79 results about "Final energy" patented technology

The invention provides a building energy consumption real-time monitoring and carbon emission evaluation method based on digital twinning, and the method comprises the steps: obtaining regional energy supply real-time data and building group load demand data, predicting an energy supply fluctuation trend and a load change trend, and obtaining a short-term supply and demand dynamic prediction result; adjusting the operation mode of the building group combined cooling heating and power system in real time according to the mode switching optimization scheme, dynamically matching the output change of the distributed energy, and feeding back the output change to the digital twinborn model; carbon emission data is extracted from the optimized load distribution scheme, a digital twinborn model is used for predicting the total carbon emission amount and peak value change trend, the threshold value and constraint of carbon emission control are adjusted, and a final energy scheduling scheme is generated; and obtaining operation data according to the final energy scheduling scheme, calculating the energy utilization efficiency and the carbon emission reduction amount of the building group through an energy efficiency evaluation method preset in the digital twin model, and obtaining an execution effect evaluation result of the scheduling scheme.

A regional building cooling and heating load artificial neural network energy distribution optimization method disclosed by the present invention comprises the steps of obtaining inter-regional topological relation data and load-related data, constructing a graph network model to capture spatial dependency, fusing meteorological data and historical load records to generate a multivariable dynamic data set, and obtaining the optimal energy distribution of the cooling and heating load artificial neural network. Processing the multivariable dynamic data set by adopting a graph convolutional neural network to obtain an initial prediction result, adjusting the initial prediction result through an artificial neural network to generate adjusted load distribution data, and analyzing by combining a heat transfer rule and a time sequence to obtain spatial and temporal distribution characteristics; and integrating equipment efficiency constraint and cost fluctuation data by adopting a multi-objective optimization algorithm to obtain an optimized objective function value, adjusting equipment dynamic parameters through deep reinforcement learning to obtain a parameter adjustment scheme, and optimizing an energy distribution proportion by adopting a linear programming algorithm to obtain a final energy distribution scheme.

The invention discloses an energy-saving amount calculation method based on a lighting system after building lighting energy-saving transformation, which relates to the technical field of intelligent lighting, and comprises the following steps: integrating preprocessed environment monitoring data and lighting quality image parameters by using a multi-modal data fusion mechanism, constructing an initial energy consumption reference value model to carry out regression analysis on comprehensive feature data, and calculating the energy-saving amount of the lighting system after building lighting energy-saving transformation; updating the initial energy consumption reference value model to generate a final energy consumption reference value model; and the remote energy consumption detection and diagnosis center carries out comparative analysis on the energy consumption reference value of the initial energy consumption reference value model and the energy consumption reference value of the final energy consumption reference value model, and outputs an energy saving amount calculation result in combination with a dynamic energy saving amount correction mechanism. According to the method, the preprocessed environment monitoring data and the illumination quality image parameters are integrated by using a multi-modal data fusion mechanism to generate the comprehensive feature data, and unified modeling of multiple factors influencing energy consumption is realized.

The invention relates to the field of port energy management, and provides a bulk cargo wharf production operation process-based energy consumption prediction method and system, and the method comprises the steps: obtaining a cargo attribute information set and an equipment parameter set, and constructing a linkage database through context fusion, time sequence storage and data cleaning; based on a cargo attribute information set splitting process, performing verification and collaborative division in combination with an equipment archive and an operation emergency degree coefficient, and performing risk assessment according to theoretical and actual parking duration to generate a link list; according to the link list and the real-time working condition, a candidate device set or a compensation scheme is output in combination with the mapping table, a collaborative operation trigger signal is generated, and a device allocation list is generated through resource allocation when a collaborative scheme is started; constructing an initial energy consumption prediction model, and carrying out online iterative optimization; and calculating each operation link and a final energy consumption prediction result, and generating a final energy consumption prediction report. According to the method, dynamic planning of a collaborative operation process and adaptive prediction of energy consumption are realized, and the method is suitable for port smart energy management and automatic scheduling.

The invention provides a carbon emission analysis method and device, electronic equipment and a storage medium, and relates to the technical field of carbon emission data processing.The method comprises the steps that multi-source real-time data and energy consumption data of all energy consumption nodes in a park in the current time period are obtained, and multi-dimensional key features are extracted; determining initial energy structure data; according to the association relationship between the energy consumption node in the park and other energy consumption nodes, performing association correction on the initial energy structure data to obtain final energy structure data; then determining a dynamic emission factor matrix of the energy consumption nodes; performing carbon emission simulation on the energy consumption node through the hybrid model to obtain a carbon emission result of the energy consumption node; and performing dynamic analysis and explanation of carbon emission through an attention mechanism to obtain a carbon emission analysis result of the park in the current time period. According to the invention, high-precision dynamic analysis of park carbon emission is realized.

The invention discloses an energy storage system control method and system based on time-of-use electricity price and multi-modal optimization, and the method comprises the steps: simulating supply and demand fluctuation in a complex scene through a pre-constructed energy storage system control strategy model based on deep reinforcement learning, dynamically optimizing a charging and discharging plan of energy storage equipment, and generating an energy storage resource distribution efficiency optimization scheme; generating a real-time electricity price adjustment scheme by adopting a game theory price adjustment algorithm based on the energy storage resource distribution efficiency optimization scheme, the real-time demand of power grid supply and demand balance, the user electricity consumption behavior change and the power grid operation state dynamic state; generating a user behavior response data set through a pre-constructed user behavior response model based on the real-time electricity price adjustment scheme in combination with user economic benefit protection requirements; and calculating a fluctuation ratio of a power grid load change trend by combining the user behavior response data set with real-time monitoring data through a power grid supply and demand balance dynamic evaluation algorithm, and determining a final energy storage scheduling scheme. The purposes of real-time monitoring and collaborative optimization of energy storage system control are achieved.

A particle acceleration and extraction system includes a cyclotron having a stripping assembly and a target. The cyclotron includes an acceleration chamber and is operable to generate a magnetic field and an electric field in the acceleration chamber such that charged particles in the acceleration chamber are accelerated along a spiral path extending outward and at increasing energies from an initial energy E1 to a final energy E2, E2 being greater than E1. The target defines a target location outside of the acceleration chamber. The stripping assembly is positioned in the acceleration chamber and is operable to extract a charge from the charged particles at an intermediate location of the outward spiral path whereby the post-stripping assembly particles are directed towards the target location. The charged particles have an intermediate energy E3 at the intermediate location that is between E1 and E2.

The invention discloses a method, a system, equipment and a medium for energy management and economic dispatching optimization of an optical storage and charging system, and relates to the technical field of optical storage and charging. The comprehensive operation state model represents an operation rule and an economic index of the optical storage and charging system in a future scheduling period; based on the comprehensive operation state model, solving a multi-objective optimization problem to obtain a Pareto optimal solution set considering economy, environmental protection property and service quality; and selecting an optimal scheduling strategy from the Pareto optimal solution set by adopting a multi-agent equilibrium game mechanism so as to determine a final energy management and economic scheduling scheme. According to the method, the problems of difficulty in multi-target coordination, insufficient electricity price response capability and user behavior modeling simplification in the existing energy management technology of the optical storage and charging system are solved, so that the overall benefit of the system is better, the method can adapt to various market mechanisms and different meteorological conditions, and the application scene is wide.

The invention discloses an energy storage power station multi-time-scale optimization scheduling method and system fusing adaptive distribution robustness and model prediction control, and the method comprises the following steps: obtaining the data of an energy storage power station, and solving a hierarchical planning model containing weekly-ahead distribution robustness optimization and day-ahead adaptive distribution robustness optimization; obtaining a robust day-ahead energy storage power scheduling plan and a charge state reference trajectory; respectively taking the day-ahead energy storage power scheduling plan and the charge state reference trajectory as a center reference and a terminal constraint of a model prediction controller, and performing rolling optimization solution in each control period by using the model prediction controller to obtain a corresponding power set value; and superposing the power set value with a fine tuning power amount to generate a final energy storage system output power instruction. On the premise of ensuring the robustness of the system, the decision conservative property is obviously reduced, and the economic benefit and the execution precision of the scheduling plan are improved.

The invention discloses an inter-pack balanced power transmission system and method of a battery pack, and relates to the technical field of battery management, and the method comprises the steps that each slave control module collects data in real time, and uploads the data to a master control module; the main control module distributes a dynamic weight factor for each battery pack according to the health state of each battery pack and the operation efficiency of the corresponding direct-current converter, generates a dynamic optimal bus voltage reference value, and controls the main converter to adjust the common direct-current bus voltage to the reference value; when it is judged that inter-group energy transmission is needed, an energy transmission instruction is issued to a related slave control module; analyzing the expected efficiency of a direct energy transmission path and a relay energy transmission path through a relay battery pack, selecting a path with higher expected efficiency as a final energy transmission scheme, and issuing the final energy transmission scheme to a related slave control module; and the slave control module generates a charging and discharging control instruction according to the energy transmission scheme to complete balanced power transmission.

The invention discloses a generalized energy storage equivalence model construction method based on multi-type micro-grid mapping, and relates to the technical field of energy storage model construction, and the method comprises the steps: dividing an energy storage unit into a plurality of equivalence model candidate structures through a graph neural network model based on an electrical topological graph and a node state of an energy storage system; model parameters are quickly initialized and calibrated online based on meta learning; deep reinforcement learning dynamic decision structure switching and parameter optimization are introduced; and adopting Monte Carlo Dropout to evaluate the parameter confidence and trigger model rollback, and outputting a final energy storage equivalent model. According to the method, the accuracy and robustness of the model under the dynamic working condition are improved, the uncertainty in the modeling process can be sensed in real time, rollback correction is actively carried out, the reliability and engineering availability of model output are ensured, and the method is particularly suitable for energy storage system modeling and control scenes with high requirements for the response speed, the adaptive capacity and the operation stability.

The invention belongs to the technical field of power system energy storage, and provides an energy storage planning method and system for peak clipping and valley filling of a regional power grid, and the method comprises the steps: dynamically recognizing the peak-valley time period of standardized load characteristic data through variational mode decomposition and Hilbert transformation, and calculating the peak-valley contribution degree index of each sub-region; obtaining a sub-region load distribution mode; establishing an energy storage-demand response collaborative optimization framework; optimizing site selection and capacity configuration of the energy storage system to obtain an initial energy storage planning scheme; and dynamically adjusting the initial energy storage planning scheme by adopting a near-end strategy optimization algorithm and taking the peak-valley smoothing reward function as a target to obtain a final energy storage planning scheme so as to realize real-time peak clipping and valley filling of the regional power grid. According to the technical scheme of the invention, through a technical path of'accurate identification-dynamic coupling-collaborative optimization ', multi-objective optimization which is difficult to consider by a traditional method is realized, and an innovative solution is provided for stable operation of a high-proportion renewable energy power grid.

The invention provides a charge and discharge control method and system for a liquid air energy storage ship based on a neural network, and relates to the technical field of energy storage ships, and the method comprises the steps: generating a control instruction of a corresponding link based on a final time node decision outputted by a neural network model; executing the control instruction, namely controlling the open sea liquefied air equipment to start or stop liquid air preparation at the final preparation time node; controlling the ship to start navigation at the final transportation start navigation time node; controlling the port gasification power generation device to start or stop power generation at the final energy release power generation time node; and in the process of liquid air preparation, ship transportation or port energy release power generation, monitoring the change of multi-source real-time data in real time, and inputting the changed data into the neural network model again so as to dynamically adjust and update the final time node decision. According to the method, the maximization of the comprehensive benefit of operation is realized, the value window of the peak period of the power grid can be accurately captured and responded, and low-efficiency or invalid discharge is avoided.

The present invention proposes a method and device for optimizing energy storage configuration based on simulation. The method is based on the method for optimizing energy storage configuration based on simulation. The energy storage parameter range set by the user is modified by a numerical calculation method to obtain a variety of configuration combination parameters. Under each set of energy storage configuration parameters, a sequential Monte Carlo sampling method is used to randomly generate a charge and discharge power curve for simulation. When generating the charge and discharge power curve, parallel calculation is performed to greatly save operating costs and time. The final energy storage configuration parameters are obtained by maximizing the average daily return on investment as an evaluation indicator. The present invention overcomes the problem in existing research that the contradiction between the leveling effect and the economic benefit cannot be fully coordinated, avoids the discrepancy between the model and the actual operation, realizes the coordinated optimization configuration of the capacity and power of the energy storage system, can be directly used in actual industrial production applications, and assists wind power plants in determining the optimal combination of energy storage capacity and power.

The invention belongs to the technical field of rail transit intelligent energy supply, particularly relates to an energy distribution method and system for a rail transit station photovoltaic and energy storage system, and aims to solve the problems of single feature learning dimension, poor multi-objective optimization balance and dynamic feedback response lag in the prior art. The method comprises the following steps: constructing a multi-subject space-time incidence matrix, carrying out feature learning by adopting a space-time double-scale attention fusion deep belief network, establishing a three-dimensional energy flow coupling tensor mining energy supply-demand relationship, constructing a multi-target optimization model based on a weighted ideal point method to generate a preliminary strategy, and carrying out multi-target optimization on the basis of the preliminary strategy; and parameters are dynamically adjusted by using an adaptive gradient feedback correction model, and a final energy distribution strategy is obtained through multiple rounds of iterative optimization. According to the method, the problems of single feature learning dimension, poor multi-objective optimization balance and dynamic feedback response lag in the prior art are solved, the energy supply and demand prediction precision is improved, and collaborative optimization of energy supply economy, environmental protection property and equipment reliability is realized.

The invention discloses an AI-based green building energy-saving evaluation management system, and relates to the field of energy-saving management, and the system comprises a region division module which is used for carrying out the partitioning of the internal space of a building according to a preset initial standard, forming an initial region range containing a plurality of power utilization function devices, and carrying out the dynamic adjustment of the division range of each region; the equipment analysis module is used for reading functional characteristics of the electric equipment in the current area, identifying an operation mode, a use scene and basic energy consumption parameters of the equipment and generating an equipment functional characteristic set; the final energy-saving strategy not only can represent the common demands of most people in the area, but also can respect the individual differences, so that the system achieves the energy-saving goal, meanwhile, the user discomfort and complaint rate caused by a forced unified strategy are reduced, the system can cope with various complicated and changeable internal and external conditions in building use, and the system has a wide application prospect. And the continuity and the stability of the energy-saving effect are ensured.

The application relates to the technical field of compressed air energy storage, and discloses an energy storage method and system for compressed air in an aquifer, which can select the most suitable aquifer for storing the excess power of a compressed air storage power plant according to the actual state of the aquifer when the excess power needs to be converted into compressed air and stored in the aquifer, ensures that the energy storage efficiency is relatively high, reduces energy loss, and reduces the cost; in addition, the suitable energy storage mode can be selected according to the actual aquifer state of the final energy storage aquifer, the energy conversion efficiency coefficient is ensured to be low, the operation cost is reduced, and the overall energy utilization efficiency is ensured.

The invention provides an energy storage prediction method, system and device, and relates to the technical field of electric energy storage, and the energy storage prediction method comprises the steps: obtaining a bus voltage signal in a current time period through a common connection point of a microgrid, and extracting a quantum phase perturbation sequence from the bus voltage signal; identifying and separating a secondary modulation component of the bus by using an adaptive noise shaping algorithm; performing unsupervised clustering on the secondary modulation components by adopting a density peak clustering algorithm to obtain a plurality of aging mode clusters, and extracting statistical characteristics of the aging mode clusters; obtaining an initial residual energy evaluation value through the variable coefficient regression sub-model; carrying out ampere-hour integration on the instantaneous value sequence, determining an estimated covariance of a statistical mean channel, and obtaining an estimated covariance of a Kalman filtering channel through Kalman filtering prediction correction circulation; and finally, according to the estimation covariance of the two channels, carrying out weighted fusion on the initial residual energy evaluation value to obtain a final energy evaluation value. According to the invention, the prediction adaptability and stability are improved.

The invention discloses a provincial power system pumped storage power station configuration method based on an NNC-MILP method, and belongs to the technical field of pumped storage power station configuration. Comprising the steps that S1, a peak regulation demand model is constructed based on provincial power system composition equipment, and the peak regulation demand model is used for obtaining a planning target annual peak regulation demand evaluation result; s2, constructing a pumped storage power station power-capacity configuration model, and constructing a dual-objective function based on the pumped storage power-capacity configuration model and the peak regulation demand model; solving the dual-objective function by adopting an NNC method to obtain a dual-objective configuration scheme; and S3, measuring and calculating the suppression effect of the power abandoning time and the power shortage time of the pumped storage power station after configuration based on the double-target configuration scheme and the return-on-investment ratio to obtain a final energy storage configuration scheme. According to the method, the power abandoning / shortage, the duration, the peak value, the power abandoning / shortage time sequence distribution, the power abandoning / shortage coverage and the alternating condition are comprehensively considered, and the annual peak regulation demand of the planning target is accurately depicted.

Ion implantation systems and methods implant varying energies of an ion beam across a workpiece in a serial single-workpiece end station, where electrodes of an acceleration / deceleration stage, bend electrode and / or energy filter control a final energy or path of the ion beam to the workpiece. The bend electrode or an energy filter can form part of the acceleration / deceleration stage or can be positioned downstream. A scanning apparatus scans the ion beam and / or the workpiece, and a power source provides varied electrical bias signals to the electrodes. A controller selectively varies the electrical bias signals concurrent with the scanning of the ion beam and / or workpiece through the ion beam based on a desired ion beam energy at the workpiece. A waveform generator can provide the variation and synchronize the electrical bias signals supplied to the acceleration / deceleration stage, bend electrode and / or energy filter.

The invention relates to the technical field of compressed air energy storage, and discloses an energy storage method and system for compressed air of an aquifer, according to the method, when electric power is excessive and needs to be converted into compressed air and stored in the aquifer, the most suitable aquifer can be selected according to the actual state of the aquifer to conduct compressed air storage on the redundant electric power of a power plant; high energy storage efficiency is ensured, energy loss is reduced, and cost is reduced; in addition, a proper energy storage mode can be selected according to the actual aquifer state of the final energy storage aquifer, it is ensured that the energy conversion efficiency coefficient is low, the operation cost is reduced, and the overall energy utilization efficiency is ensured.

This invention relates to the field of natural gas boiler energy dispatching technology, and discloses a method for optimizing energy dispatching through waste heat recovery from natural gas boiler flue gas. The method includes collecting flue gas parameters from the gas boiler and user-end heat demand parameters; determining the heat recovery threshold of the primary condensing waste heat recovery system and the heat exchange load range of the secondary white smoke elimination heat exchange system based on the flue gas parameters; generating a multi-energy coupled dispatching strategy by combining the operating status data of the four-pipe air source heat pump unit and environmental temperature and humidity parameters; allocating the heat supply ratio of the underfloor heating and air conditioning heating systems according to this strategy, and dynamically adjusting the operating modes of the two-stage systems; correcting the dispatching strategy based on real-time heat supply and demand deviation, and outputting the final energy dispatching command. This method can fully recover waste heat from the flue gas, achieve multi-energy coordinated dispatching and heat supply and demand matching, and avoid the "white smoke" phenomenon.

The application provides an energy storage prediction method, system and device, and relates to the technical field of electric energy storage.The energy storage prediction method comprises the following steps: obtaining a bus voltage signal in a current time period through a public connection point of a microgrid, and extracting a quantum phase perturbation sequence therefrom; identifying and separating a secondary modulation component of the bus by using an adaptive noise shaping algorithm; performing unsupervised clustering on the secondary modulation component by using a density peak clustering algorithm, obtaining a plurality of aging mode clusters, and extracting statistical features thereof; obtaining an initial residual energy evaluation value by using a variable coefficient regression submodel; performing ampere-hour integration on an instantaneous value sequence, determining an estimated covariance of a statistical mean channel, and obtaining an estimated covariance of a Kalman filtering channel through a Kalman filtering prediction correction cycle; and finally, weighting and fusing the initial residual energy evaluation value according to the estimated covariances of the two channels to obtain a final energy evaluation value.The application improves the adaptability and stability of the prediction.

The invention relates to the technical field of natural gas boiler energy scheduling, and discloses a natural gas boiler flue gas white smoke elimination waste heat recovery energy optimization scheduling method. The method comprises the steps that gas-fired boiler flue gas parameters and user side heat energy demand parameters are collected, and the recovery heat threshold value of a first-stage condensation waste heat recovery system and the heat exchange load range of a second-stage white smoke elimination heat exchange system are determined according to the flue gas parameters; a multi-energy coupling scheduling strategy is generated by combining the operation state data and the environment temperature and humidity parameters of the four-pipe air source heat pump unit; according to the strategy, the heat energy supply proportion of the floor heating system and the air conditioner heating system is distributed, and the two-stage system operation mode is dynamically adjusted; and based on the real-time heat energy supply and demand deviation correction scheduling strategy, outputting a final energy scheduling instruction. According to the method, flue gas waste heat can be fully recycled, multi-energy collaborative scheduling and heat energy supply and demand matching are achieved, and the white smoke phenomenon is avoided.

The invention discloses a method and a device for testing the radio frequency direct current conversion efficiency of a diode. The method comprises the following steps: S1, providing input power; s2, adjusting source traction and load traction; s3, adjusting the resistance value of a variable resistor for voltage division; s4, measuring the actual input power of the diode to be tested through the vector network analyzer; s5, obtaining energy efficiency conversion efficiency according to the maximum direct current output power and the actual input power; s6, increasing the input power of the signal source for inputting the diode to be tested, and returning to S2 to obtain the energy efficiency conversion efficiency of the current round; and when the energy efficiency conversion efficiency is not improved any more, the energy efficiency conversion efficiency of the current round serves as the final energy efficiency conversion efficiency. According to the invention, the input power and the load impedance can be adjusted, the conjugate of the source traction and the input impedance can be adjusted according to different input powers, the impedance of the direct current load can be dynamically adjusted through the load traction, the nonlinear response characteristics of the diode under different working conditions are accurately captured, and accurate data support is provided for the design and optimization of a microwave rectification circuit.

This invention relates to the field of carbon emission forecasting technology, providing a carbon emission forecasting method, system, computer equipment, and storage medium. The method includes: decomposing the industrial-specific final energy consumption data from the overall industry-specific final energy consumption data based on historical annual industrial end-product energy consumption data by category and type; predicting and analyzing this data to obtain the target year's overall industry-specific final energy consumption forecast data; and calculating the primary energy consumption forecast data based on the target year's overall industry-specific final energy consumption forecast data using power generation ratio prediction data obtained from historical annual electricity data evolution analysis, thereby obtaining the predicted value of regional energy consumption carbon emissions. This invention can capture the natural laws governing the impact of energy structure adjustment, technology diffusion, and resource constraints on energy demand and carbon emissions, improving the reliability and accuracy of regional energy carbon emission forecasting.

The application discloses a kind of energy supplement facilities positioning method and system. Obtain multi-modal multi-source vector data and carry out pretreatment;The spatial constraint system of demarcating energy supplement facilities and energy supplement demand distribution boundary;According to the topological structure of road network, select initial candidate site and extract characteristic attribute based on spatial constraint system, generate corresponding multidimensional space characteristic vector;Construct simulation positioning scene to extract the spatial characteristic vector of simulation demand point set, combine heuristic optimization result to generate corresponding construction value score label, obtain labeled dataset;Neural network is trained using labeled dataset, the mapping relationship of space characteristic and construction value is established, and the model parameter trained is stored as offline value evaluator;Using offline value evaluator, the initial candidate site is carried out quickly value retrieval screening, obtain high-value candidate site pool and carry out heuristic optimization, output the final energy supplement facility layout scheme.

The invention discloses a railway vehicle power optimization method based on energy routing control, which comprises the following steps: acquiring a velocity vector and an acceleration parameter from a channel allocation state, fusing the parameters through a Kalman filtering algorithm, determining an energy demand curve in a future time period, and obtaining a predicted power demand sequence; a reference value of a hierarchical scheduling frame is obtained from the power flow distribution scheme, instantaneous power waves are processed through a multi-time-scale hierarchical architecture, a control instruction sequence from the millisecond level to the minute level is determined, and a coordinated short-term scheduling result is obtained; and acquiring position information data from the long-term energy network topology, fusing the data through a real-time synchronization mechanism, determining a final energy routing control state, and obtaining a closed-loop feedback cycle of vehicle power optimization.

The invention belongs to the technical field of electric power energy storage systems, and discloses an energy storage system frequency stability evaluation and control method, system, device and medium, and the energy storage system frequency stability evaluation method comprises the steps: building a typical network construction type energy storage system frequency evaluation model based on the state variable of an energy storage system; constructing an initial frequency stability evaluation model; constructing a neural network optimization problem based on the system disturbance obtained at the preset time node and the corresponding real state; carrying out gradient solution on a neural network optimization problem by utilizing the defined evaluation adjoint, and carrying out iterative updating on model parameters at a fixed step length until convergence; and based on the final energy storage frequency stability evaluation model, in combination with the system initial state and the disturbance condition, solving by using an ordinary differential equation solver to obtain a prediction state of a target time node, and judging the frequency stability of the energy storage system according to the prediction state of the target time node. According to the method, the system frequency change is accurately predicted by using an ordinary differential equation solver.

The present application provides a kind of based on the persistent self-evolution vehicle energy management method and system of certainty working condition and uncertainty disturbance coordination, belong to vehicle energy management and intelligent control technical field, the method of the present application is with stable basic strategy as main controller, generates basic energy management control instruction according to current vehicle state;On this basis, based on current certainty working condition identification result and prior information of road ahead constructs certainty correction term, for the feedforward correction of basic control instruction in combination with current working condition difference and future working condition transition trend;While constructing uncertainty disturbance correction term, when detecting driving style mutation, traffic state fluctuation or demand distribution offset, output limited residual compensation quantity, and through amplitude constraint, change rate constraint and automatic attenuation mechanism guarantee online collaborative stability.Finally, basic energy management control instruction, certainty correction term and uncertainty disturbance correction term are fused to obtain final energy management control instruction.