An Optimization Method for a Green Hydrogen Metallurgy Integrated Energy System

Abstract

The present invention discloses an optimization method for a green hydrogen metallurgy integrated energy system. By targeting the multi-energy-quality flow characteristics in the green hydrogen metallurgy integrated energy system, a network matrix model of a standardized matrix is constructed to calculate the multi-energy-quality flow distribution; through the analysis of the multi-time-scale characteristics of flexible adjustable resources, an extended resource-task network model is constructed, and then the multi-link system regulation of the energy-quality flow is realized; based on the uncertain variables in the system, an operation optimization model is constructed to explore the correlation between key indicators in the operation scenario, and then a multi-market adaptive trading auxiliary decision-making system is constructed to output the trading strategies of energy blocks and carbon blocks. The method of the present invention solves the problems of inaccurate multi-energy-quality flow modeling, low system regulation efficiency, and difficulty in coping with uncertainties in the prior art; the present invention combines accurate modeling, collaborative regulation, and efficient operation to improve the overall operation efficiency of the system, optimize multi-market trading, and promote the sustainable development of the green hydrogen metallurgy system.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy system optimization, and particularly relates to an optimization method for a green hydrogen metallurgy integrated energy system. Background Art

[0002] Driven by global carbon emissions reduction, green hydrogen, as a clean energy carrier, has gradually shown important application prospects in the metallurgy industry. The traditional metallurgy industry relies on fossil fuels and has a huge carbon footprint. However, by introducing green hydrogen to replace carbon-based reducing agents, carbon emissions can be significantly reduced, and even zero-carbon production can be achieved. With the development of renewable energy technologies, the widespread application of green hydrogen provides a key approach for the green transformation of the metallurgy industry.

[0003] Currently, the research on green hydrogen metallurgy integrated energy systems mainly focuses on the production, storage, and system integration of green hydrogen. Some progress has been made in the transmission and regulation of multi-energy-quality flows, such as analysis and optimization methods for single links of different energy carriers and material flows. However, due to the interaction and collaborative regulation of multiple heterogeneous energy and material flows in the green hydrogen metallurgy system, there are still significant limitations in the overall modeling, cross-link collaborative regulation, and dynamic optimization of multi-energy-quality flows in existing research.

[0004] The existing technologies mainly face three deficiencies:

[0005] First, it is impossible to accurately describe the transmission characteristics of heterogeneous energy flows and material flows, which affects the overall optimization of the system; specifically, the green hydrogen metallurgy integrated energy system involves multiple heterogeneous energy flows and material flows such as electricity, hydrogen, and heat, and these energy-quality flows exhibit strong dynamics and uncertainties in the spatial and temporal dimensions. Existing modeling methods usually target single energy flows or use simplified models, which cannot accurately describe the complex coupling and transmission processes of multi-energy-quality flows, resulting in low energy scheduling accuracy and making it difficult to achieve the efficient operation of the system.

[0006] Second, there is a lack of an effective collaborative regulation mechanism, and it is impossible to fully achieve the efficient coordination of each link within the system; specifically, most metallurgy systems still adopt isolated resource scheduling methods, lacking collaborative regulation means on multiple time scales and multiple links. Especially between the green hydrogen production, storage, transportation, and metallurgy links, flexible adjustment and dynamic response cannot be achieved, resulting in the overall operation efficiency and stability of the system being affected under load fluctuations or unstable renewable energy output;

[0007] Thirdly, in the face of uncertain energy supply, the existing optimization methods lack robustness and are difficult to meet the comprehensive requirements of system security, economy, and flexible operation. Specifically, current optimization methods mostly focus on single objectives such as economy or energy efficiency, ignoring the uncertain risks in the system, especially the impact of the volatility of renewable energy supply on the system. In addition, traditional optimization methods are difficult to handle complex multi-objective and multi-constraint problems and lack a robust optimization mechanism for uncertain scenarios, resulting in poor adaptability and low security of the system when dealing with different operating scenarios.

[0008] These problems lead to low system energy efficiency and poor carbon emission reduction effects, and breakthrough optimization methods are urgently needed to solve them. Summary of the Invention

[0009] Aiming at the above deficiencies in the prior art, the optimization method for the integrated green hydrogen metallurgy energy system provided by the present invention solves the problems of uncertain multi-energy-quality flow modeling, low system regulation rate, and difficulty in dealing with uncertainties in the prior art.

[0010] To achieve the above invention objectives, the technical solution adopted by the present invention is as follows: An optimization method for an integrated green hydrogen metallurgy energy system, including:

[0011] Aiming at the multi-energy-quality flow characteristics in the integrated green hydrogen metallurgy energy system, a unified multi-energy-quality flow network matrix model of heterogeneous energy flow and material flow based on differential dynamic equations is constructed, and the multi-energy-quality flow distribution is calculated according to it;

[0012] Analyze the multi-time-scale characteristics of flexible adjustable resources in the integrated green hydrogen metallurgy energy system, construct an extended resource-task network model considering multi-energy-quality flow distribution, and combine a multi-model predictive control mechanism to carry out coordinated regulation of multiple links of energy and quality flow;

[0013] Based on the uncertain variables in the integrated green hydrogen metallurgy energy system, a robust optimization method is used to construct a multi-objective optimal operation model and randomly generate a large number of operation scenarios. Through a skew decision tree model, dynamic quantitative analysis of energy efficiency-flexibility-risk is carried out on the operation scenario data, and a multi-market adaptive trading auxiliary decision-making system based on a two-layer optimization model is constructed according to the results of the energy efficiency-flexibility-risk dynamic quantitative analysis. Through its output of the scheduling and trading strategies of energy blocks and carbon blocks, the efficient operation of the system is realized; the energy blocks and carbon blocks respectively represent the physical energy transmission and carbon emission quotas in the integrated green hydrogen metallurgy energy system.

[0014] During the system optimization process, the multi-energy flow distribution calculated by the multi-energy flow network matrix model provides the required multi-energy flow distribution state for constructing the extended resource-task network model; the extended resource-task network model serves as a constraint condition for constructing the multi-objective optimization operation model; the energy flow regulation strategy obtained by the multi-model predictive control mechanism serves as the production regulation strategy required for constructing the multi-energy flow network matrix model and generating a large number of operation scenarios; the scheduling and trading strategies of energy blocks and carbon blocks output by the multi-market adaptive trading auxiliary decision-making system provide optimized decision-making information for the multi-model predictive control mechanism to output the energy flow regulation strategy;

[0015] Through the system optimization process, the second-level multi-energy flow distribution calculation, the minute-level multi-link coordination regulation of energy flow, and the hour-level efficient operation of the system are realized.

[0016] Furthermore, the method for constructing a multi-energy flow network matrix model that unifies heterogeneous energy flow and material flow based on differential dynamic equations is specifically as follows:

[0017] S1. Analyze the multi-energy flow characteristics in the integrated energy system of green hydrogen metallurgy, classify the physical quantities involved into intensive quantities and extensive quantities, and then construct a unified dynamic equation for multi-energy flow based on differential dynamic equations;

[0018] The unified dynamic equation for multi-energy flow includes a unified dynamic equation for multi-energy flow transmission and a unified dynamic equation for multi-energy flow coupling and conversion;

[0019] S2. Perform static algebraic analysis based on Laplace transform and external port equivalence based on distributed parameter approximation on the constructed unified dynamic equation for multi-energy flow in sequence to construct a unified model for multi-energy flow;

[0020] The unified model for multi-energy flow includes a unified model for multi-energy flow transmission obtained by performing transmission static algebraic analysis and branch external port equivalence in sequence, and a unified model for multi-energy flow coupling and conversion obtained by performing energy conversion static algebraic analysis and coupling node external port equivalence in sequence;

[0021] S3. Construct a full-network dynamic characteristic model for multi-energy flow according to the unified model for multi-energy flow;

[0022] S4. Reduce the full-network dynamic characteristic model of multi-energy flow to a boundary equivalent model that only includes key boundary nodes, and then construct its corresponding unified Jacobian matrix as the multi-energy flow network matrix model.

[0023] Furthermore, in step S1, in the constructed unified dynamic equation for multi-energy flow, the left side of the equal sign is represented by the spatial differential of intensive quantities and extensive quantities, and the right side of the equal sign is represented by the time differential of intensive quantities and extensive quantities and related terms, and it is expressed as:

[0024]

[0025] In the formula, ψ represents the generalized intensive quantity, ζ represents the extensive quantity, and α1, α2, β1, and β2 all represent branch parameters;

[0026] The specific steps of step S4 are as follows:

[0027] According to the importance and physical properties of network nodes, they are divided into key boundary nodes and non-key nodes. The injection values of the intensive quantity and extensive quantity of the nodes involved in the whole-network dynamic characteristic model of the multi-energy mass flow network are subjected to matrix operations according to the divided node types, a block matrix is constructed, and Gaussian elimination is performed on the constructed block matrix to obtain a boundary equivalent model containing only key boundary nodes, and then a corresponding unified Jacobian matrix is constructed as the matrix model of the multi-energy mass flow network;

[0028] Among them, the constructed block matrix is expressed as:

[0029]

[0030] In the formula, Y BB , Y BI , Y IB , Y II represent the block matrix of Y, Y represents the admittance matrix of the energy node, ψ B (s) and ψ I (s) represent two sets obtained by dividing the node intensive quantity according to the node type, and ζ B (s) and ζ I (s) represent two sets obtained by dividing the extensive quantity injection value according to the node type;

[0031] The constructed boundary equivalent model is expressed as:

[0032]

[0033] The constructed unified Jacobian matrix is expressed as:

[0034]

[0035] In the formula, represents the characterization of the extensive quantity and intensive quantity of process J of the integrated green hydrogen metallurgy energy system, and the subscripts m and n represent the parameter indices in the integrated green hydrogen metallurgy energy system.

[0036] Furthermore, the method for constructing an extended resource-task network model considering the multi-energy mass flow distribution is specifically as follows:

[0037] X1. Analyze the regulation response characteristics of the energy supply, demand, energy conversion, and storage links in the integrated green hydrogen metallurgy energy system at different time scales, construct a regulation response time scale matrix, and analyze the cross-link regulation characteristics in the multi-energy quality interaction based on it to construct an equivalent model of the regulation external characteristics based on heterogeneous links;

[0038] X2. Based on the equivalent models of the regulation external characteristics corresponding to the different regulation characteristics of various devices, conduct dynamic correlation analysis, analyze the influence of different production tasks on the energy quality flow distribution, and establish an extended resource-task network model that characterizes the relationship between production tasks and the supply-demand distribution of multi-energy quality flows.

[0039] Further, the step X2 includes the following sub-steps:

[0040] X21. Classify the production tasks in the integrated green hydrogen metallurgy energy system according to production demands, determine the demand characteristics of energy quality flows for various production tasks at different time periods, fit their historical data, establish dynamic demand curves for various production tasks, and then produce multiple correlation models for different production task types;

[0041] X22. Model the energy quality demand characteristics of each production process of each production task in the integrated green hydrogen metallurgy energy system through dynamic programming or optimization algorithms, and adjust the execution order and energy quality flow distribution of the production processes of the production tasks in real time to optimize the coordinated scheduling between production processes, and construct an energy quality flow coordinated regulation model between processes;

[0042] The energy quality flow coordinated regulation model between processes is subject to the time scheduling cost between production processes, the dependency relationship between production processes, and resource constraints;

[0043] X23. According to the constructed production task dynamic correlation model and the energy quality flow coordinated regulation model between processes, and introducing the dynamic characteristics of time, space, and energy quality flow, construct an extended resource-task network model;

[0044] The extended resource-task network model is a model that dynamically adjusts the resource supply and task demand in the integrated green hydrogen metallurgy energy system according to time series data.

[0045] Further, the method for coordinating and regulating the energy quality flow based on the multi-model predictive control mechanism to output the energy quality flow regulation strategy is specifically as follows:

[0046] Based on the task-resource allocation result obtained from the extended resource-task network model, predict the random variables involved in the production process at future times and input them into the multi-model predictive control mechanism to output the energy quality flow regulation strategy for the current working condition;

[0047] The multi-model predictive control mechanism includes a multi-model prediction mechanism based on local model combination and a multi-model prediction mechanism based on multi-controller combination;

[0048] The multi-model prediction mechanism based on local model combination means:

[0049] Construct local models for predicting the energy and mass flow distribution under different working conditions, and based on the conditional model switching mechanism, switch the optimal local model according to the operating state of the integrated green hydrogen metallurgy energy system to perform corresponding energy and mass flow distribution predictions;

[0050] The multi-model prediction mechanism based on multi-controller combination means:

[0051] Based on the energy and mass flow distribution strategy predicted by the multi-model prediction mechanism of local model combination, design corresponding independent controllers according to different energy and mass flow characteristics, and for different working conditions and energy and mass flow regulation requirements, adopt a collaborative mechanism based on constraint optimization, introduce a global objective function to optimize the regulation objectives of each independent controller, and obtain the overall optimal energy and mass flow regulation strategy of the system; among them, the outputs of each independent controller are mutually related;

[0052] The basic model of the multi-model predictive control mechanism is expressed as:

[0053]

[0054] In the formula, x(t + k|t) represents the predicted value of state x at time t + k, u(t + k|t) represents the predicted value of control input u at time t + k, Q and R are the weight matrices of state and control respectively, u(t) represents the control input function, and N represents the number of prediction or time steps in the optimization process.

[0055] Furthermore, based on the uncertainty variables in the integrated green hydrogen metallurgy energy system, a robust optimization method is used to construct a multi-objective optimization operation model to randomly generate a large number of operation scenarios. The method for dynamically quantifying energy efficiency - flexibility - risk of operation scenario data through an oblique decision tree model is specifically as follows:

[0056] T1. Characterize the uncertainty variables in the integrated green hydrogen metallurgy energy system as an uncertainty set through probability distribution fitting, construct a multi-objective optimization operation model for random production simulation using the robust optimization method according to the uncertainty set, and use the continuous convex hull approximation strategy to transform the multi-objective optimization operation model with non-linear constraints into a linear model;

[0057] The uncertainty variables include power supply fluctuations and market price fluctuations; the constraint condition of the multi-objective optimization operation model is an extended resource-task network model considering the multi-energy and mass flow distribution in the integrated green hydrogen metallurgy energy system;

[0058] T2. Randomly generate the uncertainty variables included in different operation scenarios, and take maximizing the operation efficiency of the system and minimizing the risk as the optimization goal of the operation scenario, and then generate a large number of operation scenarios;

[0059] T3. Analyze the generated operation scenarios, extract the main features affecting the key indicators of system operation, construct an oblique decision tree based on multi-index sparse weights, and regularize its sparse weights, and then obtain an oblique decision tree model;

[0060] The key indicators include energy efficiency, flexibility and risk;

[0061] T4. Use the oblique decision tree model to extract the association rules among energy efficiency, flexibility and risk in the operation scenario data, and realize the dynamic quantitative analysis of energy efficiency - flexibility - risk.

[0062] Furthermore, in the step T1, the multi-objective optimization operation model for realizing random production simulation is expressed as:

[0063]

[0064] In the formula, x is the decision variable of the system, ξ is the uncertainty variable, f(x, ξ) corresponds to the profit and loss function and optimization goal of the system, θ represents the robustness parameter, which is used to control the trade-off between the expectation and conservatism of the system, represents the expectation function based on , represents the uncertainty set, P ξ represents the probability distribution of the uncertainty variable ξ, represents the reference distribution fitted by the operation historical data;

[0065] In the step T2, the optimization goal of the operation scenario is expressed as:

[0066]

[0067] In the formula, x s represents the decision variable of the operation scenario s, f(x s , ξ s , η s ) represents the operation performance of the system under the operation scenario s, R(x s , ξ s , η s ) represents the system risk, η s and ξ s respectively represent the power supply fluctuation and market price fluctuation in the operation scenario s, λ represents the weight coefficient for balancing the system performance and risk, s ∈ S, and S represents the operation scenario set.

[0068] Furthermore, the two-layer optimization model constructed based on the results of the dynamic quantitative analysis of energy efficiency - flexibility - risk includes an upper-layer model and a lower-layer model;

[0069] The optimization objective of the upper-layer model is to minimize the energy cost and carbon emission cost of the system while meeting the production requirements; the optimization objective of the lower-layer model is to purchase the required energy and carbon emission allowances at the lowest price in the energy market and carbon market according to the resource scheduling requirements of the upper-layer model, or sell the surplus energy and carbon allowances to obtain profits.

[0070] The objective function of the upper-layer model is:

[0071]

[0072] Among them, C energy (P) represents the cost of the energy block, represents the cost of the carbon block, P is the energy consumption of the system, is the carbon emission;

[0073] The constraint conditions of the upper-layer model include energy balance constraint and carbon emission constraint, which are respectively expressed as:

[0074] P generation +P import =P demand +P storage

[0075]

[0076] In the formula, P generation represents the local power generation, P import represents the energy imported from the market, P demand and P storage respectively represent the demand and the energy storage capacity, is the carbon emission allowance purchased by the system;

[0077] The objective function of the lower-layer model is expressed as:

[0078]

[0079] In the formula, λ energy (t) represents the price of the energy market at the t-th time period, λ carbon (t) is the price of the carbon market, P import (t) is the energy purchased from the market at the t-th time period, E buy (t) and E sell (t) are the carbon emission allowances purchased and sold at the t-th time period respectively;

[0080] The constraint conditions of the lower-layer model include market supply-demand balance constraint and carbon market quota constraint, which are respectively expressed as:

[0081] P import (t) + P local_generation (t) = P demand (t)

[0082]

[0083] In the formula, P import (t) represents the energy imported from the market in the t-th period, P local_generation (t) represents the energy locally generated by the system in the t-th period, P demand (t) represents the demand in the t-th period, represents the carbon dioxide emission at time t, represents the capital cost or limit of carbon dioxide emission at time t.

[0084] Furthermore, a multi-market adaptive trading auxiliary decision-making system based on a two-layer optimization model is constructed. The method for scheduling and trading strategies of the output energy block and carbon block is specifically as follows:

[0085] G1. According to the results of dynamic quantitative analysis of energy efficiency - flexibility - risk, conduct time-series coupling analysis and confidence interval analysis on the energy block and carbon block, and quantitatively infer the coupling characteristics of the energy block and carbon block;

[0086] G2. Based on the inferred coupling characteristics of the energy block and carbon block, mine the optimal bidding strategies of the energy block and carbon block in market trading, and combine the constructed two-layer optimization model to form a power trading agent, a carbon emission right trading agent, and a green hydrogen trading agent;

[0087] G3. Construct an adaptive trading auxiliary decision-making system for multi-agent reinforcement learning based on the power trading agent, the carbon emission right trading agent, and the green hydrogen trading agent, continuously learn and optimize the trading strategies of the energy block and carbon block to adapt to different market changes, and output the scheduling and trading strategies of the energy block and carbon block;

[0088] The optimization goal of the adaptive trading auxiliary decision-making system is to maximize the cumulative return of each agent through the scheduling and trading strategies of the output energy block and carbon block.

[0089] The beneficial effects of the present invention are:

[0090] (1) The present invention proposes a unified mathematical model of heterogeneous energy flow and material flow based on differential dynamics to solve the problem of large differences in the transmission characteristics of different quality flows. Combining with the distributed parameter generalized transmission model, the time-domain dynamic problem is transformed into an algebraic problem, simplifying the complex multi-energy and mass flow dynamic calculation. And through the equivalent modeling method, the modeling challenges of heterogeneous branches and nodes are solved, forming a standardized matrix modeling paradigm.

[0091] (2) Based on the multi-time scale regulation characteristics, the present invention proposes a cross-link multi-energy and mass flow collaborative regulation method to optimize the allocation of system resources. By expanding the resource-task network model to analyze the dynamic relationship between production tasks and multi-energy and mass flow distribution, the response ability of the system in multi-energy and mass flow interaction is enhanced. Combining with the multi-model predictive control strategy, the control accuracy of the system under multi-variable disturbances is improved.

[0092] (3) In the present invention, through the power supply and market uncertainty characterization method, combined with the distributionally robust optimization strategy, an optimization method for balancing system security, economy and flexibility is proposed. The continuous convex hull approximation strategy is used to optimize the non-linear constraint problem, and through multi-agent reinforcement learning, adaptive trading decisions are realized, optimizing the market trading efficiency of the system.

[0093] (4) The present invention innovatively introduces the multi-agent reinforcement learning algorithm to optimize the time-series coupling characteristics of energy blocks and carbon blocks in multi-market trading, and proposes an adaptive trading auxiliary decision-making method, which can adjust trading strategies in real time in a dynamic market environment, improve the adaptability of market trading and the accuracy of decision-making, and support the efficient trading and resource allocation of the green hydrogen metallurgy system. Brief Description of the Drawings

[0094] Figure 1 It is a principle block diagram of the optimization of the green hydrogen metallurgy integrated energy system provided by the present invention. Detailed Embodiments

[0095] The following describes the detailed embodiments of the present invention to facilitate those skilled in the art of the present technology to understand the present invention. However, it should be clear that the present invention is not limited to the scope of the detailed embodiments. For those of ordinary skill in the art of the present technology, as long as various changes are within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are within the scope of protection.

[0096] The embodiment of the present invention provides an optimization method for a green hydrogen metallurgy integrated energy system, as Figure 1 shown, including:

[0097] Regarding the characteristics of multi - energy - quality flows in the integrated energy system of green hydrogen metallurgy, a multi - energy - quality flow network matrix model that unifies heterogeneous energy flows and material flows based on differential kinetic equations is constructed, and multi - energy - quality flow distribution calculations are performed according to it;

[0098] Analyze the multi - time - scale characteristics of flexible adjustable resources in the integrated energy system of green hydrogen metallurgy, construct an extended resource - task network model considering multi - energy - quality flow distribution, and combine a multi - model predictive control mechanism for collaborative regulation of energy - quality flows in multiple links;

[0099] Based on the uncertain variables in the integrated energy system of green hydrogen metallurgy, a multi - objective optimization operation model is constructed using robust optimization methods, and a large number of operation scenarios are randomly generated. Through a skew decision - tree model, dynamic quantification analysis of energy efficiency - flexibility - risk is carried out on the operation scenario data, and a multi - market adaptive trading auxiliary decision - making system based on a two - layer optimization model is constructed according to the results of the energy efficiency - flexibility - risk dynamic quantification analysis. By outputting the scheduling and trading strategies of energy blocks and carbon blocks, the efficient operation of the system is realized; the energy blocks and carbon blocks respectively represent the physical energy transmission and carbon emission quotas in the integrated energy system of green hydrogen metallurgy;

[0100] During the system optimization process, the multi - energy - quality flow distribution calculated by the multi - energy - quality flow network matrix model provides the required multi - energy - quality flow distribution state for constructing the extended resource - task network model; the extended resource - task network model serves as a constraint condition for constructing the multi - objective optimization operation model; the energy - quality flow regulation strategy obtained by the multi - model predictive control mechanism serves as the production regulation strategy required for constructing the multi - energy - quality flow network matrix model and generating a large number of operation scenarios; the scheduling and trading strategies of energy blocks and carbon blocks output by the multi - market adaptive trading auxiliary decision - making system provide optimized decision - making information for the multi - model predictive control mechanism to output the energy - quality flow regulation strategy;

[0101] Through the system optimization process, second - level multi - energy - quality flow distribution calculations, minute - level coordinated regulation of energy - quality flows in multiple links, and hour - level efficient operation of the system are achieved.

[0102] The method for constructing a multi - energy - quality flow network matrix model that unifies heterogeneous energy flows and material flows based on differential kinetic equations in the embodiments of the present invention is specifically as follows:

[0103] S1. Analyze the characteristics of multi - energy - quality flows in the integrated energy system of green hydrogen metallurgy, classify the physical quantities involved into intensive quantities and extensive quantities, and then construct a unified kinetic equation for multi - energy - quality flows based on differential kinetic equations;

[0104] The unified kinetic equation for multi - energy - quality flows includes a unified kinetic equation for multi - energy - quality flow transmission and a unified kinetic equation for multi - energy - quality flow coupling and conversion;

[0105] S2. Conduct static algebraic analysis based on Laplace transform and external port equivalence based on distributed parameter approximation on the constructed unified dynamic equation of multi-energy mass flow in sequence to construct a unified multi-energy mass flow model;

[0106] The unified multi-energy mass flow model includes a unified multi-energy mass flow transmission model obtained by conducting transmission static algebraic analysis and branch external port equivalence in sequence, and a unified multi-energy mass flow coupling and conversion model obtained by conducting energy-mass conversion static algebraic analysis and coupling node external port equivalence in sequence;

[0107] S3. Construct a full-network dynamic characteristic model of the multi-energy mass flow network according to the unified multi-energy mass flow model;

[0108] S4. Reduce the full-network dynamic characteristic model of the multi-energy mass flow network to a boundary equivalent model that only includes key boundary nodes, and then construct its corresponding unified Jacobian matrix as the matrix model of the multi-energy mass flow network.

[0109] In step S1 of this embodiment, the integrated green hydrogen metallurgy energy system involves various heterogeneous energies and material flows such as electricity, hydrogen, and heat. Each energy-mass flow has different physical and dynamic characteristics during the transmission process. For example, the power flow takes voltage and current as basic parameters, while the hydrogen flow depends on pressure and mass flow rate. In order to accurately describe these differential fluid characteristics, a multi-energy mass flow dynamic modeling method based on differential dynamics is proposed in this embodiment.

[0110] Specifically, in this embodiment, the transmission dynamic characteristics and coupling and conversion dynamic characteristics of multi-energy mass flow in the integrated green hydrogen metallurgy energy system are analyzed. Among them, the transmission characteristic model of multi-energy mass flow includes current (carbon) flow equation, thermal (carbon) flow equation, hydrogen (carbon) flow equation, and material flow equation; the coupling and conversion process model of multi-energy mass flow includes electro-thermal conversion process model, electro-hydrogen conversion process model, and material conversion process model.

[0111] In step S1 of this embodiment, the physical quantities in the above transmission characteristic model and conversion process model are classified into intensive quantities and extensive quantities. In the constructed unified dynamic equation of multi-energy mass flow, the left side of the equal sign is represented by the spatial differential of intensive quantities and extensive quantities, and the right side of the equal sign is represented by the time differential of intensive quantities and extensive quantities and related terms, which is expressed as:

[0112]

[0113] In the formula, ψ represents the generalized intensive quantity, ζ represents the extensive quantity, and α1, α2, β1, and β2 all represent branch parameters.

[0114] Specifically, in the unified kinetic equation of multi-energy mass flow constructed above, the intensive quantity refers to the physical quantity that does not change with the system scale or the amount of matter, such as the voltage U in the power grid, the temperature difference T in the thermal grid, and the pressure change Δπ in the gas grid; the extensive quantity changes proportionally with the system scale or the amount of matter, including the current I in the power grid, the heat flow power φ in the thermal grid, and the flow change Δf in the gas grid.

[0115] In step S2 of this embodiment, during the static algebraic analysis based on Laplace transform, the research on the green hydrogen metallurgy multi-energy system mainly focuses on the mutual influence caused by "changes" between systems, so it focuses on the zero-state response of the system. Since the generalized energy flow equation is a linear equation, the influence of the initial state of the system in this embodiment can be processed by the "superposition theorem". When performing the transmission static algebraic analysis based on Laplace transform on the unified kinetic equation of multi-energy mass flow transmission, and when performing the energy-mass conversion static algebraic analysis based on Laplace transform on the unified kinetic equation of multi-energy mass flow coupling conversion, they are both expressed in the Laplace domain as:

[0116]

[0117] In the formula, ψ(x, s) = L(ψ(x, t)), ζ(x, s) = L(ζ(x, t)), L(·) represents the Laplace transform operator, and the complex number s represents the Laplace transform parameter.

[0118] In this embodiment, through the above Laplace transform, the distributed parameter circuit in the time domain can be simplified to a distributed parameter circuit in the Laplace domain that only contains spatial differentials, and resistors, inductors, and capacitors are uniformly represented. However, the distributed parameter circuit is still difficult to analyze directly, so it needs to be further simplified or approximated to a lumped parameter circuit, so as to analyze the pipeline branches in the multi-energy network as a whole. This is similar to the approximate equivalent method of using π-shaped and T-shaped equivalent circuits in the power system; based on this, in this embodiment, the external port equivalent of the unified kinetic equation of multi-energy mass flow transmission after Laplace transform is performed based on distributed parameter approximation, and the external port equivalent of the coupling node of the unified kinetic equation of multi-energy mass flow coupling conversion after Laplace transform is performed based on distributed parameter approximation. The obtained unified model of multi-energy mass flow and the unified model of multi-energy mass flow coupling conversion are the same in form and are both expressed as:

[0119]

[0120]

[0121] In the formula, and ε represent the approximation operator, a and b represent the integration constants determined by the boundary conditions.

[0122] Step S4 in this embodiment is specifically as follows:

[0123] According to the importance and physical attributes of network nodes, they are divided into key boundary nodes and non-key nodes. The intensive and extensive quantity injection values of the nodes involved in the whole-network dynamic characteristic model of the multi-energy mass flow network are subjected to matrix operations according to the divided node types to construct a block matrix, and Gaussian elimination is performed on the constructed block matrix to obtain a boundary equivalent model containing only key boundary nodes, and then a corresponding unified Jacobian matrix is constructed as the matrix model of the multi-energy mass flow network.

[0124] Specifically, in this embodiment, for key boundary nodes, the changes in the extensive and intensive quantities of such nodes are crucial to this system or other systems coupled with it; for example, the busbars connecting tie lines in the power system, the nodes where gas turbines are located in the gas network, etc.; for non-key nodes, such nodes are system nodes other than key boundary nodes and can be further divided in combination with specific system characteristics and application requirements; for example, divided according to whether they are connected to key nodes, or whether the intensive / extensive quantities are constant, etc.

[0125] In this embodiment, the constructed block matrix is expressed as:

[0126]

[0127] In the formula, Y BB , Y BI , Y IB , Y II represent the block matrix of Y, Y represents the admittance matrix of energy nodes, ψ B (s) and ψ I (s) represent two sets obtained by dividing the node intensive quantities according to the node types, and ζ B (s) and ζ I (s) represent two sets obtained by dividing the extensive quantity injection values according to the node types;

[0128] In this embodiment, the constructed boundary equivalent model is expressed as:

[0129]

[0130] In this embodiment, the constructed unified Jacobian matrix is expressed as:

[0131]

[0132] In the formula, represents the characterization of the extensive and intensive quantities of process J in the integrated green hydrogen metallurgy energy system, and the subscripts m and n represent the parameter indices in the integrated green hydrogen metallurgy energy system.

[0133] In this embodiment, the above unified Jacobian matrix simplifies the solution of complex dynamic problems as a standardized matrix model, realizes the high-efficiency computing ability of the system through fast algebraic operations, and can adapt to energy-quality flow networks of different scales and complexities, greatly improving the computing efficiency of system operation.

[0134] In the embodiment of the present invention, the method for constructing an extended resource-task network model considering multi-energy-quality flow distribution is specifically as follows:

[0135] X1. Analyze the regulation response characteristics of the energy supply, demand, energy conversion, and storage links in the integrated green hydrogen metallurgy energy system at different time scales, construct a regulation response time scale matrix, and analyze the cross-link regulation characteristics in multi-energy-quality interaction based on it to construct an equivalent model of the regulation external characteristics based on heterogeneous links;

[0136] X2. Based on the equivalent models of the regulation external characteristics corresponding to the different regulation characteristics of various devices, perform dynamic correlation analysis, analyze the influence of different production tasks on the energy-quality flow distribution, and establish an extended resource-task network model representing the correlation between production tasks and the supply and demand distribution of multi-energy-quality flows.

[0137] In step X1 of this embodiment, the operation of the integrated green hydrogen metallurgy energy system involves supply, demand, energy conversion, and storage, and these links exhibit different dynamic regulation characteristics at different time scales. To achieve multi-scale coordinated control, the regulation response characteristics of each link are analyzed in this embodiment, and a multi-time scale modeling framework is established. Exemplarily, the above supply, demand, energy conversion, and storage devices include supply, demand, energy conversion, and storage, etc.

[0138] In this embodiment, the supply-demand dynamic model is described by the following equation:

[0139]

[0140] Where, represents the state change of the system at time t, P d (t) is the demand power, P s (t) is the supply power, P st (t) is the power output of the energy storage system. Through multi-time scale dynamic regulation, ensure the supply-demand balance of the system and the optimal regulation of energy storage and release in different time periods.

[0141] In the integrated green hydrogen metallurgy energy system, each link not only has its own regulation characteristics, but also needs to consider the influence of the mutual conversion and interaction between different energy qualities (electricity, hydrogen, heat) on the overall scheduling. Exemplarily, in the process of electrolytic hydrogen production, the conversion efficiency of electric energy to hydrogen energy is not only restricted by the electrolyzer itself, but also affected by the power supply fluctuations of the upstream power grid.

[0142] Further, in step X1 of this embodiment, the method for analyzing the cross-link regulation characteristics in the multi-energy quality interaction is specifically as follows:

[0143] Analyze the impact of the mutual conversion and interaction between different energy qualities on the overall scheduling of the green hydrogen metallurgy integrated energy system by constructing an energy quality flow coupling model and analyzing the time-delay effect in the cross-link energy quality interaction process; among them, the time-delay effect includes cross-link energy quality transmission time-delay and conversion time-delay.

[0144] After analyzing the cross-link regulation characteristics in the multi-energy quality interaction, since the nonlinearity and uncertainty of various energy equipment in the actual system are difficult to be fully described by traditional physical models, it is necessary to introduce deep learning technology to assist in modeling. The key to this step is to construct a high-precision equivalent model of the regulation external characteristics through the analysis of historical data.

[0145] Specifically, the method for constructing a high-precision equivalent model of the regulation external characteristics is as follows: for the different regulation characteristic data of various equipment, select the corresponding deep neural network (such as a feedforward neural network (FFNN) or a long short-term memory network), set the equipment control variable as the network input (such as input electric power), set the regulation result as the network output (such as hydrogen production or energy efficiency), train the corresponding deep neural network according to the historical operation data and perform dynamic updates to obtain the regulation external characteristic models corresponding to the different regulation characteristics of various equipment.

[0146] Step X2 of this embodiment includes the following sub-steps:

[0147] X21. Classify the production tasks in the green hydrogen metallurgy integrated energy system according to the production requirements, determine the demand characteristics of the energy quality flow for each type of production task at different time periods, fit its historical data, establish a dynamic demand curve for each type of production task, and then generate multiple correlation models for different production task types;

[0148] Exemplarily, in the green hydrogen metallurgy integrated energy system, tasks such as hydrogen production, electric energy storage, hydrogen storage, and shaft furnace steelmaking have different energy quality flow demand types and intensities; by classifying the tasks, clarify the demand characteristics of the energy quality flow for each type of task at different time periods;

[0149] In the above process, the distribution of the energy quality flow can be regarded as a function of time and task progress. By fitting the historical data, establish a dynamic demand curve for the task, and generate multiple correlation models for different task types to ensure that the distribution of the energy quality flow meets the real-time production requirements;

[0150] X22. Model the energy and quality demand characteristics of each production process of each production task in the green hydrogen metallurgy integrated energy system through dynamic programming or optimization algorithms, and adjust the execution order and energy and quality flow distribution of the production processes of the production tasks in real time to optimize the collaborative scheduling between production processes, thereby constructing an energy and quality flow collaborative regulation model between processes; the energy and quality flow collaborative regulation model between processes is subject to the time scheduling cost between production processes, the dependency relationship between production processes, and resource constraints.

[0151] Exemplarily, the hydrogen and electricity demands of the shaft furnace during startup and operation exhibit non-linear characteristics. A large amount of energy and quality may be consumed during the startup phase, while the demand is relatively low during stable operation; similarly, the energy and quality demands of the electrolyzer also vary at different stages.

[0152] X23. Based on the constructed dynamic association model of production tasks and the energy and quality flow collaborative regulation model between processes, and introducing the dynamic characteristics of time, space, and energy and quality flow, construct an extended resource-task network model.

[0153] The extended resource-task network model is a model that dynamically adjusts the resource supply and task demand in the green hydrogen metallurgy integrated energy system according to time series data.

[0154] In this embodiment, traditional resource-task network models usually assume that resources are static and independent. However, in a multi-energy and quality flow system, the interaction between resources and tasks is dynamic and interdependent. To adapt to this complexity, it is necessary to extend the traditional resource-task network model. In this embodiment, the dynamic characteristics of time, space, and energy and quality flow are introduced to construct an extended resource-task network model. Based on this, the extended resource-task network model in this embodiment is a model that dynamically adjusts the resource supply and task demand in the green hydrogen metallurgy integrated energy system according to time series data.

[0155] In this embodiment, the time and space distributions of different energy and quality flows (such as electricity, hydrogen, and heat energy) are crucial for the overall operation of the system; in a specific example of this embodiment, during the electrolytic hydrogen production process, the electricity supply is closely related to the hydrogen production demand. It is necessary to define "supply-demand" nodes in the network model and introduce time-varying functions to describe the relationship between the two. Assume that the distributions of multiple energy and quality flows (such as electricity E elec , hydrogen ) in time and space are represented by functions h(t, x) and k(t, x) respectively. The extended resource-task network model can be defined as:

[0156] E elec (t, x) = h(t, x)(10)

[0157]

[0158] where \(t\) is time, \(x\) is the spatial position, and the functions \(h\) and \(k\) describe the dynamic distributions of different energy-mass flows in the space-time dimension.

[0159] In this embodiment, when the above-mentioned extended resource-task network model performs collaborative regulation on resources involved in multiple production tasks, it conducts multi-correlation processing on them, establishes an optimization model with constraint conditions, and realizes the collaborative matching of multi-energy-mass supply to the production task requirements; among them, the constraint conditions include resource supply capacity, dynamic allocation of energy-mass flow, and temporal dependence of production tasks.

[0160] In this embodiment, in the extended resource-task network model, each task node not only represents the execution progress of the task but also reflects the consumption of energy-mass flow; based on this, when the extended resource-task network model allocates resources-tasks, it uses a dynamic optimization algorithm to dynamically adjust the execution order of production tasks and the allocation strategy of energy-mass flow according to the current energy-mass flow distribution in the green hydrogen metallurgy integrated energy system to ensure the optimal efficiency and stability of the system.

[0161] In this embodiment, the dynamic optimization algorithm in the above process can be a heuristic algorithm or a large-scale linear programming method; exemplarily, the above heuristic algorithm includes genetic algorithm and particle swarm optimization algorithm).

[0162] In this embodiment, in a complex multi-energy-mass flow system, due to the volatility of energy-mass flow and the uncertainty of system demand, traditional regulation strategies are difficult to achieve efficient production regulation. Therefore, it is necessary to adopt a multi-model predictive control (MPC) strategy to achieve real-time regulation of system operation. In this embodiment, prediction models of multiple random variables are designed, and production regulation is carried out through a multi-model combination method to effectively cope with system complexity and uncertainty.

[0163] Specifically, the method for outputting an energy-mass flow regulation strategy based on the multi-model predictive control mechanism in this embodiment is as follows:

[0164] Based on the task-resource allocation result obtained from the extended resource-task network model, predict the random variables involved in the production process at future moments and input them into the multi-model predictive control mechanism to output an energy-mass flow regulation strategy for the current working condition; the multi-model predictive control mechanism includes a multi-model predictive mechanism based on local model combination and a multi-model predictive mechanism based on multi-controller combination. Among them, when predicting random variables, time series analysis is performed on each random variable to capture the fluctuation characteristics in its historical data. Classic time series models such as autoregressive integrated moving average model (ARIMA) and generalized autoregressive conditional heteroskedasticity model (GARCH) can be used to fit the fluctuation laws of each random variable at different time scales.

[0165] In this embodiment, the multi-model prediction mechanism based on local model combination means that:

[0166] Construct local models for predicting the energy-quality flow distribution under different working conditions, and based on the conditional model switching mechanism, switch the optimal local model according to the operating state of the integrated green hydrogen metallurgy energy system to perform corresponding energy-quality flow distribution prediction.

[0167] Specifically, in this embodiment, local models are constructed for different operating stages of the system. Exemplarily, in the case of low load and high load, the energy-quality flow distribution rules and response characteristics of the system are different. For these different working conditions, local models based on linear systems, non-linear models or machine learning models (such as long short-term memory network LSTM or support vector machine SVM, etc.) can be established respectively.

[0168] In this embodiment, introducing the conditional model switching mechanism into the above multi-model prediction mechanism based on local models can select appropriate local models under different system operating states. For example, when the system load fluctuates greatly, it can be switched to a local model suitable for high-fluctuation working conditions, while when the system operates smoothly, a simple linear model can be selected. The model switching mechanism can be implemented by setting thresholds, state observers or dynamic discrimination methods based on real-time data.

[0169] In this embodiment, the multi-model prediction mechanism based on multi-controller combination means that:

[0170] Based on the energy-quality flow distribution strategy predicted by the multi-model prediction mechanism of local model combination, independent controllers are designed according to different energy-quality flow characteristics, and for different working conditions and energy-quality flow regulation requirements, a collaborative mechanism based on constraint optimization is adopted to introduce a global objective function to optimize the regulation objectives of each independent controller, and obtain the overall optimal energy-quality flow regulation strategy of the system; among them, the outputs of each independent controller are interrelated.

[0171] In this embodiment, introducing the conditional model switching mechanism into the above multi-model prediction mechanism based on local models can select appropriate local models under different system operating states. For example, when the system load fluctuates greatly, it can be switched to a local model suitable for high-fluctuation working conditions, while when the system operates smoothly, a simple linear model can be selected. The model switching mechanism can be implemented by setting thresholds, state observers or dynamic discrimination methods based on real-time data.

[0172] In this embodiment, the basic model of the above multi-model predictive control mechanism is expressed as:

[0173]

[0174] where \(x(t + k|t)\) represents the predicted value of state \(x\) at time \(t + k\), \(u(t + k|t)\) represents the predicted value of control input \(u\) at time \(t + k\), \(Q\) and \(R\) are the weight matrices of the state and control respectively, u(t) represents the control input function, and \(N\) represents the number of predictions or time steps of the optimization process.

[0175] The above model predicts future states by rolling prediction and dynamically adjusts the production plan, thereby improving the regulation accuracy and response speed of the system.

[0176] In the embodiment of the present invention, based on the uncertainty variables in the integrated green hydrogen metallurgy energy system, a robust optimization method is used to construct a multi-objective optimization operation model to randomly generate a large number of operation scenarios. The method for dynamically quantifying energy efficiency - flexibility - risk for the operation scenario data through an oblique decision tree model is as follows:

[0177] T1. Represent the uncertainty variables in the integrated green hydrogen metallurgy energy system as an uncertainty set through probability distribution fitting. According to the uncertainty set, use a robust optimization method to construct a multi-objective optimization operation model for realizing stochastic production simulation, and use the continuous convex hull approximation strategy to transform the multi-objective optimization operation model with non-linear constraints into a linear model;

[0178] The uncertainty variables include power supply fluctuations and market price fluctuations; the constraint condition of the multi-objective optimization operation model is an extended resource - task network model considering the multi-energy quality flow distribution in the integrated green hydrogen metallurgy energy system;

[0179] T2. Randomly generate the uncertainty variables included in different operation scenarios, and use maximizing the operation efficiency of the system and minimizing the risk as the optimization objective of the operation scenario, and then generate a large number of operation scenarios;

[0180] T3. Analyze the generated operation scenarios, extract the main characteristics affecting the key indicators of system operation, construct an oblique decision tree based on multi-index sparse weights, and regularize its sparse weights, and then obtain an oblique decision tree model;

[0181] The key indicators include energy efficiency, flexibility and risk;

[0182] T4. Use the oblique decision tree model to extract the association rules between energy efficiency, flexibility and risk in the operation scenario data, and realize the dynamic quantification analysis of energy efficiency - flexibility - risk.

[0183] In step T1 of this embodiment, the method for representing the uncertainty variables in the integrated green hydrogen metallurgy energy system as an uncertainty set through probability distribution fitting is as follows:

[0184] Statistically analyze the historical operation data in the integrated hydrogen metallurgy comprehensive energy system, fit the probability distributions of the uncertainty variables therein, and characterize the uncertainty variables as corresponding uncertainty sets based on the distances between different probability distributions. Exemplarily, using probability distribution fitting techniques to generate the probability intervals of power supply and market multiple uncertainty variables can effectively characterize various possible operating states and provide a data basis for subsequent optimal scheduling; further, the Wasserstein distance is used to measure the distances between different probability distributions.

[0185] In step T1 of this embodiment, in the process of implementing the multi-objective optimal operation model of stochastic production simulation, considering the impact of power supply and market uncertainties on system operation, the Distributionally Robust Optimization (DRO) method is introduced to achieve the optimization of stochastic production simulation. In this process, a robustness parameter is introduced through the optimization model, enabling the system to balance the expectability and conservatism in different power supply and market environments. Specifically, the optimization objectives cover the safety, economy, and flexibility of system operation. In a stochastic environment, distributionally robust optimization can not only provide a stable and reliable production strategy for the hydrogen metallurgy system but also minimize the operation risks to the greatest extent.

[0186] Specifically, in this embodiment, under multiple uncertainty conditions, the Distributionally Robust Optimization (DRO) method is used. Considering the stochastic production optimization problem of the hydrogen metallurgy system, the objective function can be expressed as the worst-case expectation under the uncertainty set:

[0187]

[0188] In the formula, x represents the decision variables of the system (e.g., power generation scheduling, market trading volume, etc.), ξ represents the uncertainty variables (such as power supply fluctuations, market prices, etc.), and f(x, ξ) is the profit and loss function of the system (including indicators such as economy, safety, and flexibility).

[0189] To further consider the safety and flexibility of system operation, the extended resource-task network of the integrated hydrogen metallurgy comprehensive energy system is introduced as a model constraint condition to enable the system to achieve an optimal effect under a certain robustness level, and a robustness parameter θ is introduced. The multi-objective optimal operation model for realizing stochastic production simulation is expressed as:

[0190]

[0191] In the formula, x is the decision variable of the system, ξ is the uncertainty variable, f(x, ξ) corresponds to the profit and loss function and optimization objective of the system, and θ represents the robustness parameter, which is used to control the trade-off between expectability and conservatism of the system. Denote based on Expected function Denotes the uncertainty set, P ξ Represents the probability distribution of the uncertainty variable ξ Represents the reference distribution fitted from the operation historical data

[0192] On this basis, for the non - linear constraint problem existing in the system, the continuous convex hull approximation method is adopted for optimization. Suppose the objective function f(x) in the original problem is non - linear and difficult to solve directly, and the problem can be simplified by finding its convex hull approximation

[0193] Suppose f(x) is a non - linear function, and its linear approximation at the point x k is as follows

[0194]

[0195] Through this linearization method, the original problem is approximated as a linear programming (LP) problem, so that a high - quality solution can be obtained with limited computing resources. During the optimization and solution process, this strategy can be used to improve the computing efficiency and ensure that the accuracy of the solution meets the operation requirements of the system

[0196] In step T2 of this embodiment, in order to comprehensively evaluate the operation performance of the green hydrogen metallurgy integrated energy system under different synchronous deterministic conditions, a large number of different operation scenarios are generated through stochastic production simulation. By simulating a large number of possible power supply and market environments, the energy efficiency, flexibility and risk characteristics of the system under various operation conditions can be captured. These scenario data not only provide a solid foundation for subsequent optimization and decision - making, but also provide a comprehensive risk assessment and flexibility analysis tool for system operation

[0197] Specifically, the power supply fluctuation ξ and the market price fluctuation η are set as uncertainty variables, and different scenario sets S are constructed. Each scenario s ∈ S contains variables (ξ s , η s ) generated by random sampling or Monte Carlo simulation. For each scenario, the optimization objective is to maximize the operation efficiency of the system while minimizing the risk; Based on this, in step T2, the optimization objective of the operation scenario is expressed as

[0198] In the formula, x s represents the decision variable of the operation scenario s, f(x s , ξ s , η s ) represents the operation performance of the system under the operation scenario s, R(x s , ξ s , η s ) represents the system risk, η s and ξ srespectively represent the power supply fluctuation and market price fluctuation in the operation scenario s, λ represents the weight coefficient for balancing system performance and risk, s ∈ S, and S represents the set of operation scenarios.

[0199] In step T3 of this embodiment, based on a large number of operation scenarios, an oblique decision tree based on multi-index sparse weights is proposed to dynamically quantify and analyze the energy efficiency, flexibility, and risk of the system. By introducing sparse weights, this oblique decision tree extracts the main features affecting the key indicators of system operation. At the same time, the complexity of the model is controlled through a regularization method to avoid overfitting. The model can not only efficiently process multi-dimensional data but also dynamically identify the internal relationships between various indicators during system operation and provide high-precision quantitative analysis for multi-objective optimization problems under uncertain environments.

[0200] Specifically, an oblique decision tree is a decision tree based on linear partitioning, used to process multi-dimensional and continuous data. Let the linear partitioning function of the k-th node in the decision tree be:

[0201]

[0202] where x is the input feature vector (such as indicators like energy efficiency, flexibility, risk, etc.), ω k is the sparse weight vector of the oblique decision tree at the k-th node, and b k is the bias term.

[0203] To ensure the sparsity of the model and avoid overfitting, regularization is introduced. The objective function E(q) for regularizing the sparse weights in the oblique decision tree is expressed as:

[0204]

[0205] In the formula, represents the weight entropy, l1 and l2 represent the regularization parameters for controlling the degree of sparsity, |q| and ||q|| represent the sparse regularization terms, W i (q) is expressed as the weight function related to sample i, H i (q) represents the indicator or function related to sample i, N represents the number of samples, and i ∈ I represents the sample index.

[0206] In this embodiment, through regularization processing, the model can automatically select the most important features and remove the variables that have less impact on system operation, thereby avoiding the overfitting phenomenon of complex models.

[0207] In step T4 of this embodiment, through the analysis of the decision tree model, the significant relationships between indicators such as energy efficiency, flexibility, and risk under different operation scenarios can be identified, providing a basis for system optimization and operation strategies.

[0208] In the embodiments of the present invention, in the current operation of the energy system, not only the optimal scheduling of energy resources such as electricity and hydrogen needs to be considered, but also the carbon emission trading mechanism needs to be incorporated. Especially in the context of carbon neutrality, carbon block trading has become an important factor affecting the system operation efficiency. In order to achieve flexible and efficient system operation in the multi-market environment of energy blocks and carbon blocks, the present invention proposes a multi-market trading strategy based on a two-layer optimization model.

[0209] In the integrated green hydrogen metallurgy energy system, there is a close connection between "energy blocks" (such as electricity and hydrogen energy) and "carbon blocks" (i.e., carbon emission allowances). The consumption of energy blocks directly affects carbon emissions, and carbon emissions are restricted by quotas and market prices. In order to achieve flexible scheduling of the system in the multi-market environment, in this embodiment, the trading process of energy blocks and carbon blocks is modeled as a two-layer optimization problem. Specifically, the two-layer optimization model constructed according to the results of the dynamic quantitative analysis of energy efficiency - flexibility - risk includes an upper-layer model and a lower-layer model;

[0210] The optimization objective of the upper-layer model is to minimize the energy cost and carbon emission cost of the system while meeting the production requirements; the optimization objective of the lower-layer model is to purchase the required energy and carbon emission allowances at the lowest price or sell the surplus energy and carbon allowances to obtain profits in the energy market and the carbon market according to the resource scheduling requirements of the upper-layer model; among them, the upper-layer model represents the energy scheduling and carbon emission constraints of the system, and the lower-layer model represents the trading strategies of energy blocks and carbon blocks in the market;

[0211] Specifically, the objective function of the upper-layer model is:

[0212]

[0213] Among them, C energy (P) represents the cost of energy blocks, represents the cost of carbon blocks, P is the energy consumption of the system, is the carbon emission;

[0214] The constraint conditions of the above upper-layer model include energy balance constraint and carbon emission constraint, which are respectively expressed as:

[0215] P generation +P import =P demand +P storage (20)

[0216]

[0217] In the formula, P generation represents the local power generation, P import represents the energy imported from the market, P demand and Pstorage respectively represent the demand quantity and the energy storage capacity, the carbon emission allowances purchased for the system;

[0218] The objective function of the lower-layer model is expressed as:

[0219]

[0220] In the formula, λ energy (t) represents the price of the energy market in the t-th period, and λ carbon (t) is the price of the carbon market, P import (t) is the energy purchased from the market in the t-th period, and E buy (t) and E sell (t) are respectively the carbon emission allowances purchased and sold in the t-th period;

[0221] The constraint conditions of the above lower-layer model include the market supply-demand balance constraint and the carbon market quota constraint, which are respectively expressed as:

[0222] P import (t) + P local_generation (t) = P demand (t) (23)

[0223]

[0224] In the formula, P import (t) represents the energy imported from the market in the t-th period, P local_generation (t) represents the energy locally generated by the system in the t-th period, and P demand (t) represents the demand quantity in the t-th period, represents the carbon dioxide emission at time t, represents the capital cost or limit of carbon dioxide emission at time t.

[0225] In this embodiment, in order to ensure the flexibility of the system in the face of different market price fluctuations, a multi-market bidding and competitive coupling analysis model strategy for energy blocks and carbon blocks is also proposed. During the peak price period, by increasing local power generation and energy storage to reduce the imported energy from the market, and at the same time obtaining profits by selling the excess carbon emission allowances. During the low price period, by purchasing cheap energy or carbon emission allowances from the market to optimize the cost in the whole production process.

[0226] In the embodiment of the present invention, a multi-market adaptive trading auxiliary decision-making system based on a two-layer optimization model is constructed. The method for outputting the scheduling and trading strategies of energy blocks and carbon blocks through it is specifically as follows:

[0227] G1. Based on the results of the dynamic quantitative analysis of energy efficiency - flexibility - risk, conduct time - series coupling analysis and confidence interval analysis on energy blocks and carbon blocks, and quantitatively infer the coupling characteristics between energy blocks and carbon blocks;

[0228] G2. Based on the inferred coupling characteristics between energy blocks and carbon blocks, explore the optimal bidding strategies for energy blocks and carbon blocks in market transactions, and combine with the constructed two - layer optimization model to form power trading agents, carbon emission rights trading agents, and green hydrogen trading agents;

[0229] G3. Construct an adaptive trading auxiliary decision - making system based on multi - agent reinforcement learning for power trading agents, carbon emission rights trading agents, and green hydrogen trading agents, continuously learn and optimize the trading strategies of energy blocks and carbon blocks to adapt to different market changes, and output the scheduling and trading strategies of energy blocks and carbon blocks;

[0230] The optimization goal of the adaptive trading auxiliary decision - making system is to maximize the cumulative return of each agent through the output scheduling and trading strategies of energy blocks and carbon blocks.

[0231] In step G1 of this embodiment, for energy blocks and carbon blocks in multi - market transactions, a time - series coupling analysis method is proposed, and quantitative evaluation is carried out through confidence - level inference. Energy blocks and carbon blocks respectively represent the transmission of physical energy and the change of carbon emission quotas in the integrated energy system, and their transactions in the market are highly correlated. Through the coupling analysis model, the interaction between energy and carbon is studied, especially their transmission and trading patterns in different time periods. In this embodiment, an inference method based on confidence intervals is also proposed to quantify the coupling characteristics between energy blocks and carbon blocks under different market conditions, providing quantitative analysis results for system optimization. Through confidence interval analysis, the coupling characteristics between energy blocks and carbon blocks can be quantitatively inferred.

[0232] In step G2 of this embodiment, through confidence interval analysis, the coupling characteristics between energy blocks and carbon blocks can be quantitatively inferred; specifically, the optimal bidding strategies of participants in the market are described through game - theory models. When the bids in each market meet the Nash equilibrium conditions, by optimizing the utility function that represents the total revenue of the energy market and the carbon market, the optimal bidding strategies of energy blocks and carbon blocks in different markets are obtained;

[0233] Among them, the Nash equilibrium condition is expressed as:

[0234]

[0235] Among them, U m (b m ,b -m ) represents the utility function of market m under the bids of other markets b - m, and it is expressed as:

[0236]

[0237] Where b m Indicates price, b -m Indicates other prices, E m (b m ) represents the potential field m and b m The expected utility associated with this, C m (b m ) represents the relationship between market m and b m The associated costs, p m Represents the price of market m.

[0238] Through the above-mentioned optimization utility function, the bidding strategies of energy blocks and carbon blocks in different markets can be obtained, and the coupling analysis of energy and carbon markets can be realized.

[0239] In step G3 of this embodiment, in order to improve the flexibility and adaptability of energy blocks and carbon blocks in market transactions, multi-agent reinforcement learning technology is introduced to involve an adaptive trading auxiliary decision-making model; in this model, the interaction between multiple agents is continuously improved through reinforcement learning, so that the system can adapt to different market changes and make the best decision in a complex trading environment. Through continuous strategy updates and optimization, this method can achieve efficient scheduling and trading of energy blocks and carbon blocks in a multi-market environment, and enhance the market responsiveness and profitability of the system.

[0240] For example, a multi-agent reinforcement learning (MARL) model is introduced. Assume that there are N agents, and the state of each agent i is s i (t), action is a i (t), the reward is γ i (t). The goal of reinforcement learning is to use the strategy π i Make each agent maximize its cumulative reward R i :

[0241]

[0242] In this embodiment, the multi-agent Tsinghua learning method is introduced to realize the linkage optimization of the adaptive trading strategies of energy blocks and carbon blocks. Through the continuous interaction between agents, the reinforcement learning system can adaptively adjust the strategy to optimize the market transactions of energy blocks and carbon blocks. Ultimately, this multi-agent system can achieve the best scheduling and trading decisions in a complex market environment.

[0243] In the present invention, specific embodiments are used to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, based on the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

[0244] Those of ordinary skill in the art will realize that the embodiments described herein are for helping the reader understand the principles of the present invention, and it should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific deformations and combinations that do not depart from the essence of the present invention according to these technical revelations disclosed by the present invention, and these deformations and combinations are still within the protection scope of the present invention.

Claims

1. An optimization method for a green hydrogen metallurgy integrated energy system, characterized in that, Including: A unified multi-energy-quality flow network matrix model of heterogeneous energy flow and material flow based on differential kinetic equations is constructed according to the multi-energy-quality flow characteristics in the integrated green hydrogen metallurgy energy system, and the multi-energy-quality flow distribution is calculated based on it. The multi-time scale characteristics of flexible adjustable resources in the integrated green hydrogen metallurgy energy system are analyzed, an extended resource-task network model considering multi-energy-quality flow distribution is constructed, and coordinated control of energy-quality flow in multiple links is carried out in combination with a multi-model predictive control mechanism. Based on the uncertain variables in the integrated green hydrogen metallurgy energy system, a multi-objective optimal operation model is constructed by using the robust optimization method, and a large number of operation scenarios are randomly generated. The energy efficiency-flexibility-risk dynamic quantification analysis is carried out on the operation scenario data through the oblique decision tree model, and a multi-market adaptive trading auxiliary decision-making system based on a two-layer optimization model is constructed according to the results of the energy efficiency-flexibility-risk dynamic quantification analysis. The scheduling and trading strategies of energy blocks and carbon blocks are output through it to achieve the efficient operation of the system; the energy block and the carbon block respectively represent the physical energy transmission and carbon emission quota in the integrated green hydrogen metallurgy energy system. In the process of system optimization, the multi-energy-quality flow distribution calculated by the multi-energy-quality flow network matrix model provides the multi-energy-quality flow distribution state required for constructing the extended resource-task network model; the extended resource-task network model serves as a constraint condition for constructing the multi-objective optimal operation model; the energy-quality flow control strategy obtained by the multi-model predictive control mechanism serves as the production control strategy required for constructing the multi-energy-quality flow network matrix model and generating a large number of operation scenarios; the scheduling and trading strategies of energy blocks and carbon blocks output by the multi-market adaptive trading auxiliary decision-making system provide optimized decision-making information for the multi-model predictive control mechanism to output the energy-quality flow control strategy. Through the system optimization process, second-level multi-energy-quality flow distribution calculation, minute-level coordinated control of energy-quality flow in multiple links, and hourly-level efficient operation of the system are realized.

2. The optimization method of the integrated green hydrogen metallurgy energy system according to claim 1, characterized in that The method for constructing a unified multi-energy-quality flow network matrix model of heterogeneous energy flow and material flow based on differential kinetic equations is specifically as follows: S1. Analyze the multi-energy-quality flow characteristics in the integrated green hydrogen metallurgy energy system, classify the physical quantities involved into intensive quantities and extensive quantities, and then construct a unified multi-energy-quality flow kinetic equation based on differential kinetic equations. The unified multi-energy-quality flow kinetic equation includes a unified kinetic equation for multi-energy-quality flow transmission and a unified kinetic equation for multi-energy-quality flow coupling conversion. S2. Perform static algebraic analysis based on Laplace transform and external port equivalence based on distributed parameter approximation on the constructed unified multi-energy-quality flow kinetic equation in sequence to construct a unified multi-energy-quality flow model. The unified multi-energy-quality flow model includes a unified multi-energy-quality flow transmission model obtained by performing transmission static algebraic analysis and branch external port equivalence in sequence, and a unified multi-energy-quality flow coupling conversion model obtained by performing energy-quality conversion static algebraic analysis and coupling node external port equivalence in sequence. S3. Construct a full-network dynamic characteristic model of multi-energy-quality flow according to the unified multi-energy-quality flow model. S4. Dimensionally reduce the full-network dynamic characteristic model of the multi-energy mass flow network to a boundary equivalent model that only includes key boundary nodes, and then construct its corresponding unified Jacobian matrix as the matrix model of the multi-energy mass flow network.

3. The optimization method of the integrated green hydrogen metallurgy energy system according to claim 2, characterized in that In step S1, in the constructed unified dynamic equation of the multi-energy mass flow, the left side of the equal sign is represented by the spatial differentials of intensive quantities and extensive quantities, and the right side is represented by the time differentials of intensive quantities and extensive quantities and related terms, which is expressed as: In the formula, ψ represents the generalized intensive quantity, ζ represents the extensive quantity, α1, α2, β1, and β2 all represent branch parameters; x represents the state; t represents the moment; Step S4 is specifically as follows: According to the importance and physical attributes of the network nodes, divide them into key boundary nodes and non-key nodes, perform matrix operations on the injection values of the intensive quantities and extensive quantities of the nodes involved in the full-network dynamic characteristic model of the multi-energy mass flow network according to the divided node types, construct a block matrix, perform Gaussian elimination on the constructed block matrix, obtain a boundary equivalent model that only includes key boundary nodes, and then construct its corresponding unified Jacobian matrix as the matrix model of the multi-energy mass flow network; Among them, the constructed block matrix is expressed as: where Y BB , Y BI , Y IB , Y II denote the block matrices of Y, Y represents the admittance matrix of the energy nodes, ψ B (s) and ψ I (s) represent two sets obtained by partitioning the node intensive quantities according to the node types, ζ B (s) and ζ I (s) represent two sets obtained by partitioning the extensive quantity injection values according to the node types; The constructed boundary equivalent model is expressed as: The constructed unified Jacobian matrix is expressed as: In the formula, represents the extensive and intensive quantity characterization of process J of the integrated green hydrogen metallurgy energy system, and the subscripts m and n represent the parameter indices in the integrated green hydrogen metallurgy energy system.

4. The optimization method of the integrated green hydrogen metallurgy energy system according to claim 1, characterized in that, The method for constructing an extended resource-task network model considering the multi-energy mass flow distribution is specifically as follows: X1. Analyze the regulation response characteristics of the energy supply, demand, energy conversion, and storage links in the green hydrogen metallurgy integrated energy system at different time scales, construct a regulation response time scale matrix, and analyze the cross-link regulation characteristics in the multi-energy mass interaction based on it, and construct an equivalent model of the regulation external characteristics based on heterogeneous links; X2. Based on the equivalent models of the regulation external characteristics corresponding to the different regulation characteristics of various devices, perform dynamic correlation analysis, analyze the impact of different production tasks on the energy mass flow distribution, and establish an extended resource-task network model that characterizes the correlation between production tasks and the supply-demand distribution of the multi-energy mass flow.

5. The optimization method of the integrated green hydrogen metallurgy energy system according to claim 4, characterized in that Step X2 includes the following sub-steps: X21. Classify the production tasks in the green hydrogen metallurgy integrated energy system according to production requirements, determine the demand characteristics of the energy mass flow for each type of production task at different time periods, fit its historical data, establish dynamic demand curves for each type of production task, and then produce multiple correlation models for different production task types; X22. Model the energy mass demand characteristics of each production process of each production task in the green hydrogen metallurgy integrated energy system through dynamic programming or optimization algorithms, and adjust the execution order and energy mass flow distribution of the production processes of the production tasks in real time to optimize the collaborative scheduling between production processes, and construct an energy mass flow collaborative regulation model between processes; The energy mass flow collaborative regulation model between processes is subject to the time scheduling cost between production processes, the dependence relationship between production processes, and resource limitations; X23. According to the constructed dynamic correlation model of production tasks and the energy mass flow collaborative regulation model between processes, and introducing time, space, and the dynamic characteristics of the energy mass flow, construct an extended resource-task network model; The extended resource-task network model is a model that dynamically adjusts resource supply and task demand in the integrated green hydrogen metallurgy energy system according to time series data.

6. The optimization method of the integrated green hydrogen metallurgy energy system according to claim 4, wherein The method for outputting an energy-quality flow coordinated regulation strategy based on a multi-model predictive control mechanism is specifically as follows: Based on the task-resource allocation result obtained from the extended resource-task network model, predict the random variables involved in the production process at future times, and input them into the multi-model predictive control mechanism to output an energy-quality flow regulation strategy for the current working condition; The multi-model predictive control mechanism includes a multi-model predictive mechanism based on a local model combination and a multi-model predictive mechanism based on a multi-controller combination; The multi-model predictive mechanism based on a local model combination refers to: Construct local models for predicting energy-quality flow allocation under different working conditions, and based on the conditional model switching mechanism, switch the optimal local model according to the operating state of the integrated green hydrogen metallurgy energy system to perform corresponding energy-quality flow allocation prediction; The multi-model predictive mechanism based on a multi-controller combination refers to: Based on the energy-quality flow allocation strategy predicted by the multi-model predictive mechanism of the local model combination, design corresponding independent controllers according to different energy-quality flow characteristics, and for different working conditions and energy-quality flow regulation requirements, adopt a cooperative mechanism based on constraint optimization, introduce a global objective function to optimize the regulation objectives of each independent controller, and obtain the overall optimal energy-quality flow regulation strategy of the system; among them, the outputs of each independent controller are interrelated; The basic model of the multi-model predictive control mechanism is expressed as: where \(x(t + k|t)\) represents the predicted value of the state \(x\) at time \(t + k\), \(u(t + k|t)\) represents the predicted value of the control input \(u\) at time \(t + k\), \(Q\) and \(R\) are the weight matrices of the state and the control respectively, u(t) represents the control input function, and \(N\) represents the number of predictions or time steps of the optimization process.

7. The optimization method of the integrated green hydrogen metallurgy energy system according to claim 1, characterized in that, The method for dynamically quantifying energy efficiency-flexibility-risk analysis of operation scenario data through a skew decision tree model by using a robust optimization method to construct a multi-objective optimization operation model for randomly generating a large number of operation scenarios based on the uncertain variables in the integrated green hydrogen metallurgy energy system is specifically as follows: T1. Characterize the uncertain variables in the integrated green hydrogen metallurgy energy system as an uncertainty set through probability distribution fitting, construct a multi-objective optimization operation model for realizing stochastic production simulation by using a robust optimization method according to the uncertainty set, and use a continuous convex hull approximation strategy to transform the multi-objective optimization operation model with non-linear constraints into a linear model; The uncertain variables include power supply fluctuations and market price fluctuations; the constraint condition of the multi-objective optimization operation model is the extended resource-task network model of the integrated green hydrogen metallurgy energy system considering multi-energy-quality flow distribution; T2. Randomly generate the uncertain variables included in different operation scenarios, and use maximizing the operation efficiency of the system and minimizing the risk as the optimization objective of the operation scenario, and then generate a large number of operation scenarios; T3. Analyze the generated operation scenarios, extract the main characteristics affecting the key indicators of system operation, construct a skew decision tree based on multi-index sparse weights, and regularize its sparse weights to obtain a skew decision tree model; The key indicators include energy efficiency, flexibility, and risk; T4. Use the skew decision tree model to extract the association rules between energy efficiency, flexibility, and risk in the operation scenario data to realize dynamic quantification analysis of energy efficiency-flexibility-risk.

8. The optimization method of the integrated green hydrogen metallurgy energy system according to claim 7, characterized in that In step T1, the multi-objective optimization operation model for realizing random production simulation is expressed as: where \(x\) is the state of the system, \(\xi\) is the uncertainty variable, \(f(x,\xi)\) is the profit and loss function of the system corresponding to the optimization objective, and \(\theta\) represents the robustness parameter, which is used to control the trade-off between the expectancy and conservatism of the system. denotes the expected function based on ; denotes the uncertainty set, and \(P\) ξ denotes the probability distribution of the uncertainty variable \(\xi\), denotes the reference distribution fitted from the operation historical data. In step T2, the optimization target of the running scenario is expressed as: where x s represents the state of the operation scenario s, and f(x s , ξ s , η s ) represents the operation performance of the system under the operation scenario s, R(x s , ξ s , η s ) represents the system risk, η s and ξ s respectively represent the power supply fluctuation and market price fluctuation in the operation scenario s, λ represents the weight coefficient for balancing the system performance and risk, s ∈ S, and S represents the set of operation scenarios.

9. The optimization method of the integrated green hydrogen metallurgy energy system according to claim 1, wherein The two-layer optimization model constructed based on the results of the dynamic quantitative analysis of energy efficiency-flexibility-risk includes an upper model and a lower model; The optimization goal of the upper model is to minimize the energy cost and carbon emission cost of the system while meeting the production demand; the optimization goal of the lower model is to purchase the required energy and carbon emission quotas at the lowest price in the energy market and carbon market according to the resource scheduling requirements of the upper model, or sell the excess energy and carbon quotas to obtain profits. The objective function of the upper model is: Among them, C energy (P) represents the cost of the energy block, represents the cost of the carbon block, P is the energy consumption of the system, is the carbon emission; The constraints of the upper model include energy balance constraints and carbon emission constraints, which are respectively expressed as: P generation +P import =P demand +P storage Wherein, P generation represents the local power generation, P import represents the energy imported from the market, P demand and P storage represent the demand and the energy storage capacity respectively, is the carbon emission allowance purchased by the system; The objective function of the lower model is expressed as: where λ energy (t) represents the price of the energy market at the t-th moment, and λ carbon (t) is the price of the carbon market at the t-th moment, P import (t) is the energy purchased from the market at the t-th moment, and E buy (t) and E sell (t) are the carbon emission allowances purchased and sold at the t-th moment respectively; The constraints of the lower model include market supply and demand balance constraints and carbon market rating constraints, which are respectively expressed as: P import (t) + P local_generation (t) = P demand (t) where, P import (t) represents the energy imported from the market in the t-th period, P local_generation (t) represents the energy locally generated by the system in the t-th period, P demand (t) represents the demand in the t-th period, represents the carbon dioxide emissions at time t, represents the capital cost or limit of carbon dioxide emissions at time t.

10. The optimization method of the integrated green hydrogen metallurgy energy system according to claim 9, characterized in that, A multi-market adaptive trading decision-making auxiliary system based on a two-layer optimization model is constructed, and the method of outputting the scheduling and trading strategies of energy blocks and carbon blocks is as follows: G1. Based on the results of the dynamic quantitative analysis of energy efficiency, flexibility and risk, the time series coupling analysis and confidence interval analysis of the energy block and the carbon block are carried out to quantitatively infer the coupling characteristics of the energy block and the carbon block; G2. Based on the inferred coupling characteristics of energy blocks and carbon blocks, the optimal bidding strategy of energy blocks and carbon blocks in market transactions is explored, and combined with the constructed two-layer optimization model to form power trading agents, carbon emission rights trading agents and green hydrogen trading agents; G3. Based on the power trading agent, carbon emission trading agent and green hydrogen trading agent, a multi-agent reinforcement learning adaptive trading auxiliary decision-making system is constructed to continuously learn and optimize the trading strategies of energy blocks and carbon blocks to adapt to different market changes and output the scheduling and trading strategies of energy blocks and carbon blocks; The optimization goal of the adaptive trading auxiliary decision-making system is to maximize the cumulative reward of each intelligent agent through the scheduling and trading strategies of the output energy blocks and carbon blocks.

Images