actual carbon emissions, and actual energy consumption with the prediction results; iteratively updates the accuracy of the prediction model based on the deviation data, and at the same time corrects and optimizes the equipment operation constraints, energy storage constraints, carbon emission constraints, and supply and demand balance constraints parameters in the model, and periodically updates the scheduling strategy to achieve adaptive closed-loop optimized operation of the park's energy system.
[0025] Optionally, in S2, the prediction model predicts over a time period of 15 minutes. By incorporating a time-series prediction algorithm, it completes the prediction of park cooling, heating, and power loads, wind and solar renewable energy output, and real-time electricity and carbon price dynamics.
[0026] The system is set to a fixed 15-minute prediction cycle and is equipped with a lightweight time-series prediction algorithm. It is continuously trained based on recent 15-minute, 30-minute, and 1-hour historical operating condition samples to ensure that the prediction data is highly matched with the real-time operating conditions of the park, providing accurate input for short-cycle fine-tuning.
[0027] Furthermore, in S4, the constraints of the multi-energy flow collaborative optimization model also include constraints on the reliability of park energy supply, constraints on equipment start-up and shutdown frequency, and constraints on energy transmission loss.
[0028] This embodiment introduces three additional auxiliary constraints to enhance the practicality of the project. First, it adds a power supply reliability constraint to ensure uninterrupted power supply to critical loads in the park and prevent power outages caused by fluctuations in new energy sources. Second, it adds a constraint on equipment start-up and shutdown frequency to limit frequent start-ups and shutdowns of gas-fired heat pumps, units, etc., and reduce equipment losses. Third, it adds an energy transmission loss constraint, which incorporates the park's pipeline and line loss coefficients into the optimization calculation to avoid scheduling schemes that are theoretically optimal but have excessive actual losses, ensuring that the final scheduling strategy balances economy, low carbon emissions, and engineering stability.
[0029] Preferably, in step S6, the system's adaptive closed-loop optimization operation cycle and prediction cycle are synchronously set to 15 minutes, completing data feedback, model correction, and strategy updates cycle by cycle to adapt to dynamic fluctuations in load and weather.
[0030] This embodiment sets the system's closed-loop optimization cycle and prediction cycle to be strictly synchronized, uniformly set at a 15-minute rolling update cycle. Every 15 minutes, a complete closed loop of "data acquisition - prediction calculation - optimization solution - instruction execution - deviation comparison - model correction" is completed. For scenarios involving daytime light fluctuations, wind speed fluctuations, sudden changes in load during commuting hours, and dynamic changes in electricity and carbon prices, high-frequency rolling optimization is used to correct scheduling strategies in real time, effectively adapting to the complex dynamic conditions of the industrial park and improving its resistance to fluctuations and operational robustness.
[0031] like Figure 2 As shown, the present invention also provides a multi-energy complementary zero-carbon park integrated energy optimization management system, used to implement the above-mentioned multi-energy complementary zero-carbon park integrated energy optimization management method, the system comprising: The data acquisition unit is used to collect real-time data, including renewable energy output data of the park, operation data of conventional energy equipment, energy consumption data of various loads, environmental meteorological data, real-time electricity price and carbon price data, and equipment carbon emission data. The prediction processing unit is communicatively connected to the data acquisition unit and is used to complete ultra-short-term park cooling, heating and power load prediction, wind and solar renewable energy output prediction, and real-time electricity price and carbon price dynamic prediction based on the real-time data and historical database, and output accurate prediction results. The precise accounting unit is used to quantify and calculate the real-time carbon emissions of the park on a device-by-device and time-by-time basis, based on the energy consumption type and real-time output parameters of various energy supply equipment in the park, combined with carbon emission accounting standards, and to generate dynamic carbon emission constraints for the park. The modeling and solving unit is communicatively connected to the prediction processing unit and the accurate calculation unit, respectively. It is used to construct a multi-energy flow collaborative optimization mathematical model based on the accurate prediction results and combined with the dynamic carbon emission constraints of the park. The core optimization objectives are to minimize the park's energy operating costs, minimize overall carbon emissions, and maximize the renewable energy absorption rate. It also combines equipment operation constraints, energy storage state of charge constraints, carbon emission threshold constraints, and energy supply and demand balance constraints to solve for the optimal multi-energy scheduling strategy for future periods. The instruction execution unit is communicatively connected to the modeling and solving unit. It is used to convert the optimal multi-energy scheduling strategy for the future time period into standardized equipment control instructions and send them to each energy execution device in the park. It synchronously adjusts the real-time output of photovoltaic, wind power, gas turbine, heat pump, energy storage, and cold and heat source equipment to achieve coordinated scheduling of multiple energy flows such as electricity, heat, cold, gas, and storage. The adaptive optimization unit is communicatively connected to the data acquisition unit and the modeling and solving unit, respectively. It is used to compare the actual operating condition data after the data acquisition unit collects and executes the standardized equipment control commands with the accurate prediction results, and iteratively correct the prediction model and the multi-objective optimization model parameters inside the multi-energy flow collaborative optimization mathematical model. The multi-objective optimization model parameters include equipment operation constraint parameters, energy storage state of charge constraint parameters, carbon emission threshold parameters, and energy supply and demand balance constraint parameters. The scheduling strategy is periodically updated to achieve adaptive closed-loop optimization operation of the system.
[0032] This embodiment establishes a zero-carbon industrial park multi-energy complementary optimization management system adapted to the above optimization method. The various units work collaboratively, and the specific deployment and operation are as follows: Data acquisition unit: Deployed at various energy equipment and load terminals in the park, it collects real-time data on new energy output, conventional equipment operation, cooling, heating and power load, weather, electricity price, carbon price, and carbon emissions around the clock through smart meters, weather stations, carbon monitoring terminals, and equipment controllers, and uploads the data to the upper-level unit in real time.
[0033] Predictive processing unit: Connects to the data acquisition unit, stores historical operating condition database, performs time series prediction calculation every 15 minutes, outputs accurate prediction data of load, wind and solar power output, electricity price, and carbon price, and pushes them synchronously to the modeling and solving unit.
[0034] Precise accounting unit: Receives operating parameters of each device in real time, calculates carbon emissions for each device and time period according to device type, dynamically updates the carbon emission constraint threshold of the park, and provides low-carbon constraint boundaries for the optimization model.
[0035] Modeling and solving unit: Receives predicted data and dynamic carbon constraints, loads multi-objective and multi-constraint optimization models, and performs batch calculations to obtain the optimal multi-energy coordinated scheduling strategy for the next 15 minutes, balancing the three objectives of operating costs, carbon emissions, and new energy consumption.
[0036] Command execution unit: It parses the optimized scheduling strategy into standardized control commands that can be recognized by each device, and controls the output adjustment of photovoltaic, wind power, gas turbine, heat pump, energy storage, thermal storage and cold storage equipment respectively, so as to realize unified and coordinated scheduling of multiple energy flows.
[0037] Adaptive optimization unit: continuously collects actual operating conditions of equipment, compares the deviation between predicted and actual values, periodically iterates and optimizes the accuracy of the prediction model, dynamically corrects equipment operation constraints, energy storage constraints, carbon emission constraints, and supply and demand balance constraints, and continuously updates scheduling strategies to achieve long-term adaptive, self-correcting, and self-optimizing closed-loop operation of the system.
[0038] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.
Claims
1. A comprehensive energy optimization management method for zero-carbon industrial parks based on multi-energy complementarity, characterized in that, The method includes: S1. Collect real-time data through preset sensing devices. The real-time data includes renewable energy output data of the park, operation data of conventional energy equipment, energy consumption data of various loads, environmental meteorological data, real-time electricity price and carbon price data, and equipment carbon emission data. S2. Based on the real-time data and historical database, the prediction model is used to complete the ultra-short-term prediction of the park's cooling, heating and power load, wind and solar renewable energy output, and real-time electricity price and carbon price dynamic prediction, and output accurate prediction results. S3. Based on the energy consumption type and real-time output parameters of various energy supply equipment in the park, and combined with carbon emission accounting standards, the park’s real-time carbon emissions are quantified and calculated for each equipment and each time period to generate dynamic carbon emission constraints for the park. S4. Based on the accurate prediction results and combined with the dynamic carbon emission constraints of the park, with the core optimization objectives of the lowest energy operating cost, the lowest overall carbon emission, and the highest renewable energy absorption rate of the park, and combined with equipment operation constraints, energy storage state of charge constraints, carbon emission threshold constraints, and energy supply and demand balance constraints, a multi-energy flow collaborative optimization mathematical model is constructed, and the optimal multi-energy scheduling strategy for the future time period is obtained by solving it. S5. The optimal multi-energy scheduling strategy for the future time period is transformed into standardized equipment control instructions and sent to each energy execution equipment in the park to simultaneously adjust the real-time output of photovoltaic, wind power, gas turbine, heat pump, energy storage, and cold and heat source equipment, so as to realize the coordinated scheduling of multiple energy flows such as electricity, heat, cold, gas, and storage. S6. Real-time collection of actual operating condition data after executing the standardized equipment control commands, comparison of the accurate prediction results with the actual operating condition data, iterative correction of the prediction model and the multi-objective optimization model parameters within the multi-energy flow collaborative optimization mathematical model, the multi-objective optimization model parameters including equipment operation constraint parameters, energy storage state of charge constraint parameters, carbon emission threshold parameters, energy supply and demand balance constraint parameters, periodically rolling update of the scheduling strategy, to achieve adaptive closed-loop optimization operation of the system.
2. The method for comprehensive energy optimization management of zero-carbon industrial parks based on multi-energy complementarity according to claim 1, characterized in that, In S2, the prediction model predicts over a time period of 15 minutes. By incorporating a time-series prediction algorithm, it completes the prediction of park cooling, heating, and power loads, wind and solar renewable energy output, and real-time electricity and carbon price dynamics.
3. The method for comprehensive energy optimization management of zero-carbon industrial parks based on multi-energy complementarity according to claim 1, characterized in that, In S4, the constraints of the multi-energy flow collaborative optimization model also include constraints on the reliability of park power supply, constraints on equipment start-up and shutdown frequency, and constraints on energy transmission loss.
4. The method for comprehensive energy optimization management of zero-carbon industrial parks based on multi-energy complementarity according to claim 1, characterized in that, In S6, the system's adaptive closed-loop optimization operation cycle and prediction cycle are synchronously set to 15 minutes, completing data feedback, model correction, and strategy updates cycle by cycle to adapt to dynamic fluctuations in load and weather.
5. A zero-carbon industrial park integrated energy optimization management system based on multi-energy complementarity, characterized in that, The system is used to implement the integrated energy optimization management method for zero-carbon industrial parks based on multi-energy complementarity as described in any one of claims 1-4, the system comprising: The data acquisition unit is used to collect real-time data, including renewable energy output data of the park, operation data of conventional energy equipment, energy consumption data of various loads, environmental meteorological data, real-time electricity price and carbon price data, and equipment carbon emission data. The prediction processing unit is communicatively connected to the data acquisition unit and is used to complete ultra-short-term park cooling, heating and power load prediction, wind and solar renewable energy output prediction, and real-time electricity price and carbon price dynamic prediction based on the real-time data and historical database, and output accurate prediction results. The precise accounting unit is used to quantify and calculate the real-time carbon emissions of the park on a device-by-device and time-by-time basis, based on the energy consumption type and real-time output parameters of various energy supply equipment in the park, combined with carbon emission accounting standards, and to generate dynamic carbon emission constraints for the park. The modeling and solving unit is communicatively connected to the prediction processing unit and the accurate calculation unit, respectively. It is used to construct a multi-energy flow collaborative optimization mathematical model based on the accurate prediction results and combined with the dynamic carbon emission constraints of the park. The core optimization objectives are to minimize the park's energy operating costs, minimize overall carbon emissions, and maximize the renewable energy absorption rate. It also combines equipment operation constraints, energy storage state of charge constraints, carbon emission threshold constraints, and energy supply and demand balance constraints to solve for the optimal multi-energy scheduling strategy for future periods. The instruction execution unit is communicatively connected to the modeling and solving unit. It is used to convert the optimal multi-energy scheduling strategy for the future time period into standardized equipment control instructions and send them to each energy execution device in the park. It synchronously adjusts the real-time output of photovoltaic, wind power, gas turbine, heat pump, energy storage, and cold and heat source equipment to achieve coordinated scheduling of multiple energy flows such as electricity, heat, cold, gas, and storage. The adaptive optimization unit is communicatively connected to the data acquisition unit and the modeling and solving unit, respectively. It is used to compare the actual operating condition data after the data acquisition unit collects and executes the standardized equipment control commands with the accurate prediction results, and iteratively correct the prediction model and the multi-objective optimization model parameters inside the multi-energy flow collaborative optimization mathematical model. The multi-objective optimization model parameters include equipment operation constraint parameters, energy storage state of charge constraint parameters, carbon emission threshold parameters, and energy supply and demand balance constraint parameters. The scheduling strategy is periodically updated to achieve adaptive closed-loop optimization operation of the system.