24results about How to "Reduce communication burden" patented technology

The invention relates to a Markov jump network system control method under DoS attack based on a phototropic growth algorithm. The method comprises the following steps: establishing a networked system model with Markov jump parameters; an energy-limited DoS attack model is constructed; introducing a dynamic event triggering mechanism, and determining a triggering moment based on a measurement error, a weighting coefficient, a design parameter and an internal dynamic variable; based on a networked system model and an energy-limited DoS attack model, a dynamic event triggering mechanism is fused to construct a closed-loop system dynamic model; establishing a hybrid anti-interference performance index; performing global optimization on gain parameters of the closed-loop system dynamic model by adopting a phototropic growth algorithm to obtain an optimal controller gain; and constructing a controller under the energy-limited DoS attack, and realizing the control of the Markov jump network system under the DoS attack. The finally constructed controller can realize high robustness, low communication burden and excellent dynamic performance control of the Markov hopping network system in an energy limited DoS attack scene.

A self-organizing swarm robot system and control method based on cellular soft and hard mechanisms are disclosed. The system includes several individual robots. Each robot includes an upper shell, a middle support, a lower support chassis, electrically driven legs, a magnetically connected actuator, a PCB control board, and light-emitting elements. The PCB control board is equipped with an ESP-NOW wireless communication module, a light sensor, and a multi-pose sensor. The magnetically connected actuator includes static and dynamic actuators alternately distributed along the circumference. This invention can simulate the adhesion force regulation and morphological expansion and contraction mechanism between biological cells, achieving dynamic control between swarm robots under mechanical action. It exhibits high flexibility and fast response speed, enabling multi-degree-of-freedom movement and posture adjustment in complex environments. By using ESP-NOW wireless communication technology in conjunction with light sensors and multi-pose sensors to construct a high-precision distributed sensing and control system, it supports the self-organization, collaboration, and task execution capabilities of swarm robots in weak information environments.

The invention relates to a multi-agent collaborative sensing method based on spatio-temporal joint selection. The method comprises the following steps: acquiring original sensing data of a plurality of agents; constructing a spatial sparse region selection mask; generating a joint sparse feature map; sparse features of the intelligent agent are obtained; obtaining a fused feature map; and carrying out intermediate-stage three-dimensional target detection, and carrying out later-stage fusion on the intermediate-stage three-dimensional target detection and an independent detection result of the collaborative agent to obtain a final collaborative perception detection result. According to the method, the space sparse region is constructed to select the mask, so that the relatively high sensing performance can still be kept in a scene with extremely limited bandwidth; the communication burden is reduced, the transmission content is more focused on a dynamic target which really contributes to collaborative perception, and the information utilization rate is improved; the detection precision is improved by using multi-view complementary information, the missed detection and false detection risks caused by time delay or shielding in intermediate fusion are reduced through a later compensation mechanism, and finally a more accurate and more complete 3D target detection result is obtained.

The invention provides a finite time cross-domain aircraft cluster formation control method based on a neural network, and relates to the field of aircraft control, and the method specifically comprises the steps: building a unified nonlinear non-strict feedback system for the dynamic characteristics of cross-domain aircrafts in different domains; collecting real-time flight states and position information of a plurality of followers; designing an improved Tan type nonlinear mapping function, and identifying an initial output constraint type of the system to obtain an unconstrained new variable; constructing a dual neural network combining a shared network and an exclusive network, designing a backstepping method, combining a switching function and a non-singular fast finite time control strategy, and controlling the output of a dual neural network structure; and a switching threshold event triggering mechanism is designed, so that the unmanned aerial vehicle group has different responses in different environments. According to the technical scheme, the problem that mode switching, dynamic coupling and cooperation consistency in cross-domain cooperation are not considered in a formation control method in the prior art is solved.

The application discloses a quad-rotor formation obstacle avoidance control method based on an improved DDPG algorithm, and belongs to the technical field of unmanned aerial vehicle formation control. The method adopts an improved DDPG reinforcement learning algorithm to plan an obstacle avoidance path of the quad-rotor. When the improved DDPG reinforcement learning algorithm is executed, the priority weight of each quadruple experience in the experience replay pool is initialized. After the quadruple experience in the experience replay pool is sampled and trained, the priority weight of each quadruple experience is recalculated based on a TD error, and a Sum_Tree structure is updated. The method effectively alleviates the training instability caused by hyperparameter sensitivity, the misleading of policy updating caused by overestimation of Q values, and the problem that key experiences are not sufficiently learned, accelerates the convergence speed of the quad-rotor formation obstacle avoidance training, and improves the obstacle avoidance effect.

This invention discloses a hierarchical federated learning method and system based on split meta-learning. The method specifically includes: a cloud server initializing a global model and distributing it to various edge servers; the edge server layer distributing the global model to its respective clients; each client updating the feature extraction module of the global model locally based on local data, while simultaneously freezing the classifier module of the global model; the edge server layer aggregating the updated parameters of the feature extraction modules from multiple clients and performing meta-optimization on the classifier module using a local validation dataset to generate an edge local model; and the cloud server layer periodically collecting model parameters from multiple edge servers and updating the global model using a gradient-sensitive momentum aggregation strategy. This invention, through a three-layer "vehicle-edge-cloud" architecture and a two-level collaborative optimization mechanism, achieves coordinated optimization between privacy protection, communication efficiency, and model adaptability in a vehicle-to-everything (V2X) environment.

The application provides a kind of unmanned ship consistency control method and equipment, it is related to unmanned system cooperative control technical field.The method comprises: according to the real-time state of the unmanned ship and the state of the unmanned ship at last event trigger time, construct real-time local measurement error;According to the state of the unmanned ship at last event trigger time and the state of all adjacent unmanned ships of the unmanned ship, construct joint error;Based on the real-time local measurement error and joint error of each unmanned ship, judge whether event trigger condition is satisfied, when any unmanned ship satisfies event trigger condition, obtain and according to the state of the unmanned ship at event trigger condition satisfying time, the state of the adjacent unmanned ship of the unmanned ship and unmanned ship controller gain matrix, update the controller output of the unmanned ship and the adjacent unmanned ship of the unmanned ship, carry out consistency control to each unmanned ship according to controller output;The application can accurately and safely carry out multi-unmanned ship consistency control under the condition that system model is unknown.

This invention discloses an adaptive self-triggered optimal control method for catalytic rod reactors, specifically comprising: a temperature field model of the catalytic rod reaction process described by a high-dissipation partial differential equation system based on the control input of the cooling material under time triggering, and obtaining a low-order slow subsystem characterizing the high-dissipation partial differential equation system after order reduction processing; constructing a corresponding Hamiltonian function based on the performance index of the low-order slow subsystem, obtaining the optimal control strategy under time triggering control based on the Hamiltonian function, and then obtaining the optimal control strategy under self-triggered control, converting the Hamiltonian function into HJB equations; constructing a self-triggered controller based on an evaluation-execution dual-network structure using data-driven adaptive dynamic programming, and outputting the adaptive self-triggered optimal strategy based on the optimal value function of the HJB equations.

The application provides a kind of decommissioned battery remaining life prediction method, system and battery management system, the decommissioned battery remaining life prediction method includes: end side equipment carries out feature extraction and correlation screening to the operation data of decommissioned battery, and battery characteristic data after screening is uploaded to side node;Based on the battery characteristic data after screening, the inference is carried out using battery life prediction model, and the remaining life prediction value is obtained;Wherein, the battery life prediction model uploads the parameters of the battery life prediction model by the side node, the cloud server carries out aggregation optimization to the parameters uploaded by each side node and issues the updated parameters, and the side node receives the updated parameters and updates.The method provided by the application can improve the accuracy and real-time performance of the remaining life prediction of decommissioned battery.

The invention discloses an energy storage system battery equalization method and device and a storage medium, and the method comprises the steps: collecting multi-dimensional state data in real time through an integrated low-power-consumption wireless sensor node for any single battery in an energy storage system, and asynchronously uploading the multi-dimensional state data to a central processing unit through a self-organizing wireless network; the central processing unit analyzes the multi-dimensional state data based on the dynamic evaluation model, determines target single batteries needing energy exchange and determines an energy exchange path and a corresponding exchange rate according to the residual capacity, the thermal state and the load distribution of each target single battery; and distributing an energy exchange instruction and an adaptive rate regulation factor to each target battery monomer based on the energy exchange path and the corresponding exchange rate, so that each target battery monomer performs energy exchange based on the energy exchange instruction and the corresponding adaptive rate regulation factor. The method can effectively reduce the power consumption of the energy storage system, reduces the communication burden, and achieves the asynchronous cooperative control of global balance.

The invention discloses a fully distributed time-varying formation tracking control method and device, and relates to the field of time-varying formation control, and the method comprises the steps: obtaining a dynamic model, a communication topology and an expected time-varying formation of a cluster system; constructing a state estimation law and a time-varying formation offset vector estimation law of each following agent based on an event trigger communication mechanism; further determining a formation tracking adjacent error, a local measurement error and an adjacent measurement error; constructing an adaptive formation control law according to the formation tracking adjacent error, the local measurement error and the adjacent measurement error; determining a dynamic event triggering condition according to an adaptive formation control law; controlling a plurality of following agents to track the leading agent according to the triggering time and the self-adaptive formation control law; according to the invention, the network communication burden when the cluster system works can be reduced, and the dependence on global prior information is reduced.

This application discloses a method, apparatus, and computer device for wind farm data source authentication based on SVM-UGR. It includes: acquiring the original feature set of multimodal physical signals generated by wind turbines; normalizing the original feature set to a preset feature space using a static SVM model to obtain low-dimensional static features of the multimodal physical signals; extracting dynamic coupling features of the multimodal physical signals at different time dimensions from the original feature set using a dynamic UGR model; fusing the low-dimensional static features and dynamic coupling features corresponding to different modal physical signals to form a physical fingerprint of the wind turbines; and authenticating the target wind farm data source based on the first similarity between the target wind farm data and the physical fingerprint. The method of this application constructs a "physical fingerprint" of the wind turbine's operational characteristics through a model and achieves trusted data source authentication based on operational behavior and physical state through comparison with new data, without relying on network identity.

The application discloses a multi-region power system event-triggered load frequency safety control method and system, and the technical scheme points are as follows: in view of the problem that the existing load frequency control method generally assumes that the communication link is continuously available and is difficult to maintain stable operation under the condition of DoS attack, the system is modeled as a switching system when the DoS attack exists, and the control mode is switched in real time according to whether the link is subjected to the DoS attack: the conventional learning control is executed to optimize the frequency regulation performance when the communication is normal; the anti-attack control mode is switched to when the attack occurs, so that the closed-loop stability can be maintained and the frequency deviation and the tie-line power fluctuation can be inhibited under the condition that the communication is blocked, and the system safety is significantly improved; in addition, based on the RL method, the control strategy is obtained by online learning through interaction with the environment under the condition that the system model is unknown or the parameters are uncertain, so that the control energy minimization and the operation economy are realized without depending on the accurate system dynamics.

This invention discloses a method for implementing a fault-tolerant satellite attitude tracking controller based on event-triggered learning, comprising the following steps: S1, establishing a mathematical model of satellite attitude actuator failure; S2, defining a tracking error vector and designing a satellite angular velocity command signal based on the established mathematical model; S3, designing an interference observer based on external interference, and then designing a controller and adaptive law; S4, for cases where the additive failure of the actuator is unknown, introducing a fuzzy logic system to approximate it; and designing event triggering conditions, satisfying the following condition: the weights of the fuzzy logic system are only updated when the additive failure of the actuator triggers the designed event triggering conditions. This invention can save communication resources from ground base stations to satellites and reduce the communication burden.

The invention discloses a heterogeneous perception task scheduling method and system based on personalized federal reinforcement learning, and the method comprises the steps: constructing a task scheduling environment with a scene boundary based on load data, and constructing a local scheduling model based on the task scheduling environment through employing a dual-reviewer near-end strategy optimization algorithm; according to the method, public reviewer network model parameters in a constructed local scheduling model are aggregated, a personalized model is generated based on multi-head attention weights, and value estimation of local reviews and public reviews is fused by introducing Dual-Critic PPO, so that the problem of performance reduction of a global model in a heterogeneous environment is effectively relieved; and meanwhile, the stability of advantage estimation and the reliability of strategy updating are improved. According to the method, a server side carries out personalized aggregation on public reviewer parameters through a multi-head attention mechanism, so that different clients can obtain public models matched with environment characteristics of the clients instead of depending on a general average model, and thus faster convergence and stronger personalized adaptation are realized.

This application provides a coordinated control method, system, and storage medium for distributed energy storage in low-voltage distribution areas. An objective function is constructed with the goal of minimizing the difference between the initial frequency deviation variable of the distributed energy storage and the consistency control quantity. Constraints are established, and a proportional-integral consistency algorithm is used to solve the optimization problem composed of the objective function and constraints, obtaining the optimal consistency control quantity. Based on this, a corrected angular frequency reference value is calculated. If the local state measurement error of the distributed energy storage meets a preset event triggering condition, the distributed energy storage is controlled to broadcast its current state. A frequency reference command is generated based on the corrected angular frequency reference value, enabling the distributed energy storage to adjust the converter output using the frequency reference command. This achieves coordinated control of distributed energy storage, improves the stability of the power grid under extreme events, effectively reduces redundant data traffic in the communication network, thereby reducing the communication burden and improving the resilience of the distribution network.

The invention belongs to the technical field of multi-UUV formation collision avoidance, and particularly relates to a careful formation collision avoidance method based on navigation UUV local coordination planning, a program, equipment and a storage medium. Firstly, parameters and task target points are initialized; the navigation UUV carries out obstacle detection and sensing and construction of a rolling probability occupied grid local map by using a multi-beam sonar installed at the bow of the navigation UUV; performing map rolling updating according to the formation scale; calculating a local optimal sub-target point based on the virtual potential field; formation constraint-oriented improved IRRT * path planning is carried out, formation constraint collision detection is completed, and a local optimal path is obtained; and performing path execution and formation coordination control so as to realize formation coordination collision avoidance and complete a task. The multi-UUV formation collision avoidance method realizes safer, more real-time and more coordinated multi-UUV formation collision avoidance, is especially suitable for an underwater unknown complex environment with limited resources and difficult communication, and has important practical application value.

The application discloses an energy storage system power distribution strategy based on an error function, mainly comprising an event-triggered dynamic consistency algorithm module, an error function-based SOC equalization algorithm module, a virtual voltage drop module, a voltage compensation module and a voltage and current double-loop control module. The event-triggered dynamic consistency algorithm module is added, so that the system changes from "timed communication" to "on-demand communication", while reducing the communication burden, the error function-based SOC equalization algorithm module can dynamically divide the output current of each energy storage unit according to the real-time deviation of the state of charge of each energy storage unit and the average state of charge of the energy storage system, thereby improving the accuracy of the equal division of the output current between energy storage units with different capacities. In addition, the virtual voltage drop module and the voltage compensation module ensure that the voltage is stable within the rated range.

The invention discloses a PUF (Physical Unclonable Function)-based Internet of Vehicles identity authentication method and system, and relates to the technical field of Internet of Vehicles identity authentication, the method comprises the following steps: a vehicle and an RSU respond to and restore key parameters by using a preset PUF, and the vehicle sends a request containing a pseudo identity, a first authentication code and a temporary public key to the RSU; the RSU verifies the legality of the identity of the vehicle by calculating and comparing the first authentication code, and after the verification is passed, the RSU generates a second authentication code and an updated pseudo name and sends the second authentication code and the updated pseudo name to the vehicle; the vehicle completes identity authentication of the RSU by verifying the second authentication code; according to the method, both parties generate a unified session key by mixing parameters generated in two authentication processes, including a first authentication code, a second authentication code, an updated pseudo name and a temporary identity key obtained through elliptic curve Diffie-Hellman exchange, and after authentication succeeds, the both parties can independently update local PUF related parameters, so that the authentication efficiency is improved. Forward security is achieved, and machine learning attacks are effectively resisted.

The application relates to a dispatching control method and system of an integrated energy storage power station interconnection system, and relates to the technical field of offshore power management. The method comprises the following steps: taking the maximum equivalent effective utilization of the interconnection system as an optimization target in a dispatching model, quantitatively comparing wind power consumption, pumped storage regulation contribution, power loss and operation and maintenance cost by mapping them to the power scale, expanding the dispatching decision from instantaneous power balance to the optimization of the overall energy utilization level in the dispatching period, and more truly reflecting the system operation efficiency; and discretizing the dispatching period into multiple dispatching time periods, introducing power balance constraints, equipment output constraints, interconnection line transmission constraints and seawater pumped storage power station exclusive constraints in each time period, so that the dispatching result meets the new energy output fluctuation characteristics, the traditional equipment operation limitation and the energy storage energy state evolution law, and the safety and the executability of the dispatching scheme are significantly improved.

This invention relates to the field of intelligent connected vehicle technology, addressing the shortcomings of existing intelligent connected vehicle communication network trust assessment and consistency coordination. Specifically, it relates to a collaborative control method for trusted interaction among intelligent connected vehicle groups under a zero-trust architecture. By fusing direct and indirect trust functions to obtain a dynamic comprehensive trust assessment function, it achieves real-time fusion of the global communication network and the comprehensive trust calculation model, accurately quantifying the degree of interaction between vehicles and significantly improving the safety performance of ICV group interaction. A distributed collaborative control algorithm based on state feedback adapts to differences in vehicle trust levels, achieving the goal of consistent coordination among vehicle queues and ensuring the stability of collaborative control in dynamic communication scenarios for the ICV group. The integrated design of zero-trust security protection and vehicle communication network allows the security of communication relationships in the ICV group system to be updated in real time, adapting to the communication topology changes under dynamic vehicle movement.

A multi-agent system intermittent predetermined time tracking control method based on event triggering comprises the following steps: step S1, constructing an undirected topological graph and a Laplacian matrix of a multi-agent system in combination with graph theory knowledge and an actual system; s2, determining a dynamic model of the multi-agent system; s3, designing an intermittent event to trigger a predefined time state observer, and enabling a follower agent which cannot directly obtain the leader information to estimate the leader information; and S4, designing an intermittent pre-defined time fuzzy controller and a virtual speed so as to realize a tracking control target in pre-defined time. Based on the predefined time control strategy, the problems that the convergence time of finite time control is limited by the initial state of the system and the upper limit of the convergence time of fixed time control is influenced by the parameters of the controller are solved, and the method can adapt to more working conditions while the system performance is ensured.

The invention provides a method and system for automatically configuring a process data object and a computer readable storage medium. The method comprises the steps of judging whether a function of an automatic configuration process data object is opened or not; when it is judged that the function of automatically configuring the process data object is opened, whether the current process data object is complete or not is judged; and when the current process data object is judged to be incomplete, configuring a new process data object. According to the method provided by the invention, automatic PDO configuration can be realized, the difficulty and time of manual configuration are reduced, the probability of PDO missing and / or errors caused by manual configuration is reduced, and the accuracy and reliability of PDO configuration are improved.

The invention provides a wireless communication method, terminal equipment and network equipment. The method comprises the following steps: the terminal equipment sends first capability information; wherein the first capability information is used for indicating one or more capabilities of the terminal equipment, and the one or more capabilities belong to UE capability types in a first set. By selecting one or more UE capability types from the first set for reporting, the dimension corresponding to the capability reported by the terminal equipment can be more flexible, so that the size of a message reported by the UE capability can be smaller, the communication burden of a UE capability reporting process is reduced, and the energy consumption of the terminal equipment is saved.