189 results about "Distributed power generation" patented technology

The invention relates to the technical field of scheduling management, in particular to a source network load optimization scheduling analysis method and system for an active power distribution network of an electric vehicle. The method comprises the following steps: acquiring power supply side data, power grid side data and load side data in real time, and performing sliding filtering and standardization processing to obtain source network load standard data of the electric vehicle; historical charging data, traffic flow data, weather data and user appearing habit data are obtained, and load and power output prediction calculation is carried out to predict and output electric vehicle charging power distribution and distributed power generation power distribution; a corresponding multi-objective optimization function and a power distribution network operation constraint condition are constructed through an electric vehicle active power distribution network, a source network load optimization scheduling model is constructed, and a source network load optimization scheduling scheme is solved to adjust corresponding electric vehicle charging power and distributed power generation power in real time. The energy utilization efficiency and the power grid operation stability can be improved.

The invention provides a meteorological-distributed power supply-load long-term joint prediction method, and relates to the technical field of power system load prediction, and the method comprises the steps: introducing a multi-channel attention fusion mechanism, and constructing a feature fusion layer; performing multi-source feature coding and feature weighted fusion by using a meteorological encoder, a power encoder, a load encoder and a feature fusion layer to obtain a sample training data set; based on the time weighted loss function, adopting the sample training data set to supervise and train the long-short term memory network until convergence; and executing generation power prediction and power load prediction by using the long-term trend prediction plug-in. According to the method and the device, the technical problem of insufficient coupling modeling between prediction objects in the prior art can be solved, the technical target of collaborative modeling between the weather, the distributed power supply and the load is realized, and the technical effect of improving the power prediction precision is achieved.

The invention provides a power distribution network load flow calculation and optimal scheduling method and device based on a graph convolutional network, and the method comprises the steps: obtaining node power balance, distributed power supply output limitation and voltage constraint conditions from a network correlation matrix and original parameters of a power distribution network, adjusting the weight of the constraint conditions through the correlation matrix, and obtaining a load flow calculation result; generating a power distribution network load flow calculation nonlinear equation set; identifying an overload line and a low-voltage node from node voltage amplitude, phase angle and branch power data, generating an optimized operation scheme meeting N-1 security constraints by using a load clustering prediction and distributed power supply output probability model, and generating a power distribution network scheduling strategy; weak links are identified from a power distribution network scheduling strategy, the influence of future load increase on voltage and power is predicted by using global feature vectors, and a grid structure optimization suggestion and an equipment upgrading scheme are generated according to a power distribution network planning standard.

The invention provides a large-scale distributed power supply access rural power distribution network fault feature analysis method, which comprises the following steps of 1, analyzing rural power distribution network fault feature types, including short-circuit fault features, small-current grounding fault features and arc light high-resistance fault features; 2, establishing a fault equivalent model of the distributed power supply; and step 3, analyzing the fault characteristics of the rural power distribution network containing distributed power supply access. According to the scheme, the influence of large-scale distributed power supply access on the short-circuit fault characteristics of the power distribution network is analyzed, and the influence of various influence factors such as the type, the position and the fault impedance of the distributed power supply on the amplitude, the phase and the like of fault current is systematically analyzed and summarized; the limitation of a traditional short-circuit fault differential protection algorithm applied to a distributed power supply access scene is discussed, and a foundation is laid for follow-up related research of a rural power distribution network.

The invention relates to the technical field of micro-grid control, and provides an island micro-grid distributed control method, system and device and a storage medium. Comprising the following steps: performing voltage compensation gain and frequency compensation gain calculation based on droop control output of each distributed power generation unit, droop control output of all neighbor distributed power generation units, and a voltage dynamic tracking error and a frequency dynamic tracking error which are obtained by calculating a microgrid global recovery target to obtain secondary adjustment output; and after corresponding items in the droop control output and the secondary regulation output are summed to generate comprehensive reference output, voltage synthesis is carried out according to the comprehensive reference output to obtain voltage regulation output for output control of a corresponding inverter. Based on a distributed regulation and control mechanism for cooperatively calculating the compensation amount of each power generation unit by using neighbor information and a global recovery target, the dynamic response speed and the power distribution precision can be improved, voltage drop and frequency deviation caused by load disturbance are effectively eliminated, and rapid recovery is realized.

The invention provides a district-based distributed power consumption capability assessment method and system and a medium, and belongs to the technical field of power system capability assessment. The method comprises the steps that pre-processed associated data parameters are classified and stored, and a structured feature database is generated; constructing a transformer area load vector model according to the load power flow direction of the power distribution transformer areas of the power grid line, screening and classifying a plurality of power distribution transformer areas with similar characteristics of the line, and constructing a line load quantification model based on the structured characteristic database and the transformer area load vector model; obtaining a power distribution area consumption capability range according to the structured feature database and the area load vector model, and obtaining a line consumption capability range according to the structured feature database and the line load quantification model; and on the basis of the principle of minimizing the two, combining the power distribution area consumption capability range and the line consumption capability range to generate an actual evaluation result of the power grid consumption capability. According to the method, the district-based distributed power consumption capability evaluation precision can be effectively improved.

The invention discloses a high-voltage distribution network reactive voltage optimization method, device, equipment and medium based on a time scale, and relates to the technical field of distribution network optimization, and the method comprises the following steps: obtaining the real-time operation state data and prediction information of a high-voltage distribution network, dividing the operation time of the high-voltage distribution network, obtaining the divided data, and calculating the real-time operation state data of the high-voltage distribution network; the division data comprises a long time scale and a short time scale; under a long time scale, based on load prediction and distributed power supply output prediction, a mixed integer programming model is established, and a capacitor bank switching scheme and a transformer tap reference position are obtained; under a short time scale, constructing an optimal power flow model with minimum voltage deviation as a target, and dynamically calling the reactive capacity of the distributed energy converter for real-time correction; and establishing a cross-time-scale coordination control mechanism, triggering advanced re-optimization of a long time scale when the accumulated reactive power regulation quantity under a short time scale reaches a preset reactive power capacity threshold value, and updating an equipment action constraint condition.

The invention discloses a method for evaluating the carrying capacity of a distributed power supply of a power grid, and aims to solve the defects of a traditional method in the aspects of dynamic modeling, complex topology adaptability, real-time performance and robustness. According to the method, multi-scale time features and spatial dependence features are extracted through wavelet transform and a graph neural network, and comprehensive feature vectors are generated through multi-head attention mechanism fusion; constructing a Transform and gating cycle unit hybrid model, embedding power balance and voltage stability constraints, and predicting the bearing capacity; optimizing the access capacity and position by using a depth deterministic strategy gradient algorithm; parallel processing and result verification are realized through distributed calculation and a digital twinborn model; and evaluating the extreme scene risk by adopting a generative adversarial network and a conditional value-at-risk method. According to the method, the evaluation precision, the real-time performance and the robustness are remarkably improved, the access capacity is improved, and the method is suitable for an intelligent power grid scene with high-proportion distributed power supply access and has good economic and social benefits.

The invention discloses a furnace flue gas waste heat graded cycle power generation method and system, which combines multi-stage purification and temperature division utilization, and comprises the following steps: firstly, carrying out component analysis and desulfurization purification treatment on furnace flue gas, establishing a layered purification chain, and identifying an acid dew point area; a safe flue gas purification area is formed through material adaptability evaluation and corrosion control measures; then carrying out temperature gradient analysis and temperature field reconstruction on the purified flue gas, establishing a heat grade distribution mechanism and forming a gradient heat energy flow to realize complementary utilization of heat sources at different temperature sections; a water vapor main cycle and organic working medium auxiliary cycle cascade power generation system is constructed, and the magnetic suspension bearing technology is integrated to improve the auxiliary cycle power generation efficiency; establishing a heat balance parameter and optimizing a circulation network through heat matching degree monitoring and mismatch detection; and finally, an energy transfer matrix is constructed, distributed power generation configuration is formed through generator coupling analysis and rotating speed coordination control, stable electric energy output is completed, and efficient utilization of waste heat is achieved.

The invention relates to a park micro-grid distributed power supply and energy storage coordinated optimization configuration method, and belongs to the field of power system computer software application. The method comprises the steps that original data collection and import design is carried out, and a user interaction visual interface is created and used for importing and visualizing original data needed by micro-grid planning; establishing and designing a distributed power generation model, namely establishing a wind power generation model and a photovoltaic power generation model; establishing and designing an energy storage model, and adopting a KiBaM quasi-steady-state battery simulation model; time-of-use electricity price setting design: designing a time-of-use electricity price setting interface; model control and target optimization design, including micro-grid power balance and storage battery charging and discharging power control design; designing a micro-grid operation program, and optimizing system configuration and a scheduling strategy; and carrying out simulation calculation and result data analysis, verifying the effectiveness of a system optimization configuration scheme, and realizing park micro-grid distributed power supply and energy storage coordinated optimal configuration.

The invention discloses a flexible interconnection and mode smooth switching method for a distributed power generation system, and relates to the technical field of distributed power generation, and the method comprises the steps: building a droop control relation through continuously collecting DC voltage and current for a source side rectifier of each power generation unit; in a normal mode, the output current of the back-to-back rectifier and the voltage of an intermediate capacitor are collected, the same phase of the current and the load current is kept by using phase locking control, and voltage regulation is realized by combining a dq coordinate model; when a fault of a source side rectifier is detected, an alternating current reference value is generated based on intermediate capacitor voltage deviation and is input into a single current loop controller for voltage stabilization, and meanwhile, a phase advance, adaptive gain and integral saturation resistance mechanism is introduced, so that quick response and stable operation are ensured; in the mode switching process, normal control quantity and fault control quantity are subjected to weighted fusion, and dynamic consistency is achieved through pole matching and reference pre-alignment; the intermediate capacitor voltage fluctuation is significantly reduced, the recovery time is shortened, and the system stability and reliability are improved.

The invention discloses a power distribution network short circuit fault diagnosis method and device based on a heterogeneous graph attention network and a medium, and belongs to the field of power system protection and control, and the method comprises the steps: building a heterogeneous power distribution network topological graph structure, and measuring the electric data of each node in the power distribution network topological graph; preprocessing the measured electric data and constructing a fault data set; constructing a power distribution network short-circuit fault diagnosis model based on the heterogeneous graph attention network; defining a training hyper-parameter and a loss function of the power distribution network short-circuit fault diagnosis model, and training the power distribution network short-circuit fault diagnosis model; and when a power distribution network fault occurs, preprocessing real-time measurement data, and inputting the data into the optimal power distribution network short-circuit fault diagnosis model to obtain prediction results of a node fault state, a fault category and a fault phase. According to the method, the fault of the power distribution network can be accurately and effectively diagnosed under the condition of distributed power supply deployment, and the method has relatively high diagnosis accuracy and robustness.

The invention provides an overhead line power supply reliability assessment method and device considering a distributed power supply. The method comprises the following steps: acquiring an assessment parameter set of a first line; calculating the evaluation parameter set according to a preset evaluation method to obtain the number of households during first power failure and the number of households during second power failure; obtaining the total number of lines and the total number of users corresponding to the medium-voltage overhead line set; determining a third number of households during power failure according to the total number of lines, the first number of households during power failure and the second number of households during power failure; the third number of households during power failure represents the number of households during power failure of all medium-voltage overhead lines; determining the average power failure time of the users according to the number of households in the third power failure and the total number of the users; and determining the target power supply reliability corresponding to the medium-voltage overhead line set according to the user average power failure time. Various evaluation parameters can be comprehensively considered, so that the accuracy of power supply reliability evaluation of the medium-voltage overhead line is improved.

The application discloses a kind of kiln flue gas waste heat grading circulation power generation method and system, adopt multi-stage purification and temperature utilization combination, first, kiln flue gas is carried out component analysis and desulfurization purification treatment, establish layered purification chain and identify acid dew point area, form safe purification flue gas area by material adaptability evaluation and corrosion control measure;Then, temperature gradient analysis and temperature field reconstruction are carried out to purified flue gas, establish heat grade distribution mechanism and form cascade thermal energy flow, realize the complementary use of different temperature section heat source;Further, build the cascade power generation system of water vapor main cycle and organic working medium auxiliary cycle, integrate magnetic suspension bearing technology to improve auxiliary cycle power generation efficiency;Through heat matching degree monitoring and mismatch detection, establish heat balance parameter and optimize circulation network;Finally, build energy transfer matrix, through generator coupling analysis and speed coordination control, form distributed power generation configuration and complete stable electric energy output, realize the efficient use of waste heat.

The invention provides a distributed optimal scheduling method and system for an AC / DC power distribution network. The method comprises the following steps: acquiring load data, distributed power supply output data and energy storage state data of a local node based on a first local intelligent controller; performing a local optimization decision based on the first local intelligent controller according to the local optimization objective function in combination with the load data, the distributed power supply output data and the energy storage state data to obtain a preliminary local scheduling decision; based on each first local intelligent controller, performing consistency collaborative optimization according to the first interaction information and second interaction information of the second local intelligent controller, and determining a target local scheduling decision; and performing distributed collaborative optimization according to the target local scheduling decision of the target local intelligent controller based on each regional coordinator, determining a node scheduling decision of a node corresponding to the target local intelligent controller, and realizing peak-valley difference optimal scheduling of the AC / DC power distribution network. The overall operation efficiency and stability of the power grid are improved.

The invention belongs to the technical field of solid oxide fuel cells, and discloses a perovskite-spinel composite material and application thereof. The perovskite-spinel composite material is prepared from the following raw materials: perovskite powder, spinel powder, an adhesive and a dispersing agent, the structural formula of the perovskite powder is LaxSr (1-x) CoO3, and x is more than or equal to 0.6 and less than or equal to 0.8; the mass ratio of the perovskite powder to the spinel powder is (3-1): 1. The perovskite-spinel composite material provided by the invention can be used in the assembly of a solid oxide fuel cell stack, can be used as a cathode collector layer of a cell and a protective layer of a connector, can effectively improve the electrochemical performance and long-term stability of the solid oxide fuel cell stack, has wide application potential in the field of power generation devices, and can be widely applied to the field of power generation devices. The perovskite-spinel composite material and the solid oxide fuel cell stack can be applied to preparation of auxiliary or power sources of distributed power generation and fixed power stations, vehicles or unmanned aerial vehicles, and the preparation process of the perovskite-spinel composite material and the solid oxide fuel cell stack is simple, easy to operate, low in cost, short in period and suitable for mass production.

This invention discloses a UPS power supply system and control method based on hydrogen fuel cell distributed power generation, relating to the field of power supply circuit technology. The system includes a safety and control module, a control execution module, a front-stage bidirectional DC-DC converter module, and a rear-stage bidirectional DC-DC converter. The safety and control module is used to determine whether the proton exchange membrane (PEM) shows signs of dehydration or flooding. The control execution module controls the air compressor to perform pulsed water blowing on the PEM. The front-stage bidirectional DC-DC converter module switches the front-stage converter to current closed-loop mode. The rear-stage bidirectional DC-DC converter switches the rear-stage converter to either a boost or buck topology. This invention, by determining whether the PEM shows signs of dehydration or flooding, maximizes the net output efficiency and ensures high-reliability continuous operation of the UPS power supply system under all dynamic operating conditions, solving the problem of significantly reduced operating efficiency in existing UPS power supply systems.

The invention discloses a fault component compensation type low-voltage ride-through control method and system of a distributed power generation system and a storage medium, and the method comprises the steps: introducing a difference value between a d-axis voltage instantaneous component of a common coupling point and a system rated voltage into a quadrature-axis voltage compensation branch during the voltage drop period of a power grid, and obtaining a quadrature-axis voltage compensation amount through compensation coefficient calculation, the calculation result is added to the phase-locked loop control link, the q-axis voltage of the common coupling point tracked by the phase-locked loop is adjusted in real time, and the problem that the phase angle of the distributed power generation system is prone to loss stability during the transient state is effectively solved without any additional control information. And the low-voltage ride-through capability of the distributed power generation system under the extreme working condition is obviously enhanced.

The present application relates to a kind of optimal covert attack detection method, device and medium based on double adaptive observer in power grid system, for detecting optimal covert attack based on the vulnerability of adaptive unknown input observer in direct current micro grid system, for the direct current micro grid system with ZIP load, the dynamic model of distributed power generation unit is established;Adaptive unknown input observer and adaptive distributed observer are deployed for each distributed power generation unit, monitor its state when decoupling with neighbor distributed power generation unit;Adaptive distributed observer accepts the output of neighbor adaptive unknown input observer and predicts the output of distributed power generation unit;Based on the detection residual between actual output and estimated system output of system through adaptive unknown input observer and adaptive distributed observer, it is judged whether distributed power generation unit is attacked.Compared with prior art, the reliability and security of direct current micro grid system are effectively improved.

The invention relates to the technical field of power grid power distribution, and provides a distributed energy power grid energy storage dynamic power distribution method, system and device. The method comprises the following steps: collecting distributed power generation data, and performing preprocessing to obtain preprocessed data; constructing a prediction model according to the preprocessed data to obtain a pre-trained prediction model; performing power distribution optimization on the pre-trained prediction model to obtain a prediction model; inputting the real-time data into the prediction model to obtain the optimal charging and discharging power; and controlling the converter to control the circuit according to the optimal charging and discharging power. By constructing the multi-objective optimization function and comprehensively considering the power grid stability, the energy storage charge and discharge stability and the battery health state, the optimal power distribution scheme can be obtained, the distributed energy power fluctuation is effectively stabilized, the power grid voltage deviation ratio is reduced, the power grid frequency is stabilized, and the acceptance capability of the power grid to the distributed energy is enhanced; and the overall operation stability and reliability are improved.

The application discloses a SOFC integrated power generation system containing a diesel pretreatment unit, and belongs to the technical field of solid oxide fuel cells. The SOFC integrated power generation system at least comprises a diesel pretreatment unit, a SOFC power generation unit and an intelligent control system. The pretreatment unit converts diesel into high-purity hydrogen-rich gas through desulfurization, denitrification and autothermal reforming processes. The SOFC power generation unit adopts a metal support type stack and realizes efficient power generation in combination with heat management. The intelligent control system can realize real-time monitoring and dynamic adjustment to ensure stable operation of the system. The power generation efficiency of the SOFC integrated power generation system can reach 55% to 58%, the fuel utilization rate reaches more than 90%, and the emission is low. The SOFC integrated power generation system is suitable for distributed power generation, mobile power sources, emergency power sources and automobile fuel cells and the like application scenarios, and has the characteristics of high efficiency, environmental protection and stability.

The present invention discloses a double ratchet friction nanogenerator based on vortex-induced vibration, which relates to the field of marine energy technology. The present invention includes a shell, a float and a symmetrically distributed power generation component. A groove is provided on the shell, and the float slides vertically on both sides of the bottom of the groove through a sliding seat and a spring system. The power generation component includes a frame, upper and lower electrode plates and a double ratchet transmission mechanism; the upper electrode plate is hinged to the auxiliary frame, and forms a vertical contact-separation friction nanogenerator with the fixed lower electrode plate; the ratchet escapement mechanism is linked to a bidirectional ratchet group through a rotating shaft, and the vertical vibration of the float is converted into a unidirectional rotation of the ratchet through a gear-rack trigger mechanism, driving the electrode plate to high-frequency contact and separation. The present invention can realize the three-level energy conversion of ocean current energy-mechanical vibration-unidirectional rotation-friction power generation, breaking through the locking range limitation of traditional devices. Through modular plug-in expansion, it is suitable for the efficient collection of low-frequency energy in complex marine environments.

The present invention provides a distributed power generation system, a control method for the distributed power generation system, and an output control device that can more appropriately reduce the amount of electricity purchased from the power grid and more effectively utilize the generated electricity. [Solution] A distributed power system is provided, comprising: a distributed power source; a power converter that converts the power supplied from the distributed power source into AC power corresponding to the load and supplies the converted AC power to the load; an output control device that controls the operation of power conversion by the power converter; and a power generation forecasting device that stores a power generation forecasting model that enables the prediction of the amount of power generated by the distributed power source based on weather forecasts at the locations where the distributed power source is installed, predicts the amount of power generated by the distributed power source after a predetermined time based on the weather forecasting data and the power generation forecasting model, and outputs power generation forecasting information including the predicted value of the amount of power generated, thereby enabling the planning of the demand power required by the load in advance.

The present invention discloses a privacy protection control method and system for a space-ground integrated microgrid cluster. The method includes: constructing a hybrid control model based on device attribute information of distributed power generation equipment, collecting current status information of the distributed power generation equipment, and adding a noise signal to the current status information to generate a first status signal, sending the first status signal to a neighboring power generation equipment adjacent to the distributed power generation equipment in the space-ground integrated microgrid cluster, and receiving a second status signal sent by the neighboring power generation equipment, parsing the second status signal to obtain device status information of the neighboring power generation equipment, inputting the current status information and the device status information into the hybrid control model, generating a control signal, and controlling the distributed power generation equipment based on the control signal. While ensuring efficient control of the distributed power generation equipment, it effectively avoids communication and data transmission leakage, thereby greatly improving the security performance of the space-ground integrated microgrid cluster.

A distributed power adaptive voltage control method based on multi-agent reinforcement learning: according to the selected distribution network containing distributed power, input the basic parameter information of the distribution network; form a Markov decision process for voltage control of the distribution network containing distributed power, and construct each distribution network regional agent and a distributed power reactive output dynamic boundary mask method based on a multi-agent deep deterministic policy gradient network; conduct offline training on each distribution network regional agent to obtain each trained distribution network regional agent; regulate the distributed power in the region, and each distribution network regional agent gives a control strategy for the distributed power in the region based on the real-time input distribution network status in the region, and is processed by the distributed power reactive output dynamic boundary mask method and sent to the distributed power converter in the region for execution. The present invention can improve the voltage operation level of the distribution network, improve the voltage quality, and enhance the economic efficiency of power system operation.

The invention discloses a distributed power supply power distribution network fault detection method, system and device and a medium, and belongs to the technical field of power distribution network fault detection, and the method comprises the steps: collecting a voltage signal, and converting the voltage signal into first two-dimensional time-frequency domain image data through a time-frequency analysis method; performing data enhancement on the data to generate a fault data set; constructing a fault detection model; training a fault detection model by using the fault data set to obtain a pre-trained fault detection model; and converting a voltage signal acquired in real time into second two-dimensional time-frequency domain image data through a time-frequency analysis method, inputting the second two-dimensional time-frequency domain image data into the pre-trained fault detection model, and outputting a fault position prediction result. According to the method, fault detection and positioning can be realized before the insulation fault occurs, the influence of the transient response of the distributed power supply on fault detection is considered, the method can better adapt to the actual operation conditions of the power distribution network, such as distributed power supply access, load, line switching and the like, and the robustness of the method is high.

The invention discloses an island detection method and system based on a Goertzel algorithm and quality factor entropy dispersion. The method comprises the following steps: acquiring three-phase voltage and current signals of a distributed power generation system; performing double-domain leakage suppression processing on the signal to obtain an accurate fundamental wave parameter; carrying out heavy fundamental wave construction and harmonic signal separation on the accurate fundamental wave parameter to obtain a residual harmonic signal; a Goertzel algorithm is adopted to carry out directional spectrum analysis on specific harmonics in the residual harmonic signals, and the voltage amplitude and the current amplitude of the specific harmonics are obtained; calculating a harmonic impedance amplitude according to the voltage amplitude and the current amplitude of the specific harmonic, and obtaining a quality factor entropy dispersion corresponding to the specific harmonic based on the harmonic impedance amplitude; and carrying out island detection according to the quality factor entropy dispersion corresponding to the specific harmonic wave to obtain a detection result. The load quality factor distribution consistency is quantified by using the information entropy theory, the detection blind area can be reduced, and the detection efficiency and accuracy are improved.

The application belongs to the technical field of electric power, and provides a DC micro-grid system and a secondary control method of the DC micro-grid. The voltage compensation module, the droop control module, the steady-state current distribution compensation module, the dynamic current distribution compensation module and the voltage and current loop control module of the DC micro-grid system work cooperatively to ensure the accurate distribution of load current among different distributed power generation units, and improve the power quality and robustness of the DC micro-grid. The DC micro-grid system introduces compensation voltage to be used for bus voltage recovery and offsetting the influence of line resistance on the steady-state current distribution accuracy. The voltage and current loop control module adopts a cascaded voltage and current loop control mode to ensure that the output voltage of the distributed power generation unit converter closely tracks the reference output voltage, so as to realize the accurate distribution of load current among the distributed power generation units and improve the power quality of the DC micro-grid.

The invention aims to provide a multi-objective optimization method for an integrated energy power generation device, and belongs to the field of distributed power generation. Setting a working current, an air excess ratio of the solid oxide fuel cell and a fuel utilization rate to obtain an initial constraint condition; the variables meeting the independent variable constraint conditions take the system efficiency and the return cycle of the comprehensive energy power generation device as optimization target values, and take the inlet and outlet temperature difference of the proton exchange membrane electrolytic cell, the air inlet flow of the solid oxide fuel cell and the inlet flow and temperature of the thermoelectric generator as constraint values. And performing non-dominated sorting on the variables in the initial population, and calculating the congestion degree. And obtaining a crossover and mutation solution through variation crossover according to the crowding degree of the individual. And obtaining a new population according to an elitism strategy. And outputting the Pareto optimal solution set until the number of iterations is reached. According to the method, multi-target optimization of the comprehensive energy power generation device can be realized, and the output Pareto optimal solution can provide theoretical and method support for actual operation of the comprehensive energy power generation device.