168 results about "Carbon price" patented technology

The invention relates to the technical field of data processing, and provides an intelligent risk control method for carbon asset transaction, which is used for solving the problems of data island, response lag, low efficiency, safety risk and the like in traditional carbon transaction. According to the invention, standardized access of a carbon emission permit trading system, a registration system and enterprise internal data is realized by constructing a carbon asset data middle platform, integrating a block chain and an RPA technology, a price fluctuation rate and a quota gap risk are calculated in real time based on Apache Flink, a carbon price trend is predicted through an LSTM + Attention model, and an intelligent contract is triggered to generate a hedging instruction; a three-level risk prevention and control system is constructed by adopting an ABAC model and biological characteristic verification, a quota regulation path is optimized through a graph neural network, automatic performance is driven, strategy self-adaption is realized in combination with PPO reinforcement learning and BERT policy analysis, and the problems of data islands, response lag, low efficiency and security risks in traditional carbon transactions are systematically solved.

The invention discloses an intelligent building energy-saving optimization platform and method based on carbon footprint tracking, and relates to the technical field of building energy saving and carbon emission management. The method is used for solving the problems of extensive carbon emission evaluation, rigid quota distribution and insufficient energy-carbon collaboration. A three-dimensional carbon density map is constructed by collecting people flow, equipment energy consumption and environment data in real time, and carbon emission hotspots are dynamically identified. And analyzing the association between the power grid and the renewable energy source through a carbon flow tracking model, and correcting a weight output contribution matrix. The characteristics of equipment energy efficiency, building material hidden carbon emission and the like are fused to construct a carbon emission gene entropy, a quota migration strategy is generated in combination with a game algorithm, and oriented transfer from high carbon to low carbon buildings is promoted. A double-ring collaborative framework is constructed, an inner ring chaos search optimization device starts and stops to suppress carbon density fluctuation, an outer ring carbon price mapping adjusts energy storage scheduling, accurate carbon emission tracing, quota dynamic allocation and energy-carbon deep collaboration are achieved, building low-carbon transformation is supported, and the building cluster carbon emission reduction efficiency is improved.

The invention provides a carbon emission digital management system based on a cloud platform. The carbon emission digital management system comprises a data acquisition layer, a hardware resource layer, a data management layer, a platform algorithm layer, an application layer and a display layer, according to the system, through multi-source data acquisition and data analysis based on an AI large model, artificial filling errors are avoided, meanwhile, carbon emission factors are dynamically adjusted through introduction of machine learning and automatic calculation, and the carbon emission accounting precision is comprehensively improved; secondly, the system is combined with a digital twinning technology to help enterprises to realize multi-level carbon emission trend analysis of groups, enterprises, processes, equipment and the like, comprehensive strategy optimization is carried out through multi-level data arrangement, and wider application services are provided; besides, the system is in butt joint with international standards such as the international carbon market and CBAM, can help enterprises to monitor carbon price fluctuation and predict in real time, intelligently adjust carbon tax and provide a compliant carbon transaction scheme, and helps the enterprises to reduce cost, thereby realizing comprehensive upgrading of carbon management from static statistics to intelligent prediction and optimization.

The embodiment of the invention discloses a multi-virtual power plant energy optimization method and device based on energy-carbon sharing. The method comprises the steps of establishing a master-slave game architecture of a power distribution system operator and each virtual power plant based on a transaction electricity price and a transaction carbon price of the power distribution system operator, and a transaction electricity quantity, a transaction carbon quota and equipment output of each virtual power plant; a dynamic pricing model for maximizing the income of a power distribution system operator is constructed based on a master-slave game architecture, an energy management model for minimizing the operation cost of the virtual power plant is constructed based on the master-slave game architecture, and a master-slave game double-layer optimization model for energy-carbon sharing of the multiple virtual power plants is determined based on the dynamic pricing model and the energy management model; and equivalently converting the master-slave game double-layer optimization model into a single-layer optimization model based on a Carlo-demander-Kuhn-Tuck condition, and solving the single-layer optimization model to obtain a target energy management strategy of each virtual power plant, thereby giving consideration to economic benefits and carbon emission reduction.

The invention relates to a collaborative optimization scheduling method and system based on low-carbon demand response, and the method comprises the following steps: constructing a source-network-load-carbon storage emission flow metering model, and obtaining the carbon emission data of each part during the operation of a power system; obtaining a dynamic carbon emission factor according to the carbon emission data of each part during the operation of the power system, issuing the dynamic carbon emission factor to a user side, guiding a user to change the power utilization habit, and achieving the dynamic transfer of the power utilization load; a stepped carbon transaction mechanism is formulated according to the power utilization load transfer condition of the user, and the user is stimulated to optimize the carbon emission cost through carbon quota distribution and carbon price grading; and constructing a multi-objective optimization problem with minimum carbon emission intensity and minimum total cost of the power system, and solving the multi-objective optimization problem through a near-end strategy optimization PPO algorithm to obtain an optimal scheduling strategy.

A flexible power distribution network carbon emission responsibility allocation calculation method based on a carbon emission flow belongs to the technical field of power system carbon emission management, and comprises the following steps: firstly, analyzing the carbon emission characteristics of a flexible power distribution network, and establishing a flexible power distribution network carbon emission flow calculation method; then, establishing a flexible power distribution network low-carbon optimization operation model based on an improved carbon emission flow theory; and finally, solving the model and introducing a Shapley value theory, researching the carbon emission responsibility allocation of the load side of the flexible power distribution network from the perspective of cooperative game, and determining the carbon emission responsibility of the terminal user of the flexible power distribution network. According to the method, each load node in the flexible power distribution network can have a reasonable carbon emission responsibility interval, stepped carbon prices are specified in different intervals, and stepped pricing of load side carbon emission responsibility can be more fair.

The invention relates to the field of energy dispatching, and particularly provides an intelligent energy station dispatching method and device based on artificial intelligence, a terminal and a medium, and the method comprises the steps: obtaining multi-source data of an energy station, and generating a short-term load prediction result and a medium-and-long-term load prediction result; a multi-objective optimization function is constructed with the minimum energy consumption, the minimum operation cost and the minimum carbon emission, a Pareto optimal solution set is generated through an NSGA-II algorithm, a final operation plan is selected as a scheduling scheme according to the real-time electricity price and carbon price weight, the scheduling scheme is disassembled into executable instructions, and the executable instructions are issued to a field control unit after safety certification; making a maintenance plan according to the medium-term load prediction result, and making expansion and reconstruction according to the long-term load prediction result; and continuously training and optimizing each model. According to the method, multi-source data is utilized, multi-time-scale accurate prediction is realized, multi-target collaborative optimization is carried out, and a scheduling plan is ensured to be safe and reliable.

The invention relates to the technical field of virtual power plant collaborative optimization, and discloses a virtual power plant multi-target carbon economy optimization method based on swarm intelligence, which comprises the following steps: S1, constructing a digital twinborn body of a virtual power plant, and synchronizing distributed energy output, load demand and carbon emission data of a physical VPP (virtual power plant) in real time; s2, establishing an energy-carbon economy dual-objective optimization model; s3, solving the dual-objective optimization model through an improved swarm intelligence algorithm, wherein the algorithm dynamically adjusts the weight of the economical efficiency and the weight of the carbon emission objective; s4, real-time data based on the digital twinborn body; and S5, outputting a Pareto optimal solution set. The total operation cost and the full life cycle carbon emission in the operation cycle of the virtual power plant are taken as double optimization targets, the target weight is adjusted through the dynamic carbon price sensitivity coefficient, carbon market signals are coupled, the decision-making deviation of high implicit carbon and operation pseudo-low carbon of equipment is avoided, and the multi-target decision-making scientificity of the virtual power plant under the carbon constraint is improved.

The invention discloses a low-carbon path real-time planning method and system based on multi-source data fusion and reinforcement learning. According to the invention, through a dynamic weight self-adjustment mechanism, the real-time adaptation capability of low-carbon path planning is significantly improved. Meanwhile, scenes such as traffic flow abrupt change, carbon price abnormity and energy station high load are recognized in real time through high-frequency scanning of multi-source fusion data, weights are dynamically adjusted through a formula, and planning can quickly respond to emergencies. For example, energy weight is reduced during charging pile queuing, emission constraint is enhanced when carbon price rises, planning lag caused by weight fixing in a traditional method is avoided, path selection better fits current environment changes, the problems of congestion and energy supplement shortage can be solved more timely in actual use, emission, time and cost are more accurately balanced under low-carbon constraint, and the method is suitable for popularization and application. In practical application, carbon emission can be effectively reduced, and user time and energy expenditure are saved.

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.

An optimized scheduling method for guiding the orderly charging of electric vehicles includes the following steps: S1. Establish an unordered charging load prediction model for electric vehicles based on the Monte Carlo method; S2. Introduce a carbon trading mechanism into the unordered charging load prediction model of electric vehicles in step S1 to calculate the carbon emissions and carbon quotas of power generation enterprises; S3. Introduce a reward coefficient ξ1 and a carbon trading cost growth rate τ1 into the conventional stepped carbon price to establish a reward and punishment stepped carbon price model; S4. Establish a dynamic time-of-use electricity price model based on the reward and punishment stepped carbon price; S5. Establish an electricity price regulation model for electric vehicles; S6. Establish a multi-objective optimization function for the orderly charging of electric vehicles; S7. Adopt a multi-objective non-dominated genetic NSGA-II solution algorithm; The present invention guides electric vehicle users to perform orderly charging behaviors by using a regulation method based on the reward and punishment stepped carbon price and the dynamic time-of-use electricity price, thereby effectively achieving the effect of peak shaving and valley filling of the power grid and reducing the fluctuation of the power grid.

The invention relates to an integrated energy system optimization method considering a carbon emission reward and punishment mechanism and shared electrochemical energy storage, and the method comprises the following steps: carrying out the modeling of an integrated energy system which comprises energy supply, energy conversion, load and shared electrochemical energy storage; constructing a peak-flat-valley period stepped carbon emission mechanism considering the carbon emission difference of different energies and a dynamic carbon price factor, and determining a corresponding carbon transaction cost / reward according to the total carbon emission of the integrated energy system in a scheduling period; based on a capacity leasing and power service mechanism, modeling is carried out on the cost of the shared electrochemical energy storage mode; an optimization scheduling problem is constructed by taking system operation cost minimization and clean energy utilization rate improvement as targets; and solving the optimization scheduling problem to obtain an optimal output scheme and an energy storage charging and discharging strategy of each energy device in the integrated energy system, thereby realizing optimization of the integrated energy system.

The invention discloses a multi-virtual power plant energy carbon transaction price determination method and system based on a master-slave game. The method comprises the following steps: determining a master-slave game framework between a power distribution system operator and a plurality of virtual power plants; based on a master-slave game framework, a double-layer optimization model of energy and carbon sharing of the multiple virtual power plants is established, the upper layer of the double-layer optimization model is a dynamic pricing model with the purpose of maximizing the income of a power distribution system operator, and the lower layer of the double-layer optimization model is an energy management model with the purpose of minimizing the operation cost of the virtual power plants; and establishing a double-layer Kriging meta-model taking the transaction electricity price and the carbon price as inputs and the transaction electricity quantity and the carbon quota quantity as outputs, fitting and replacing the energy management model of the double-layer optimization model by adopting the double-layer Kriging meta-model, and solving to obtain a global optimal solution. According to the method, sharing and circulation of energy and carbon quotas among virtual power plants are effectively promoted, the economic and environmental benefits are improved, and the privacy security of each subject can be protected.

The invention discloses an electric vehicle service network low-carbon charging method based on carbon emission flow, which comprises the following steps of: 1, establishing a daily charging load model of an electric private car by considering travel starting time, travel ending time, daily driving mileage and air conditioner energy consumption of the electric private car; step 2, considering the basic load of the network node and the charging load of the electric vehicle, obtaining the dynamic carbon potential of the node of the service network of the electric vehicle, and recording the carbon emission obtained by combining the charging amount and the corresponding carbon potential; step 3, dividing a service network step carbon emission responsibility range and a corresponding step carbon price interval based on a Shapley value; and 4, establishing a low-carbon charging optimization model of the electric vehicle service network, and redistributing the charging load capacity of the electric vehicle. For an electric vehicle service network, carbon emission caused by charging of the electric vehicle is obviously reduced, the carbon emission cost, namely the operation cost, is reduced, and the low-carbon property of the electric vehicle is fully exerted.

The invention discloses a shadow carbon price-based power transformation path analysis method and system, and relates to the technical field of power transformation path analysis, and the method comprises the following steps: dividing a path in a power transformation process into a plurality of node regions, obtaining the power supply state data of each region, extracting an abnormal power supply coefficient, an equipment overload coefficient and an abnormal communication coefficient from the power supply state data; constructing a power supply fault model based on a neural network by using the power supply abnormal coefficient, the equipment overload coefficient and the communication abnormal coefficient, and generating a power supply fault coefficient; and acquiring a power supply fault coefficient of each node region, drawing a power supply-fault curve graph, judging a region with a fault in the power transformation process based on the power supply-fault curve graph, and performing priority processing. Through power supply fault analysis, the problem that various abnormal faults of power supply cannot be found and eliminated in time in the power transformation process is solved.

The invention provides a low-carbon integrated energy system modeling method based on a hybrid energy storage system. And constructing a multi-dimensional constraint and cost optimization objective function, and establishing a global optimization framework of the integrated energy system. Wherein the balance constraint and the assembly constraint ensure dynamic matching of electric / hot / cold / gas multi-energy flow and cooperative operation of equipment, and the problem of unbalanced supply and demand of a traditional system is solved. The carbon emission constraint is divided through a dynamic carbon valence interval, the carbon emission and the carbon cost are in nonlinear correlation, a low-carbon technology path is guided, the green certificate constraint converts excess renewable energy power generation into economic benefits, and dual excitation of environmental protection and economy is formed. And the target function comprehensively optimizes equipment investment, maintenance cost and market income, and drives multi-energy complementation and full life cycle cost optimization. The system is adaptive to renewable energy fluctuation, load change and energy price fluctuation through optimal configuration of system output and equipment capacity, and economical and efficient operation under the low-carbon target is achieved.

The invention relates to the technical field of power system resource optimization scheduling, in particular to a deep scheduling method and system for deep peak regulation of a coal-fired unit, and the method comprises the steps: collecting multi-dimensional operation parameters of the unit, a deep peak regulation instruction and a carbon price signal of a carbon emission permit trading market, and achieving timestamp alignment; constructing a five-dimensional security constraint model associated with the economic cost boundary; taking peak regulation income maximization as a target, combining fire coal purchase cost, carbon transaction cost and equipment maintenance cost to construct a target function, adopting a dynamic planning algorithm to solve an economic dispatching scheme, and executing a cross-system cooperation strategy; and on the basis of LSTM-based equipment life prediction and digital twin simulation, triggering a cross-system correction strategy. According to the method, the commercial cooperation problem of economy, environmental protection and equipment reliability in deep peak regulation is solved, and the peak regulation income maximization of the coal-fired unit in an electricity market environment is realized.

The invention discloses an electricity price prediction method and system considering electricity-carbon real-time coupling transaction, and belongs to the field of electricity price prediction, and the method comprises the following steps: S1, monitoring and recording the power consumption of each node in real time, and storing the power consumption data in a central database; s2, calculating the carbon emission of each node by using a preset carbon emission coefficient according to the power consumption data in the step S1, and tracking the carbon emission flow; s3, calculating the power utilization carbon emission intensity of each node in a specific time period based on the real-time monitored power consumption data in the step S1 and the tracked carbon emission flow data in the step S2; s4, on the basis of the collected carbon quota price data on the market, in combination with the real-time electricity utilization carbon emission intensity of the nodes, calculating the carbon price corresponding to electricity utilization of each unit, and obtaining the dynamic electricity utilization carbon price; and S5, electricity market transaction data and electricity demands of each node are collected in real time, the basic electricity price and the dynamic electricity utilization carbon price are embedded into the electricity price prediction model, and the coupled real-time electricity price is calculated. According to the electricity price prediction method and system considering the electricity-carbon real-time coupling transaction, the influence of the carbon emission cost on the electricity price can be reflected, more accurate price signals are provided for electricity users and market participants, and electricity transaction decisions and carbon emission management are optimized.

The invention belongs to the technical field of power systems, and particularly discloses a micro-grid electricity-carbon joint transaction method and system and a medium, and the method comprises the steps: constructing a regional interconnection micro-grid system model; constructing a local electricity-carbon combined market mechanism, carrying out order matching by adopting a multi-round bilateral auction mode, determining a transaction result in combination with an electricity price and carbon price combined bidding rule, and carrying out trend constraint verification; the method comprises the following steps: constructing a multi-agent Markov decision process model based on a micro-grid model and a market mechanism, and setting a state space, an action space and a multi-target reward function; and a multi-agent near-end strategy optimization algorithm MAPPO-TDSA fusing task decomposition and an attention mechanism is adopted to train each agent strategy network, and settlement with an external power market and a carbon trading market is carried out according to a micro-grid trading execution result and a power carbon quota income and expenditure condition. According to the method, energy-carbon collaborative transaction and intelligent regulation and control between regional micro-grids are realized, and the method has remarkable low-carbon property, autonomy and strategy optimization capability.

The invention relates to the technical field of comprehensive energy system optimization scheduling, in particular to an energy-carbon excitation-based farm comprehensive energy system optimization scheduling method, which comprises the following steps: S1, constructing a comprehensive energy system covering an energy operator and farm users, providing electric heating energy by the operator, and supplying heat by the farm users through biogas power generation, the three types of loads are combined to construct an equipment and load model; s2, carbon potential is calculated based on a carbon emission flow theory, an energy-carbon price is formulated, and a stepped carbon transaction and segmented subsidy mechanism is adopted to stimulate a user to use low-carbon energy; s3, constructing a master-slave game model, performing upper-layer pricing excitation and lower-layer optimization response, and performing joint iterative solution by adopting a genetic algorithm and GUROBI; according to the invention, by constructing a master-slave game scheduling framework and introducing an energy-carbon joint pricing and stepped carbon excitation mechanism, collaborative optimization of system economy and a low-carbon target is realized, and user response enthusiasm and carbon emission reduction potential are effectively improved.

The invention discloses a power distribution network multi-type flexible resource low-carbon scheduling method based on carbon emission flow, and relates to the technical field of power system low-carbon scheduling, and the method comprises the steps: constructing a scheduling time period set of a discrete time domain, and building an equivalent lossless network model; power flow calculation is carried out, and a node-branch carbon flow mapping relation is established; according to the carbon emission intensity of the unit, the carbon flow rate and node carbon emission flow of each branch are calculated; performing differential approximate calculation on the node injection power to obtain a carbon marginal coefficient of each node; generating a time-varying carbon price signal of each node in combination with an external carbon price reference; constructing a weighted combination objective function based on the node time-varying carbon price signal; and solving a weighted combination objective function and constraint conditions by adopting a distributed multi-agent collaborative optimization strategy. According to the invention, collaborative scheduling of multiple types of flexible resources under a low-carbon target is realized, and the carbon emission reduction effect is improved.

The invention provides a power distribution system area energy autonomous optimization method under new energy bearing capacity constraint. The method comprises the following steps: acquiring basic data of a target power distribution system area; a Voronoi-energy flow entropy dynamic space partitioning method is adopted, autonomous units are divided, and energy flow entropy features are calculated; generating initial new energy installed capacity, energy storage capacity and bearing capacity threshold values according to the space boundary and energy flow entropy characteristics of each autonomous unit; a Stackelberg game model is adopted, a dynamic electricity price, a carbon price and a deviation reward and punishment mechanism are introduced, a distributed iteration method is combined, and an operation scheduling strategy of each autonomous unit is determined; and performing rolling optimization and scheduling adjustment according to the feedback data, and dynamically updating the space boundary, the bearing capacity threshold and the scheduling strategy of the autonomous unit. According to the method, the energy management capability of the power distribution system is effectively improved, the new energy resource configuration is optimized, the scheduling cost is reduced, and the flexibility and stability of the system are enhanced.

The invention discloses an optimal scheduling method for a regional integrated energy system, and relates to the technical field of energy optimization. Comprising the following steps: step 1, multi-source data hierarchical acquisition and preprocessing; step 2, multi-time scale uncertainty scene modeling is carried out; step 3, constructing a multi-objective optimization model; 4, intelligent algorithm solving and dynamic scheduling are carried out; 5, carrying out constraint processing and resource integration; and 6, carrying out closed-loop correction and strategy optimization. According to the regional integrated energy system optimization scheduling method, a dynamic relaxation factor mu (t) is introduced to adjust equipment climbing constraint in real time, and a virtual energy storage equivalent model is combined to integrate a transferable load, so that when the load of the system suddenly increases, the equipment power adjustment fluctuation is controlled within 10% of rated power, frequent out-of-limit of energy storage is avoided, and meanwhile, the optimal scheduling of the regional integrated energy system is realized. The grading pricing mechanism excitation system of the stepped carbon transaction model preferentially consumes new energy, and the carbon emission is greatly reduced compared with that of a traditional fixed carbon price model.

The invention provides a power plant carbon emission data full life cycle management method and device, and relates to the technical field of data processing, and the method comprises the steps: collecting production, fuel and coal quality test system multi-source data in real time through a standard interface, and forming a dynamic data flow; predicting the carbon content of the fire coal element based on a BP neural network, and calculating the carbon emission by combining an emission factor method; carrying out back calculation on the discharge amount by using a mass balance method, analyzing and verifying the relevance between data and an accounting result through multiple regression, and triggering correction when an error exceeds a threshold value; a double-stage attention deep learning network is adopted to predict the carbon price in a rolling mode, a carbon asset dynamic analysis result is generated in combination with a quota estimation model, real-time emission data, quota surplus and shortage and the carbon price trend are displayed through a visual interface, and graded early warning is conducted on abnormal data. According to the method, full-life-cycle automatic management is realized, the data acquisition real-time performance and accounting precision are improved, the data authenticity and traceability are guaranteed, and the carbon asset management decision support capability is optimized.

The invention discloses a coal-fired power plant carbon emission intelligent control method and system based on machine learning, and relates to the technical field of coal-fired power plant carbon emission, and the method comprises the four steps: building a three-level sensing network to collect carbon flow data, importing various parameters to construct a carbon flow digital twinborn body, building a real-time mapping link, and obtaining twinborn body boiler data; establishing a solid waste related mapping model, and calculating and outputting a coal blending combustion proportion through an optimal solution; predicting the carbon release amount within 5 minutes in combination with boiler data and a blending combustion ratio, constructing a carbon capture agent model, and judging whether elastic adjustment is triggered or not through an improved Sarsa algorithm game; and analyzing a quota consumption rule based on prediction data, predicting a carbon price, optimizing multiple targets and analyzing a Pareto optimal strategy. According to the method, full-chain collaborative management and control are realized, the carbon emission control precision and intelligent level are improved, environmental protection standard reaching, quota management and cost control are balanced, and low-carbon and efficient operation of a power plant is assisted.

A VCG mechanism-based comprehensive energy system optimization operation method in an electricity-gas-carbon combined market comprises the following steps: constructing a comprehensive energy system coupling model integrating electric power, natural gas, carbon cycle and green certificate transaction, maximizing social welfare through a distributed robust optimization model, processing carbon price and green certificate price uncertainty by adopting a Wasserstein fuzzy uncertainty set, and obtaining a comprehensive energy system optimization model; and calculating an external payment value of each unit by using a VCG mechanism, endogenously determining an electricity price and a gas price, and finally outputting an optimal scheduling scheme meeting multiple constraints. The method can solve the problems that an existing single market mechanism is low in resource allocation efficiency, insufficient in carbon emission reduction excitation and the like, the reliability of multi-market data association analysis is improved by mining energy conversion, carbon circulation and other associations, the robustness under data limitation is enhanced through a Wasserstein uncertainty set, strategy quotation distortion is avoided through a VCG mechanism, and the reliability of multi-market data association analysis is improved. The data analysis reliability and optimization decision accuracy of the complex energy system are remarkably improved, and support is provided for construction of a novel electric power system.

The invention discloses a multi-objective optimization decision-making method and system for sewage treatment based on OLAP reinforcement learning, and solves the problems that an existing sewage treatment control method neglects carbon emission, is extensive in cost control and does not integrate a carbon transaction mechanism. The method comprises the following steps: constructing an OLAP cube, and generating an optimal historical strategy set; establishing a state set according to the sewage environment parameters and the carbon price; an action set is established according to the optimal historical strategy set, and an action priority strategy is set according to the carbon emission weight partition; establishing a multi-target reward function dynamically adjusted according to the carbon price; constructing each controller agent model for training until the strategy converges; and dynamically outputting an optimal strategy by the intelligent agent according to the change of the carbon price. According to the method, a multi-dimensional OLAP cube is constructed to analyze the incidence relation between key variables, a plurality of process control agents are constructed, reinforcement learning collaborative optimization of working condition adjustment is achieved, the carbon emission item optimization weight is adjusted according to the real-time carbon transaction price, and dynamic policy adaptation is achieved.

The invention discloses an integrated energy system multi-time scale optimization method and system considering electric-carbon coupling. The method comprises the following steps: constructing an electric-carbon model of each device in an integrated energy system; constructing an electricity-carbon coupling price model based on the electricity price of the electric power spot market and the floating carbon price; based on the electricity-carbon model of each device and the electricity-carbon coupling price model, constructing a multi-time scale regulation and control optimization model with the goal of minimizing the total cost of the system; and solving the multi-time-scale regulation and control optimization model under the condition of meeting a constraint set comprising a power balance constraint, a reserve capacity constraint, a power-carbon coupling price constraint, an intra-day regulation constraint, a real-time deviation constraint and a power grid security constraint of each device of the system to obtain an optimization scheduling scheme. According to the invention, through deep fusion of an electricity-carbon coupling mechanism, the time-of-use electricity price signal and the multi-time scale carbon price signal of the electric power spot market cooperatively guide the optimal scheduling of the integrated energy system, and the low-carbon toughness and the operation stability of the urban integrated energy system in the electric power spot market are enhanced.

The invention relates to an interval value carbon price prediction method based on multi-source data fusion and deep learning integration, and the method comprises the following steps: obtaining the actual historical transaction data of a carbon market, collecting the maximum price and the minimum price of the daily actual transaction of the carbon market, and determining an interval value carbon price sequence; key external driving factors influencing the carbon transaction price are screened through feature importance analysis, and data alignment is conducted on the key external driving factors of different market transaction days through a cubic spline interpolation method; cEEMDAN-VMD dual decomposition is adopted, and higher-precision multi-scale characterization of an original interval value carbon price sequence is achieved; and by taking the decomposition result and the determined external key driving factor as input and the carbon price prediction interval as output, constructing a carbon price interval prediction model, and finally outputting to obtain the carbon price prediction interval containing upper and lower boundary values. The method can effectively cope with the non-stationary and non-linear characteristics of the carbon valence sequence, and is good in expansibility and adaptability.

The invention discloses an integrated energy system flexible optimization scheduling method based on a large language model. The method comprises the following steps: S1, constructing a multi-source heterogeneous knowledge base and a rule logic coding system of the comprehensive energy system; s2, training a large language model agent with a dynamic reasoning capability in the field of the integrated energy system; s3, analyzing a user input demand, and constructing an optimal scheduling scene comprising adjustable equipment, a scheduling time period and a target weight; s4, dynamically predicting the carbon price and the energy price in the scheduling time period; s5, establishing a flexible optimization scheduling model containing a target function and constraint conditions according to the optimization scheduling scene; and S6, solving the flexible optimization scheduling model, updating model cognition in real time according to user feedback and a scheduling result, and realizing adaptive optimization of a scheduling strategy. According to the invention, the flexibility and adaptability of the optimization scheduling process can be effectively improved, and flexible, efficient and low-carbon operation of the integrated energy system is facilitated.