69 results about "Energy system optimization" patented technology

The invention discloses a regional integrated energy system optimization method and system, and the method comprises the steps: S1, constructing a multi-energy demand response model, and carrying out the linkage scheduling among multi-energy loads based on the multi-energy demand response model; s2, designing and optimizing a stepped carbon transaction mechanism; and S3, performing multi-objective optimization and cooperative operation. According to the invention, through a three-layer optimization architecture of multi-energy demand response, stepped carbon transaction and multi-target cooperation, economic, low-carbon and efficient cooperation optimization of the regional integrated energy system is realized, and the blank of the traditional technology in the aspects of multi-energy flow linkage scheduling, dynamic carbon price excitation and new energy refined consumption is filled.

The invention relates to the technical field of comprehensive energy optimal configuration, in particular to a comprehensive energy system optimal configuration method and system considering medium and long term characteristics of hydrogen energy storage, and the method comprises the steps: constructing a multi-energy coupling mathematical model of a rural comprehensive energy system; a typical day containing multi-dimensional data is generated by a typical day generation method based on spectrum joint clustering, a hydrogen energy storage long-period operation model is constructed, and the hydrogen storage amount at any moment in the whole-year operation period is decomposed into dynamic superposition of the initial hydrogen storage amount and a typical day scene; constructing a double-layer optimization configuration model comprising capacity configuration and scheduling operation, wherein the double-layer optimization configuration model comprises an upper-layer capacity configuration model and a lower-layer scheduling operation model; and solving the double-layer optimal configuration model by adopting a Benders decomposition method, splitting the double-layer optimal configuration model into a main problem and a sub-problem, and carrying out iterative approximation to an optimal solution by utilizing a plane cutting method. The system capacity configuration is optimized, the solving efficiency is improved, and the consumption capability of renewable energy sources and the overall flexibility of the system are effectively improved.

The invention relates to the technical field of energy system optimization, in particular to a multi-source heterogeneous energy data fusion method and system based on a neural network, and the method specifically comprises the steps: collecting and preprocessing structured, semi-structured and unstructured multi-source heterogeneous energy data, carrying out the feature convergence of the energy data based on neural routing driving, forming a comprehensive feature vector, and carrying out the fusion of the multi-source heterogeneous energy data. The method comprises the following steps: firstly obtaining a comprehensive feature vector, then obtaining a collaborative feature vector generated by collaborative feature learning developed by each subsystem in a distributed system, and finally fusing the collaborative feature vector and the comprehensive feature vector based on a deep fusion network to form a centralized and distributed fusion architecture, thereby realizing accurate fusion of centralized and distributed multi-source heterogeneous energy data. The problems that existing energy data sources are wide, formats are diversified, fusion difficulty is increased dramatically, compatibility and collaboration dilemma is caused remarkably by different service system architecture differences, and an existing fusion algorithm is difficult to consider precision and efficiency at the same time can be solved.

The invention belongs to the technical field of energy system optimization, and particularly provides a multi-objective collaborative optimization method and system for an integrated energy system. Comprising the steps of generating a multi-dimensional uncertainty time sequence scene of the integrated energy system; establishing a high-fidelity dynamic behavior model library; defining decision variables, and constructing a multi-target two-stage stochastic programming optimization model by taking the economy, environmental protection and toughness of the comprehensive energy system as a three-dimensional optimization target; solving the multi-objective two-stage stochastic programming optimization model by adopting a self-adaptive multi-objective evolution algorithm assisted by an agent model; and according to a solving result, realizing a mixed multi-attribute decision based on a fuzzy analytic hierarchy process and a multi-criterion compromise solution sorting method. According to the method, the park-level IES global optimal, high-robustness and high-efficiency planning design is realized from uncertainty modeling, equipment characteristic description and large-scale solution to multi-attribute decision full-chain innovation.

The invention discloses an end-to-end scheduling method and system for a multi-source weather-driven urban integrated energy system. The method comprises the following steps: constructing an integrated energy system model; constructing a source load prediction model based on multi-source numerical weather forecast data in combination with historical photovoltaic output data and power load and thermal load data; the method comprises the following steps: establishing a comprehensive energy system optimization scheduling model with minimization of system operation cost as an optimization target, designing a differentiable optimization layer, and reversely transmitting the gradient of the optimization target in the scheduling model to a source load prediction model parameter to the source load prediction model through a back propagation algorithm by the differentiable optimization layer, the parameters of the driving source load prediction model are updated, and end-to-end linkage optimization from prediction to scheduling is achieved; and periodically obtaining updated multi-source numerical weather forecast data and source load data, readjusting prediction model parameters, and executing optimization solution of the integrated energy system optimization scheduling model. According to the invention, cooperative training and iterative optimization of the prediction model and the scheduling decision are realized.

The invention relates to the technical field of integrated energy systems, and provides an integrated energy system optimization method and system in multiple uncertain environments, and the method comprises the steps: obtaining the state of an integrated energy system, and obtaining a multi-energy-flow equipment action through an actor network; wherein MPC actors are embedded into a double-delay depth deterministic strategy gradient architecture, an actor network and transfer tuples of the MPC actors are respectively stored in an agent experience playback pool and an expert experience playback pool, a priority is given to each sample according to a time sequence difference error of the samples in the two experience playback pools, and a mixing ratio is determined according to a training time step; in combination with the mixing ratio and the priority, the sampling probability of samples is calculated, and then the degree of dependence of updating of the comment network on an expert experience playback pool in the initial training stage is controlled to be high, and the degree of dependence on an agent experience playback pool in the later training stage is controlled to be high. And the performance is better in a multi-uncertainty coupled IES environment.

The invention discloses a multi-role large model assisted hydrogen-containing building energy system operation optimization method, and belongs to the technical field of building energy system optimization control, and the method comprises the steps: firstly, building a hydrogen-containing building multi-energy system operation cost minimization problem in an off-grid operation mode; secondly, re-modeling the problem into a security Markov decision process, and defining a system state space, an action space and a composite reward function; then, solving a safety Markov decision process of modeling based on a multi-role large language model assisted near-end strategy optimization algorithm, and obtaining an intelligent agent operation strategy related to the hydrogen-containing building multi-energy system; finally, the intelligent agent makes an online decision based on the obtained optimization strategy, the decision acts on the actual hydrogen-containing building multi-energy system, the system operation cost can be effectively reduced, and the energy supply reliability is improved.

The invention discloses a multi-energy system optimization method and system based on hydrogen energy storage, and belongs to the field of multi-energy system optimization, and the method comprises the steps: obtaining the historical wind speed, wind direction and solar irradiance data of an anemometer tower and a photovoltaic power station, training a time sequence analysis model through the historical wind speed, wind direction and solar irradiance data, and obtaining a time sequence analysis model; wind energy power and solar energy power prediction curves in a future time period are obtained; the method comprises the following steps: acquiring pressure and temperature data of a hydrogen storage tank, inputting the pressure and temperature data into a pre-established leakage rate dynamic compensation algorithm to obtain a real-time hydrogen loss amount, and if the hydrogen loss amount is greater than a preset threshold value, reducing the operation pressure or temperature of the hydrogen storage tank; and according to the wind and light power prediction curve, the hydrogen production equipment operation data, the hydrogen storage tank operation parameters, the hydrogen conversion equipment control signal, the constraint model and the income cost model as input of a linear programming algorithm, an equipment capacity configuration scheme for maximizing the system economic benefits is obtained.

A method for optimizing dispatching of a fully distributed integrated energy system with preset times is provided. [Solution] The optimization dispatch method establishes an integrated energy system operation optimization model and constructs an objective function as a dispatch problem for the integrated energy system with the goal of minimizing the total cost of the integrated energy system. Safe operation constraints are set in the objective function, including a power balance constraint, a power upper / lower limit constraint, and an operation ramp rate constraint. The method also assumes that the communication topology of the integrated energy system's source side, load side, storage side, and station side is an undirected connected graph. A fully distributed optimization algorithm based on TBG with a preset time is used to solve the objective function, so that the integrated energy system operation optimization model reaches a convergence state within a preset time, and an optimal output strategy for the integrated energy system is obtained.

The invention belongs to the technical field of comprehensive energy system optimization and intelligent control, and particularly relates to a comprehensive energy system demand response self-adaptive control method for multi-energy coordinated regulation, which comprises the following steps: identifying multi-energy response resources; performing multi-energy demand response collaborative decomposition; and closed-loop adaptive adjustment and excitation correction: in the instruction execution process, monitoring the deviation between the actual response and the expected response of each energy source in real time, dynamically generating a compensation control instruction based on the deviation and carrying out online correction on excitation parameters so as to realize the closed-loop adaptive control of the response. According to the method, the sensitivity and prediction precision of the system to load change can be remarkably improved, and the flexible regulation and control capability and response stability of the integrated energy system are enhanced from the source.

The invention relates to a comprehensive energy system optimization scheduling method considering indirect carbon emission uncertainty. The method comprises the following steps: acquiring basic data; quantitative modeling is carried out on the uncertainty factors, and an uncertainty set used for describing the fluctuation range of the uncertainty factors is constructed; establishing a carbon emission and transaction cost calculation model of the system, firstly accounting the free carbon emission quota of the system, secondly calculating the actual net carbon emission of the system, and finally calculating the carbon transaction cost required to be paid or obtained by the system; constructing a stochastic optimization scheduling model, taking a minimum actual total net carbon emission amount of the system as a target function, and setting constraint conditions including a system total operation cost constraint, a power balance constraint and an equipment operation constraint; and converting the stochastic optimization scheduling model into a mixed integer linear programming problem for solving to obtain an optimal output plan and an energy scheduling scheme of each device, which enable the actual total net carbon emission of the system to be minimum. According to the method, the net carbon emission of the system can be minimized in multiple uncertain environments.

The invention discloses a rural comprehensive energy system optimal configuration method based on multi-energy complementation. The method comprises the following steps: S1, collecting multi-dimensional rural energy data; s2, mathematical modeling of the energy equipment; s3, performing matching analysis on the rural multi-energy demand and the equipment; s4, constructing a multi-objective optimization constraint system; s5, constructing and solving an optimal configuration model of the integrated energy system; according to the method, layered modeling is carried out on the performance parameters of the energy conversion type equipment and the cold and heat supply type equipment, so that the suitability and accuracy of rural comprehensive energy system equipment modeling are effectively improved; a multi-agent system is adopted to carry out matching analysis of rural multi-energy demands and equipment, and it is ensured that multi-energy complementary potential evaluation can accurately adapt to multi-element demands of different rural scenes; an optimal configuration model is solved by constructing a target function fused with a rural power grid vulnerability index, so that an optimal configuration result can realize collaborative optimization and can adapt to the characteristics of a rural power grid.

The application discloses a two-stage distribution robust planning method of a comprehensive energy system considering flexibility, relates to the technical field of comprehensive energy system optimization planning and intelligent decision-making, and comprises the following steps: constructing a comprehensive energy system equipment and multi-network coupling model; establishing a random source and load model of photovoltaic available output, wind power available output, and electric load, heat load and gas load; extracting covariant information corresponding to a target scene, and constructing a conditional experience distribution and a Wasserstein conditional distribution fuzzy set based on historical error samples; establishing a two-stage distribution robust optimization model of one-stage capacity configuration and two-stage operation scheduling, which takes the minimum of annualized investment cost and expected operation cost under the worst distribution as a target and contains flexibility margin constraints; and obtaining an optimal capacity configuration scheme of the comprehensive energy system through a model reconstruction and decomposition algorithm. Compared with the prior art, the application can improve the flexibility, robustness and economy of the planning result of the comprehensive energy system under uncertain operation conditions.

The multi-time-scale asynchronous optimization scheduling method for the ammonia-containing integrated energy system based on the layering TD3 comprises the following steps: step 1, analyzing an electricity-to-ammonia operation mechanism, and establishing an electricity-to-ammonia and fuel gas ammonia doping mathematical model; 2, constructing a day-ahead scheduling model of the ammonia-containing integrated energy system, and designing an intra-day asynchronous optimization scheduling strategy by considering energy difference characteristics; 3, establishing an intra-day upper and lower layered Markov decision process, and proposing an intra-day rolling asynchronous optimization scheduling strategy generation method based on a layered TD3; and step 4, carrying out optimization scheduling on the ammonia-containing integrated energy system. According to the ammonia-containing integrated energy system optimization scheduling method provided by the invention, relatively low system operation cost and carbon emission can be realized in a short time, and meanwhile, compared with a traditional synchronous scheduling method, the training speed can be remarkably improved, and the training time can be shortened.

The invention discloses an incremental learning-based optimization control method and system for a modified energy system, and the method comprises the steps: obtaining the field collection data of an original energy system, and carrying out the processing through a multiple data processing method, and obtaining an original energy system data set; training a pre-selected data model by using the normalized original energy system data set, and selecting a system energy consumption and temperature model by comparing fitting effects of different types of data models; for the transformed new energy system, adopting an incremental learning algorithm to form a new energy system energy consumption and temperature model which can be simultaneously suitable for old knowledge and new knowledge; the optimal operation mode, the operation state and the optimal system control parameters under different working conditions are solved by utilizing the energy consumption and temperature model of the new energy system according to different optimization objectives and matching with corresponding optimization algorithms, so that energy conservation is realized. According to the method, the new energy system model is rapidly formed by forward migration of old energy system knowledge, and the problem of disastrous forgetting is avoided.

The invention belongs to the technical field of energy system optimization, and particularly relates to a comprehensive energy park operation optimization method and device, equipment and a medium. The method comprises the steps of performing economic dispatching based on day-ahead prediction data to obtain a unit output plan; traditional dynamic carbon emission factors are calculated and improved, the abandoned energy of renewable energy sources is considered during improvement, and the equivalent carbon emission benchmark is transmitted to a heat energy and cold energy network through multi-energy coupling equipment; determining a carbon intensity partition threshold based on the improved carbon emission factor and executing partition; generating a carbon reward and punishment price signal; the adjustable load is optimized through a user side objective function, and a responded load curve is obtained; and finally, economic dispatching is executed again to obtain a final output plan. The technical problems that traditional carbon emission factor calculation is inaccurate, the carbon transaction price suddenly changes, and carbon signal transmission is incomplete are solved, and the low-carbon operation effect of the comprehensive energy park is improved.

A kind of comprehensive energy system optimization method and system giving consideration to cost and new energy consumption, comprising: comprehensively considering the characteristics of multi-energy equipment and spot market electricity price mechanism, constructing regional comprehensive energy system model;Based on the regional comprehensive energy system model, a multi-objective optimization scheduling model containing day-ahead, intra-day, real-time multi-time scale and minimizing system total cost and maximizing new energy consumption is established;The day-ahead and intra-day multi-objective optimization scheduling model is solved;Based on the day-ahead and intra-day optimization results, the real-time multi-objective optimization scheduling model is solved by designing a distributed intelligent agent architecture and using a distributed model predictive control algorithm;According to the solving result, the output plan of each unit, the charging and discharging plan of energy storage and the system energy purchase plan are determined to realize optimal scheduling.The present application comprehensively considers operation cost and new energy consumption, and realizes economic and low-carbon operation of regional comprehensive energy system.

The invention discloses a rural integrated energy system optimization scheduling method considering multi-energy coupling and microclimate. The method comprises the following steps: S1, constructing an electricity-gas-heat-hydrogen multi-energy flow coupling system model; s2, microclimate modeling and scene extraction are carried out, and a dynamic correction model of meteorological variables on photovoltaic and wind power output, user load behaviors and electric heat pump energy efficiency under microclimate is established; extracting a typical scene set according to the collected historical microclimate data; s3, establishing a unified time sequence constraint model for various heterogeneous flexible resources, and constructing a'operation area polyhedron 'of the heterogeneous flexible resources in a multi-dimensional space; s4, constructing a day-ahead-real-time two-stage random optimization scheduling model which comprises a day-ahead decision-making stage and a real-time scheduling stage; and S5, constructing a cloud edge collaborative hierarchical distributed optimization framework, solving a day-ahead-real-time two-stage random optimization scheduling model, and finally outputting a multi-time scale scheduling decision covering a day-ahead plan and real-time adjustment.

The invention relates to the field of integrated energy system optimization, and particularly discloses a time-frequency combined feature extraction and clustering acceleration optimization model training method, which comprises the following steps: S1, acquiring mixed integer programming (MIP) equation data; s2, performing data enhancement, and extracting and preprocessing the MIP data; s3, time domain features are extracted, and low-dimensional MIP time domain features are extracted from variables and constraint node matrixes of the MIP bipartite graph through a time domain auto-encoder; s4, extracting a frequency domain feature, and calculating a frequency spectrum energy entropy of each node as the frequency domain feature; s5, inputting the time domain and frequency domain features into a fusion network to obtain final time-frequency combined MIP low-dimensional features; s6, training a feature extraction model to enable the obtained feature space to better serve a downstream clustering task; and S7, clustering the fusion features, and extracting typical examples. According to the method, the characteristics of each MIP can be identified more accurately, typical instances can be extracted for subsequent training of the MIP solver model, a large number of redundant MIP problems are eliminated, and the solving accuracy is improved.

The invention discloses a cross-border integrated energy system electric heating collaborative transaction optimization operation method based on a block chain technology, and relates to the technical field of integrated energy system optimization operation. The method comprises the following steps: firstly, constructing a multi-energy coupled cross-border comprehensive energy system model containing electricity, heat, hydrogen, natural gas and the like, and introducing diversified utilization mechanisms such as electricity-to-gas conversion, hydrogen energy storage, fuel gas hydrogen doping and the like; secondly, an energy transaction exchange rate prediction model is established by using LSTM, and the financial risk in the cross-border settlement process is reduced; then based on an asymmetric Nash negotiation theory, constructing a double-layer optimization model composed of an alliance cost minimization sub-problem and a profit distribution sub-problem, and adopting an improved dynamic penalty factor ADMM algorithm to realize distributed solution of the multinational integrated energy system; finally, an alliance chain adopting a PoA consensus mechanism is introduced, and safe storage, credible verification and anonymous interaction of the electric heating transaction data are achieved. The economical efficiency, the safety and the low-carbon operation level of the cross-border energy system can be remarkably improved.

An incremental learning-based optimization control method and system for modified energy systems includes: acquiring on-site data from the original energy system and processing it using multiple data processing methods to obtain an original energy system dataset; training a pre-selected data model using the normalized original energy system dataset, and selecting a system energy consumption and temperature model by comparing the fitting effects of different types of data models; for the modified new energy system, using an incremental learning algorithm to form a new energy system energy consumption and temperature model applicable to both old and new knowledge; and using the new energy system energy consumption and temperature model, according to different optimization objectives, combining appropriate optimization algorithms to solve for the optimal operating mode, operating state, and optimal system control parameters under different operating conditions to achieve energy saving. This invention utilizes the forward transfer of knowledge from the old energy system to quickly form a new energy system model, avoiding the problem of catastrophic forgetting.

The present application relates to the technical field of energy system optimization, in particular to a multi-source heterogeneous energy data fusion method and system based on neural network, which specifically collects and preprocesses structured, semi-structured and unstructured multi-source heterogeneous energy data, forms a comprehensive feature vector based on neural routing driven energy data feature aggregation, then obtains the collaborative feature vector generated by the collaborative feature learning of each subsystem in the distributed system, and finally fuses the collaborative feature vector and the comprehensive feature vector based on the deep fusion network, so as to realize the accurate fusion of centralized and distributed multi-source heterogeneous energy data, solve the problems of increasing difficulty of fusion of extensive energy data sources and various formats, compatibility and collaboration dilemma caused by significant differences in architecture of different business systems, and difficulty of existing fusion algorithms to balance accuracy and efficiency.

The invention relates to the technical field of comprehensive energy system optimization control, and provides a novel multi-energy-flow system optimization method which is characterized in that an optimization path is adaptively determined through system optimization evaluation factors, each device has a load form when optimization is not needed, and each device has a load form when optimization is needed. On the basis of the coarse-to-fine optimization mode, the configuration optimization problem of the equipment model in the comprehensive energy system can be better processed macroscopically and microcosmically. It is ensured that the operation strategy result obtained under the current output quantity combination meets energy balance and is relatively excellent, meanwhile, the optimization method can greatly improve the speed and quality of the optimization process, the solving difficulty is reduced, and the solving efficiency is improved. Aiming at multi-energy-flow equipment parameters with complex models, the optimal configuration is directly determined through the method disclosed by the invention, and an innovative solution is provided for optimization of a multi-energy-flow system through systematic innovation in the patent technology.

The invention provides a multi-integrated energy system game playing method based on two-stage random robustness, and belongs to the field of integrated energy system optimization operation. The method comprises the following steps: constructing a plurality of integrated energy system models based on renewable energy output and power price of a power distribution system in different integrated energy systems; constructing a plurality of multi-energy load aggregator models based on energy prices formulated by different integrated energy systems; constructing an N-S game model based on the plurality of integrated energy system models and the plurality of multi-energy load aggregator models by using a game theory; and solving the N-S game model by adopting a KKT condition in combination with an ADMM algorithm and C & CG-AIS to obtain the optimal interaction power among all the integrated energy systems and the pricing of the energy price. The method can stimulate the demand response potential of the user, reduce the dependence of the integrated energy system on an external energy network, and improve the overall benefits and individual benefits of multiple market subjects.

The invention discloses a random robust optimization method considering multiple uncertainties, and belongs to the field of optimal scheduling of an integrated energy system. The method is used for obtaining the power output of each device in the integrated energy system, and comprises the following steps: firstly, establishing a first-stage optimization model by taking the planning cost of the integrated energy system in a minimum basic scene as a target; establishing a second-stage optimization model by taking minimization of the power interaction cost of the integrated energy system and the regional power grid in the worst electricity price scene as a target; secondly, establishing a third-stage optimization model by taking the operation cost of the minimum integrated energy system as a target; and finally, constructing a three-stage random robust model, and solving the three-stage random robust model by using a column sum constraint generation algorithm to obtain the power output of each device in the integrated energy system. According to the method, the relation between the economical efficiency and the robustness of the system can be well balanced, and the worst scene better conforms to engineering practice.

This invention discloses a method and system for optimized scheduling of integrated energy systems based on a large language model in the field of integrated energy system optimization scheduling and intelligent control. The method includes: partitioning the integrated energy system according to power supply sources and energy conversion equipment; constructing an integrated energy system model, an energy trading matrix, and a carbon emission rights trading matrix; and calculating the total net carbon emissions and total green electricity certificates of the integrated energy system; constructing the state space, action space, and reward function of a deep reinforcement learning model; training the deep reinforcement learning model based on historical optimized scheduling data of the integrated energy system and the large language model; and generating optimized scheduling actions for the integrated energy system using the trained deep reinforcement learning model based on real-time operating data of the integrated energy system. This invention can improve the coordinated optimization capability of integrated energy systems and enhance the adaptability and flexibility of scheduling strategies.

The invention discloses a comprehensive energy system optimization scheduling model construction method considering uncertainty carbon transactions, comprising the following steps: predicting an obtained historical carbon price sequence to obtain a predicted carbon price; according to the predicted carbon price, establishing an uncertainty carbon transaction model based on carbon price prediction; establishing an improved conditional value-at-risk model based on the uncertain carbon transaction according to the carbon price prediction-based uncertain carbon transaction model; and according to the carbon price prediction-based uncertain carbon transaction model and the improved conditional value-at-risk model based on the uncertain carbon transaction, establishing a comprehensive energy system optimization scheduling model considering the uncertain carbon transaction. Furthermore, a quadratic programming hybrid algorithm based on a cross genetic mechanism is adopted to solve the integrated energy system optimal scheduling model considering the uncertain carbon transactions. The method has high superiority in the aspects of carbon capture level and total operation cost of the comprehensive energy system.

The invention discloses a multi-energy complementary system dynamic collaborative optimization method based on a geographic information system, and belongs to the technical field of energy system optimization. In order to solve the bottleneck problems of lack of operation feedback, disjunction of planning and scheduling and the like in the prior art, a real-time optimization architecture of space evaluation, capacity allocation, operation verification and closed-loop adjustment is provided. The method is characterized in that a hour-level operation model is constructed through mixed integer programming, and the actual performance of capacity configuration is accurately quantified; establishing a bidirectional feedback channel, and feeding operation indexes such as a load power shortage rate and a power abandoning rate back to an upper-layer capacity decision in real time; and an improved NSGA-II algorithm is adopted to realize dynamic balance of economy and reliability. According to the method, the adaptive capacity of the system to uncertainty is remarkably enhanced, the planning scheme is ensured to be continuously optimized in the whole life cycle, and a self-adaptive decision tool is provided for the renewable energy system.

The application discloses a kind of low-carbon scheduling methods of integrated energy system considering energy-carbon coupling, which is based on carbon emission flow theory, combined with the strong fitting ability of neural network, proposes the method of carbon flow constraint learning, converts the complex mapping relationship between power flow and carbon flow into mixed integer linear constraint, realizes the effective embedding of carbon flow constraint in optimization model. At the same time, in order to reduce the structural complexity of neural network, the sparse training strategy is introduced, the model parameter size is effectively compressed, and the ReLU activation function is linearized by the improved big-M method, the feasible region is gradually tightened by introducing the cut plane constraint, so as to significantly improve the solving efficiency of optimization model. Finally, the carbon flow constraint model is embedded in the integrated energy system optimization scheduling problem, the carbon emission reduction consciousness of load side is stimulated, the demand response behavior of load side based on its own carbon signal is guided, low-carbon energy adjustment is promoted, and low-carbon scheduling under energy-carbon cooperation is realized, to reduce the overall carbon emission level of the system.

The invention provides a multi-energy system scheduling modeling method, device, equipment and medium under severe weather, and relates to the technical field of comprehensive energy system optimization scheduling, and the method comprises the steps: obtaining comprehensive energy system data, and building an electric-gas-thermal coupled comprehensive energy system scheduling and optimization model based on the comprehensive energy system data; performing scene division on the original wind and light output data to generate a plurality of typical day scene data; taking the plurality of typical day scene data as input data, solving the electric-gas-thermal coupled integrated energy system scheduling and optimization model by using a hierarchical robust optimization algorithm to obtain an optimal solution, and outputting a final scheduling strategy according to the optimal solution; according to the method, multi-energy complementation and collaborative energy optimization are realized, the energy utilization rate of the comprehensive energy system is improved, the influence of wind and light uncertainty on the stability of the system is effectively reduced, and the method can better adapt to different scenes.