103 results about "Second-order cone programming" patented technology

A power grid planning method and system adapted to multiple uncertainties and multi-objective requirements, which relate to the technical field of power grid planning. The method comprises: constructing a deterministic multi-objective coordinated planning model with the objectives of minimizing economic cost, reliability risks and environmental impact; on the basis of an IGDT, constructing a multi-uncertainty model considering wind power, photovoltaic power and load; converting a model into a second-order cone programming model by using variable substitution, absolute value linearization, second-order cone relaxation and McCormick envelopes relaxation methods; and solving the second-order cone programming model, in order to obtain a power grid planning scheme that adapts to uncertainties in wind and photovoltaic power output and load demand growth and meets the requirements for the economy, reliability and environmental friendliness of power grid operation. Thus, economic benefits of power grid planning are improved, carbon emissions from power grid operation are reduced, the reliability of a power grid is enhanced, and an obtained planning scheme has high robustness within expected objectives of planners.

The invention provides an active power distribution network multi-time scale rolling optimization method driven by multi-agent graph reinforcement learning. The method comprises the following steps: dividing slow time scale equipment and fast time scale equipment; the slow time scale is optimized and modeled into a multi-agent Markov game, and a global state space and a combined action space corresponding to switch actions, reactive compensation equipment gears and voltage regulation equipment gears are defined; switching action candidate vectors are generated based on a basic loop of the power distribution network, and action space dimensions are compressed through a scheme of excluding conflicting actions of the same common branch; fitting an action value function of each agent by adopting a graph neural network, generating a dimensionality-reduced discrete action strategy according to the global state space, and carrying out collaborative optimization through a distributed decision and a global reward mechanism; and on the basis of the slow time scale optimization result, the fast time scale optimization problem is converted into a mixed integer second-order cone programming model, and an instruction is solved in a rolling manner.

The invention discloses an active-reactive collaborative optimization scheduling method and system for a power distribution network containing high-proportion distributed photovoltaic, and a storage medium. The method comprises the following steps: S1, constructing a constraint model of a network power flow constraint condition of a power distribution network, a substation side reactive voltage regulation equipment operation constraint condition and a feeder side active and reactive regulation equipment operation constraint condition; s2, constructing an objective function of power distribution network optimization regulation and control of calculation formula weighted combination of a plurality of optimization objectives; s3, constructing an optimal scheduling model, wherein the optimal scheduling model takes the constraint model constructed in the step S1 as a constraint condition to solve a minimum value of the target function constructed in the step S2; s4, processing a non-convex constraint condition and a target function containing an absolute value in the optimal scheduling model, converting the optimal scheduling model into a mixed integer second-order cone programming model, and solving the mixed integer second-order cone programming model; according to the method, various active and reactive power regulation devices in the power distribution network can be accurately and effectively coordinated, optimized and dispatched according to a plurality of optimization targets.

The invention relates to the field of power distribution network energy storage, in particular to an optimal configuration method for a power distribution network energy storage system containing wind and light. According to the method, a double-layer optimization modeling framework is adopted, an outer-layer model is used for determining site selection and capacity configuration of the energy storage system, the aim is to comprehensively optimize energy storage investment cost and operation performance indexes of the power distribution network, and configuration benefits are maximized on the basis of meeting operation constraints. An energy storage optimization benefit balance index is introduced into the outer layer model to serve as an evaluation index, and an adaptive variation particle swarm optimization algorithm is adopted to solve the configuration position and capacity of the energy storage system. And the inner layer model is constructed based on a second-order cone programming method and is used for optimizing a charging and discharging plan of the energy storage system under a given energy storage configuration condition. And the active power loss and the voltage deviation of the system are comprehensively considered by the inner-layer objective function so as to realize the optimal operation benefit. Through double-layer collaborative optimization, combined design of configuration and scheduling of the energy storage system is realized, and the operation stability and economy of the power distribution network under the access of renewable energy sources are improved.

The invention discloses a distributed power grid dispatching management and optimization method, and relates to the technical field of power grid automation, and the method comprises the steps: collecting multi-dimensional power grid data in a system, carrying out the data preprocessing of the multi-dimensional power grid data, carrying out the electrical load prediction of the initial multi-dimensional power grid data through an LSTM neural network, and carrying out the optimization of the electrical load. Performing energy storage SOC state real-time evaluation on the electrical load data based on a DTW dynamic time warping load identification model, performing state judgment on power grid equipment according to an evaluation result, constructing a multi-target optimization model by using mixed integer second-order cone programming, performing power grid constraint adjustment by using the multi-target optimization model, and performing power grid constraint adjustment on the basis of a power grid constraint result. And performing real-time power generation plan adjustment by using an improved particle swarm algorithm to obtain target electric power output of the power grid, and performing power grid energy storage control optimization according to the target electric power output. And the prediction accuracy of the new energy output and the load demand is obviously improved.

A multi-energy coupling aggregator feasible region rapid identification method relates to the technical field of comprehensive energy system operation optimization, and comprises the following steps: firstly, establishing an optimization operation model which aims at minimizing the total operation cost and covers electricity-gas-heat multi-energy coupling and equipment operation constraints; secondly, on the basis of the model, defining an interactive energy feasible region (IEFR) and a flexible climbing feasible region (FRFR) to be identified; then, a max-min robust optimization model used for depicting a feasible region boundary is constructed, and the max-min robust optimization model is converted into a mixed integer second-order cone programming MISOCP model capable of being efficiently solved through a strong dual theory and a KKT condition; and finally, carrying out iterative solution by adopting a polyhedral projection algorithm based on a dichotomy and a plane cutting mechanism, and rapidly obtaining an accurate boundary of the IEFR and the FRFR.

The invention discloses a power transmission and distribution power grid robust optimization unit scheduling method based on the whole frequency response process, and relates to the technical field of power systems. The method comprises the following steps: constructing a whole-process frequency security constraint around three links of inertial response, primary frequency modulation and secondary frequency modulation, establishing a power transmission and distribution network two-stage robust unit combinatorial optimization model considering the whole frequency response process by taking min-max-min as a structure, and minimizing the start-stop cost, the power generation cost and the standby cost of the primary frequency modulation and the secondary frequency modulation as a target; and converting the two-stage robust unit combinatorial optimization model of the power transmission and distribution network into a mixed integer second-order cone programming model by adopting a column sum constraint generation algorithm and a strong duality theory, and carrying out iterative solution. According to the method, the frequency regulation capability of the power transmission and distribution network can be effectively improved, the operation cost is reduced, the robustness and efficiency of a scheduling scheme are improved, and safe, stable and economical operation of the power transmission and distribution network under the output uncertainty condition of new energy such as wind and light is ensured.

The invention relates to a semantic communication anti-interference method and system based on a multifunctional intelligent metasurface, and the method comprises a system model design part and a robust optimization algorithm part, and improves the degree of freedom of reconstructing an electromagnetic propagation environment through the flexible regulation and control capability of the multifunctional intelligent metasurface on the phase and amplitude of electromagnetic waves. And meanwhile, actual defects such as hardware power consumption are overcome through an energy collection function. On the basis of the proposed system model, a robust optimization problem with transmission and rate maximization is constructed. In order to solve the optimization problem, a global optimal algorithm based on fast convergence monotone optimization and decoupling second-order cone programming is provided, a global optimal solution can be obtained through fast convergence, and efficient intelligent metasurface semantic communication anti-interference capability obtaining is achieved.

The present invention relates to a method and system for generating a real-time penetration trajectory of an aircraft. The present invention solves the penetration trajectory optimization problem by using a second-order cone programming method to obtain the penetration trajectory under different initial conditions, and after generating a data set, uses the generated data set to train a deep neural network to obtain a trained deep neural network model, and then uses the trained deep neural network model as a real-time controller of the angle of attack and the roll angle to quickly generate a penetration trajectory based on the current state parameters of the hypersonic gliding aircraft. In the actual application process, the penetration trajectory can be obtained by simply inputting the obtained current state parameters, so as to improve the solution efficiency of the convex optimization problem, thereby meeting the real-time requirements of the highly dynamic environment of the HGV.

The invention provides a power distribution network comprehensive planning method and system in electric power engineering design. The method comprises the following steps: firstly, acquiring geographic space data and historical operation data in a planning area and cable vibration spectrum data monitored by an optical fiber sensing network; carrying out distributed storage and correlation analysis on the geographic space data and the cable vibration spectrum data through a mixed integer programming parallel acceleration algorithm, and generating a cable aging risk distribution diagram based on spatial topology constraints; performing multi-target collaborative optimization based on a second-order cone programming model, and generating a high-voltage distribution network line capacity increasing scheme and a cable replacement priority sequence; and finally, in combination with a partial discharge frequency domain characteristic change trend in the cable vibration spectrum data, correcting a line corridor extension parameter, and outputting a dynamic planning map including a cable life prediction node and a capacity increasing path. According to the technical scheme provided by the invention, precise planning and optimization of the high-voltage power distribution network are realized, and the accuracy and efficiency of cable life prediction and capacity increasing path planning are improved.

The invention discloses an active power distribution network power supply recovery control method based on an intelligent soft switch, and belongs to the field of active power distribution network power supply recovery. Wherein the key data comprises topological information, intelligent soft switching information and distributed power supply output information; according to the key data of the active power distribution network, constructing an active power distribution network power supply recovery model based on the intelligent soft switch; converting a non-convexity constraint in the power supply recovery model of the active power distribution network into a convexity constraint to obtain a mixed integer second-order cone programming model, and solving the mixed integer second-order cone programming model by adopting a Gurobi solver to obtain a fault recovery control strategy; and completing power supply recovery of the active power distribution network based on the fault recovery strategy. The problem that the fault recovery capability of the active power distribution network is insufficient in the prior art is solved.

The invention discloses an energy storage type intelligent soft switch double-layer optimization site selection method based on improved whale algorithm and second-order cone programming cooperation, and belongs to the technical field of power distribution networking and optimization operation, and the method comprises the steps: collecting and preprocessing the basic data of a power distribution network; a double-layer optimization model with the minimum daily operation cost of the system as the target is established, the upper layer takes the installation position of the energy storage type intelligent soft switch as a decision variable, and the lower layer takes the three-port power transmission value as a decision variable and constructs constraints based on the power flow equation after second-order cone relaxation and the energy storage operation limitation; an upper layer site selection problem is solved by adopting an improved whale optimization algorithm introducing a self-adaptive inertia weight, a lower layer operation problem is solved by adopting a second-order cone programming method, and collaborative optimization is realized through double-layer interaction. According to the method, global collaborative optimization of planning and operation is realized, the solving precision and efficiency of the site selection problem are improved, and the system operation cost and the network loss are effectively reduced.

The invention discloses a multi-microgrid intelligent power distribution system joint optimization operation method based on energy interaction, and the method comprises the following steps: 1), taking the minimum total operation cost of the power generation cost, the environment cost and the power exchange cost between the power generation cost and a power distribution network as a target, and building a bottom layer multi-microgrid system optimization model; 2) constructing an optimization model of an upper-layer intelligent power distribution system, considering the cost of power purchase of an upper-layer power grid, the cost of controllable distributed power generation, the cost of load demand response compensation and the cost of interaction with a multi-microgrid system, and establishing a model by taking the minimum total operation cost and the minimum payload peak-valley difference of the intelligent power distribution network as targets; 3) converting the upper-layer model and the lower-layer model into a second-order cone programming problem and a mixed integer linear programming problem respectively by using a second-order cone relaxation method and a linearization method to solve the two-order cone programming problem and the mixed integer linear programming problem; according to the invention, the operation cost of the intelligent power distribution system and the multi-microgrid system can be reduced, the load fluctuation condition of the intelligent power distribution system is reduced, and the electric energy quality of the intelligent power distribution system is improved.

The invention discloses a probabilistic optimal power flow calculation method based on a second-order cone and unscented transformation, belongs to the field of power system optimization, and efficiently processes the uncertainty of new energy output and load by coupling the probabilistic sampling capability of unscented transformation (UT) and a convex optimization framework of second-order cone programming (SOCP). According to the method, unscented transformation efficient sampling is utilized, a covariance matrix is directly embedded to simplify correlation processing, and accurate probability distribution of network loss, voltage and line power can be output. Test results show that the calculation efficiency is improved by dozens of times compared with Monte Carlo simulation, the error is lower than 3%, and the method is suitable for risk assessment and operation optimization of the power system.

The invention provides a power distribution network reactive power optimization method and device based on deep reinforcement learning, and the method comprises the steps: building a mixed integer second-order cone programming model according to the state parameters of low-speed reactive power regulation equipment in a power distribution network, solving the mixed integer second-order cone programming model, and obtaining the day-ahead optimal scheduling result of each piece of low-speed reactive power regulation equipment; based on the day-ahead optimal scheduling result and the operation characteristics of the current power distribution network, establishing a multi-agent reinforcement learning model with the goal of minimizing the current operation cost of the power distribution network; a multi-agent depth deterministic strategy gradient algorithm is adopted to train the multi-agent reinforcement learning model, and an intra-day multi-agent real-time scheduling strategy is generated; and fusing the day-ahead optimal scheduling result with the intra-day multi-agent real-time scheduling strategy, and outputting a multi-time-scale coordinated power distribution network reactive power optimization control instruction. According to the technical scheme, a multi-time-scale coordinated reactive power optimization mechanism considering day-ahead economical efficiency and intra-day real-time performance is realized.

The invention discloses a multi-energy coordinated optimization scheduling method and system for a power distribution network, and the method comprises the steps: defining a multi-objective optimization function, maximizing the power-loss load recovery, and minimizing the network loss; introducing a branch power flow constraint, an energy storage operation constraint, a load constraint and a power distribution network topology constraint; a second-order cone programming method is adopted to relax the power flow constraint, and a multi-objective optimization problem is solved through an NNC method. The system comprises a scheduling module, a data acquisition module, a calculation module, an optimization module and a display module, and can perform optimization scheduling and display a result according to real-time data. The method has the advantages that the energy utilization efficiency of the power distribution network can be improved, loss is reduced, the recovery capability of the system is enhanced, and safe and stable operation of the power grid is ensured.

The invention provides an energy storage optimization configuration method and system, and the method comprises the steps: building a layered optimization architecture which comprises a dynamic strategy generator and a distributed solver; the dynamic strategy generator drives the Actor-Critic network to generate an energy storage charging and discharging strategy through a constraint-oriented confrontation exploration mechanism; a distributed solver decomposes the global optimization problem into sub-region optimization modules, generates a region decision variable and converts the region decision variable into a global coordination variable; performing relaxation processing on the global coordination variable based on second-order cone programming to generate a coordinator residual error and a relaxation gap parameter; the hierarchical optimization architecture corrects constraint boundaries according to the parameter feedback, and generates corrected power grid constraints and energy storage configuration parameters; and iteratively executing until the coordinator residual error meets a preset threshold value, and outputting an optimal configuration scheme. According to the method, the deep reinforcement learning dynamic decision and distributed convex optimization calculation reliability are combined, and online self-adaptive energy storage configuration is achieved.

The invention relates to the technical field of optimized operation of a comprehensive energy system, and discloses a P2G two-stage modeling gas-electricity-hydrogen coupling distribution network distribution robust low-carbon operation method. The method comprises the following steps: establishing a P2G refinement model in consideration of two-stage processes of water electrolysis hydrogen production and hydrogen methanation, constructing a target function which takes the minimum operation cost of a gas-electricity-hydrogen coupling distribution network system as a target function, and converting a low-carbon operation optimization model into a mixed integer second-order cone programming model for solving; uncertain scenes of wind power output and load fluctuation are obtained, an uncertain parameter distribution probability fuzzy set is constructed based on KL divergence, and a gas-electricity-hydrogen coupling distribution network distribution robust low-carbon operation model considering source load uncertainty is established; according to the method, the flexibility and the environmental protection property of system scheduling can be improved, and the optimal operation decision for balancing the economical efficiency and the safety is obtained on the premise of guaranteeing the safe operation of the system.

The invention discloses a power distribution network optimal power flow optimization method and system, and the method comprises the steps: carrying out the state evaluation of a simulation model of a target power distribution network through employing obtained measurement data, obtaining initial operation state information, and generating electrical island information; based on the electrical island information, modeling the optimal power flow problem of the power distribution network into a second-order cone programming model; the optimal power distribution network power flow state vector of the second-order cone programming model is solved by adopting an improved interior point optimization algorithm, the improved interior point optimization algorithm is defined to carry out iterative updating on variables of the second-order cone programming model according to the corrected original variable correction step length and dual variable correction step length, and then iterative optimization is carried out according to the iteratively updated variables, so that the optimal power distribution network power flow state vector of the second-order cone programming model is obtained. And outputting the optimal power flow state vector of the power distribution network until convergence or the maximum allowable number of iterations is reached, so as to optimize the optimal power flow parameter of the target power distribution network. The optimization method provided by the invention has better convergence and smaller error, and improves the reliability and accuracy of the optimal power flow calculation of the distribution network.

This invention discloses a distributed MIMO radar resource allocation method for integrated reconnaissance, interception, and communication, belonging to the technical field of radar resource allocation. It aims to solve the performance balance problem under multi-task coordination in distributed MIMO radar air combat scenarios. An integrated reconnaissance, interception, and communication adversarial scenario is constructed, using the lower bound of position estimation error (SPEB), missile detection probability, and inter-node communication capacity as performance evaluation indicators for reconnaissance, interception, and communication, respectively. Then, with the goal of minimizing the total system transmit power, a model is constructed by combining relevant performance constraints and node task rules. Finally, the model is transformed into a mixed-integer second-order cone programming problem, and the non-convex terms are convexified using the McCormick envelope method. A numerical solution is obtained based on the CVX solver in MATLAB, achieving joint optimization of node task allocation and power allocation. This invention reduces the total transmit power while satisfying three types of performance requirements, achieving efficient waveform resource scheduling and improving the practicality and robustness of radar countermeasures.

The invention discloses a clearing model and a pricing mechanism of an electric energy and auxiliary service combined market under strong uncertainty. A fuzzy set of system uncertainty power, a combined market clearing model considering the uncertainty power and an electric power combined market price system are constructed in sequence. According to the invention, node marginal prices of electric energy, standby, frequency modulation and uncertain power are obtained based on a marginal pricing principle. Price excitation is provided for flexible resources through standby and frequency-modulated node marginal prices, and an uncertain market subject is generated through node marginal price punishment of uncertain power. In the aspect of solution of a clearing model, distributed robust bilateral opportunity constraints are converted into mixed integer second-order cone programming through convex reconstruction. The method aims at enabling the uncertain power punishment cost amount generated by a new energy station to flow to a traditional generator set and an energy storage enterprise which provide standby capacity and frequency modulation power through a market pricing mechanism, and the actual application value of an uncertain power electricity price mechanism is verified.

This invention discloses an intelligent control system for a space-type atomic layer deposition equipment, belonging to the field of intelligent control technology. The system of this invention includes: an acquisition module that acquires the pressure difference and flow rate values ​​of the gas curtain pipeline and performs low-pass filtering to obtain a pure signal matrix; a feature extraction module that calculates the flow field impedance and impedance residual based on this matrix and converts them into an empirical probability distribution vector; a model building module that constructs a degenerate distribution uncertainty set and a scheduling objective cost function based on this vector, and converts them into a mixed integer second-order cone programming model; an offline solution module that discretizes and classifies the dynamic distribution divergence tolerance and solves the model, and pre-generates a scheduling strategy library; and an online control module that looks up tables in the strategy library according to the real-time divergence tolerance and outputs substrate transmission speed control and channel switching commands. This invention transforms the minimization-maximization probability model into a convex optimization problem for offline solution, breaking the computing power bottleneck and balancing control response speed and scheduling decision-making through efficient table lookup.

The present invention discloses a reentry tracking guidance method for an aircraft based on a reinforcement learning algorithm, which is used to solve the problems of high dependence on the system model, poor adaptability and guidance performance in the prior art. The implementation scheme is as follows: establishing the continuous optimal control problem of aircraft reentry in the semi-speed coordinate system; transforming the continuous optimal control problem of aircraft reentry into a sequential convex optimal control problem; transforming the sequential convex optimal control problem into a sequential second-order cone programming problem; solving the sequential second-order cone programming problem to obtain the optimal bank angle of the aircraft; sampling the optimal bank angle trajectory to obtain a reference trajectory training data set; constructing a neural network and a reward function; using the training data set to perform offline training on the neural network until the cumulative reward converges to the maximum value to obtain a guidance network; obtaining the reentry guidance command of the aircraft online through the guidance network and tracking the target altitude in real time. The present invention has strong adaptability and high guidance accuracy, and can be used for rocket recovery.

The present invention discloses a positioning method for a wireless sensor network based on hybrid RSS / AOA with unknown transmission power. Based on the RSS measurement model, the AOA azimuth measurement model, and the AOA elevation angle measurement model, an original non-convex objective optimization problem is constructed according to the least squares criterion; the semi-definite relaxation technique and the second-order cone relaxation technique are used to relax the variables or constraint conditions in the equivalent description after introducing variables in the original non-convex objective optimization problem constructed according to the least squares criterion, so as to obtain the final convex objective optimization problem; the hybrid semi-definite / second-order cone programming technique is used to solve the final convex objective optimization problem, and the position and transmission power of the target node are jointly estimated; the advantage is that it can ensure that the optimization of unknown variables can obtain the global optimal solution and is not affected by local convergence, thereby effectively improving the positioning accuracy and effectively suppressing the influence of measurement noise errors.

The invention relates to the technical field of micro-grids, and particularly discloses a hydrogen energy micro-grid and power distribution network collaborative operation optimization method, which comprises the following steps that a micro-grid operation model is constructed according to equipment parameters of a grid-connected hydrogen energy micro-grid, and the micro-grid operation model comprises an operation constraint and a total operation cost function; constructing a power distribution network operation model based on an IEEE-33 node power distribution model; coupling variables are adopted, the micro-grid operation model and the power distribution network operation model are coupled to form a coupling model, the coupling model is solved based on a mixed integer second-order cone programming method, and peak-valley difference changes of the power distribution network after coupling and wind and light absorption of the micro-grid are analyzed; the method has the advantages that renewable energy sources such as solar energy and wind energy are gathered to be connected into the power distribution network and consumed and utilized on site, consumption of fossil energy is effectively reduced, and the power distribution network is promoted to develop towards the clean and low-carbon direction.

The invention provides an off-grid ReP2A integrated system topology capacity collaborative planning method, and relates to the technical field of renewable energy source hydrogen production and synthesis ammonia, and the method comprises the steps: constructing a mixed integer second-order cone programming model covering a power network, energy storage, hydrogen production, hydrogen storage, hydrogen transmission and synthesis ammonia full-chain coupling constraint; wherein the mixed integer second-order cone programming model takes the minimum annual average comprehensive cost of the system as a target to collaboratively optimize equipment capacity configuration, power transmission and hydrogen transmission network topology and a system operation strategy; and solving the mixed integer second-order cone programming model by adopting a branch and bound Benders decomposition algorithm, and outputting a programming construction scheme. The scheme can solve the problems of high comprehensive cost and low operation efficiency of the system.

The invention discloses an active power distribution network two-stage risk scheduling method and device, a medium and a product, and relates to the technical field of power distribution network scheduling, and the method comprises the steps: constructing a source-load typical scene set considering prediction error space-time correlation; constructing an active power distribution network two-stage risk scheduling model based on the source-load typical scene set; the active power distribution network two-stage risk scheduling model comprises a day-ahead scheduling stage model and an intra-day scheduling stage model; and converting the two-stage risk scheduling model of the active power distribution network from a mixed integer nonlinear programming problem to a mixed integer second-order cone programming problem through a second-order cone relaxation method, and solving the two-stage risk scheduling model of the active power distribution network to obtain a scheduling scheme of the active power distribution network. The method can effectively cooperate with the source-grid-load storage to flexibly adjust the resources so as to reduce the power grid dispatching operation risk caused by the source-load uncertainty.

The invention discloses a power distribution network new energy bearing capacity determination method and device, a medium and electronic equipment, and relates to the technical field of new energy access, and the method comprises the steps: obtaining a plurality of transformer area topology networks of a target power distribution network and operation parameters of multilevel new energy bearing capacity evaluation indexes corresponding to the transformer area topology networks; performing constraint condition construction by adopting the operation parameters corresponding to the topological networks to obtain constraint conditions corresponding to the topological networks; based on each constraint condition and a target function taking maximization of the photovoltaic access capacity of the target power distribution network as a target, a mixed integer second-order cone programming model is adopted to carry out model construction, and an optimization model of the target power distribution network is obtained; and solving the optimization model by adopting a branch and bound algorithm to obtain the new energy bearing capacity of the target power distribution network. The new energy bearing capacity of the power distribution network determined by the method is more accurate.

The present invention discloses a method for optimizing the trajectory of an aircraft during reentry based on a neural network, which mainly solves the problems of poor real-time performance and adaptability in the prior art. The implementation scheme is as follows: establishing the continuous optimal control problem of aircraft reentry in the semi-speed coordinate system; transforming the continuous optimal control problem of aircraft reentry into a sequential convex optimal control problem; transforming the sequential convex optimal control problem into a sequential second-order cone programming problem; solving the sequential second-order cone programming problem; sampling from the solution results to obtain a state quantity data set and a control quantity data set; constructing a neural network and a loss function; using part of the state quantity data set as a training data set to perform offline training on the neural network until the loss function converges to a minimum value, obtaining a trained trajectory network; and using the trajectory network to online obtain the trajectory optimization result of the aircraft during reentry. The present invention has strong adaptability and good real-time performance, reduces the influence of parameter changes on the aircraft, and can be used for rocket recovery.

The invention relates to a train energy-saving optimization method and device and a storage medium. The method comprises the following steps: acquiring train operation line data and train parameters; a train energy-saving convex optimization model is determined, the train energy-saving convex optimization model comprises an objective function and constraint conditions, the constraint conditions comprise constraint conditions for convex relaxation auxiliary variables, and the convex relaxation auxiliary variables are used for replacing non-convex terms in the train energy-saving optimization model; and based on the line data and the train parameters, solving the train energy-saving convex optimization model by taking the minimum train operation energy consumption as an optimization target, and determining train operation state information. According to the embodiment of the invention, an energy-saving optimization problem of the train can be converted into a second-order cone programming problem (namely a convex optimization problem), the effect of stable and rapid solution can be realized, a globally optimal solution can be obtained, various complex route constraint conditions can be processed, the calculation efficiency is improved, and calculation resources are saved.