4912 results about "Power control" patented technology

A wireless communication method and system enabling dynamic multi-path data transmission and reception across heterogeneous radio access networks. The method includes selecting between sequential, concurrent, or redundant multipath transmission strategies based on real-time measurements of link quality parameters, including signal-to-interference-plus-noise ratio (SINR), reference signal received power (RSRP), delay, and spectrum availability. The system further enables adaptive transmission power control, modulation scheme selection, and carrier configuration based on physical layer feedback, minimizing interference and optimizing spectral efficiency. Peer-to-peer communication between terminals is supported without base station mediation, reducing RAN load. Multi-base station connectivity is enabled, allowing terminals to simultaneously transmit through multiple nodes and aggregate at the core network. The architecture supports real-time topology control, dynamic link adaptation, and transmission parameter adjustment based on physical-layer constraints.

The invention relates to an intelligent scheduling method and system for a virtual power plant, and aims to improve the precision and efficiency of distributed resource scheduling. The method comprises the following steps: monitoring the state of each distributed resource node of a virtual power plant, and collecting real-time output, charge state and communication quality indexes to obtain a resource state data set; and performing power prediction according to the resource state data set, calculating power prediction deviation in real time, and triggering online correction to obtain a power prediction sequence. And inputting the resource state data set and the power prediction sequence into an improved bee algorithm, and generating a target scheduling scheme of the virtual power plant through neighborhood search containing a prediction deviation correction term and probability selection based on communication reliability. And based on the target scheduling scheme, establishing a three-layer progressive optimization architecture, and realizing multi-time scale coordination through time coupling constraint to obtain a distributed resource power control instruction. By optimizing the resource scheduling scheme, the scheduling efficiency and the system reliability of the virtual power plant in a variable environment are improved.

The invention discloses an intelligent discharge port dynamic regulation and control system and method based on multi-source time sequence fusion, and relates to the technical field of intelligent water affairs, and the system comprises a data collection module which is used for obtaining the multi-source data of a target area in real time; the space-time fusion module is used for mapping the meteorological radar data to the topological space of the drainage pipe network through a space-time alignment encoder, dynamically fusing the meteorological radar data, the surface runoff sensor data and the historical drainage data by adopting a multi-head attention mechanism, and generating a space-time fusion tensor; the prediction model module is used for constructing a TCN-LSTM hybrid model, taking the space-time fusion tensor as input and taking future drainage flow as output; and the dynamic regulation and control module is used for optimizing the gate opening degree and the pump station power control sequence in a rolling manner based on a model predictive control algorithm, and performing dual-target optimization by combining real-time electricity price data and overflow risks. According to the system, the prediction precision of the drainage flow can be improved, and double-target balance of the overflow risk and the energy consumption cost can be achieved.

The invention discloses an Internet of Vehicles communication resource allocation method based on federal multi-agent deep reinforcement learning, and belongs to the technical field of deep crossing of intelligent transportation, wireless communication and distributed machine learning. According to the technical scheme, in an Internet of Vehicles scene, a vehicle is taken as an agent, and local training is performed through a multi-agent depth deterministic strategy gradient algorithm: each agent decides spectrum access, power control and bandwidth allocation based on a local state; asynchronous federation learning is adopted, each agent uploads local model parameters to a global server, weights are dynamically adjusted based on model updating quality, communication quality and updating frequency, and a global model is generated through weighted aggregation; and issuing the updated global model to an intelligent agent to realize distributed privacy protection and dynamic optimization of communication resources. The method has the beneficial effects that the spectrum efficiency, the transmission success rate and the system adaptability are remarkably improved on the premise of ensuring the data security, and the method has wide application prospects and commercial values.

The invention overcomes the constraints imposed by conventional wireless communication standards by introducing a physical-layer optimized architecture that decouples transmission control from any single protocol. Rather than being confined by the predefined behaviors of LTE, 5G NR, Wi-Fi, or NB-IoT, the system implements a unified control system that dynamically manages radio parameters—such as modulation, coding, and power—based on real-time link quality and network context. This cross-standard, multimode capability effectively supersedes traditional standard-driven implementations, enabling adaptive, low-latency, and spectrum-efficient communication in complex heterogeneous environments.The system dynamically controls radio access network (RAN) and physical layer parameters, including carrier aggregation, dynamic spectrum allocation, modulation and coding scheme (MCS) adaptation, beamforming configuration, channel coding, transmit power control, and frequency selection. The system architecture includes multi-mode base stations, relay nodes, and edge access points that support inter-RAT handover, fast radio link recovery, and seamless mobility across diverse wireless technologies.

The invention discloses an integrated scheduling system for realizing a PCS, an EMS and a BMS, and relates to the technical field of power control, and the system comprises a multi-dimensional performance evaluation module which constructs a battery aging dynamic model, carries out the training, carries out the health state pre-judgment through the battery aging dynamic model based on a standardized state vector, and generates a multi-dimensional performance evaluation index; the multi-objective optimization module is used for generating a collaborative scheduling strategy set by combining a fuzzy analytic hierarchy process with a multi-objective optimization solver of an improved genetic algorithm based on the multi-dimensional performance evaluation indexes; the dynamic derating module is used for generating an executable instruction queue with security constraints by combining an industrial internet of things protocol stack with a dynamic derating coefficient algorithm based on the collaborative scheduling strategy set; according to the invention, through the physical driving characteristic layer and the dynamic parameter calibration layer, the nonlinear coupling modeling of the cyclic attenuation and calendar aging mechanism in the battery aging dynamic model is realized.

The invention discloses an unmanned aerial vehicle anti-collision method and system based on LoRa communication, and belongs to the technical field of risk avoidance of multiple unmanned aerial vehicles. The method comprises the following steps: constructing an ad hoc network communication architecture to realize flight state broadcast and synchronization; fusing the multi-source data by adopting a space-time alignment algorithm, and constructing a dynamic airspace situation map taking a local machine as a center; calculating a time window and space overlapping probability of the predicted intersection; a multi-priority dynamic negotiation protocol is considered, and autonomous decision making of the unmanned aerial vehicle cluster in a scene without a central node is supported; and dynamically adjusting the flight path, speed and height through a collaborative obstacle avoidance algorithm. Through a spread spectrum modulation technology and an adaptive power control mechanism, over-the-horizon communication coverage of more than 10km level is realized; through fusion of a kinematics prediction model and a risk quantification algorithm, millisecond identification and hierarchical response of collision threats are realized, a global optimal avoidance strategy is achieved, communication delay and calculation bottleneck brought by centralized decision are effectively avoided, and the real-time collaborative obstacle avoidance capability in a complex airspace is ensured.

Methods and apparatuses for power control and beam management to enable coexistence of radar sensing and wireless communication. A method for a UE includes determining a sensing category or characteristics for a sensing application, and selecting a spatial filter for radar sensing transmission or reception based on determined sensing category or characteristics. The method further includes identifying a radar sensing transmission power and transmitting or receiving radar sensing signals using the spatial filter and the identified radar sensing transmission power. The method further includes reporting one of communication blockage, radar sensing beam information, or CSI adapted to the radar sensing beam information to a base station or neighboring UEs.

Methods, systems, and devices for wireless communication are described. A user equipment (UE) may receive a message scheduling transmission, by the UE, of uplink control information (UCI) in a physical uplink control channel (PUCCH) resource. The UE may receive an indication that the UE is scheduled to transmit the UCI in the PUCCH resource to both a first transmission-reception point (TRP) and a second TRP. The UE may also receive a first set of uplink power control parameters for transmitting the UCI to the first TRP and a second set of uplink power control parameters for transmitting the UCI to the second TRP. The UE may transmit the UCI to the first TRP and to the second TRP in the PUCCH resource, based on the first set and the second set of uplink power control parameters, and without an uplink control channel beam indication.

The invention provides a fault ride-through control method and system for a network-forming converter, and relates to the technical field of power electronics. The fault ride-through control method of the network construction type converter comprises the following steps: determining a real-time virtual impedance value corresponding to a control loop based on a virtual admittance control module; in response to the fact that the real-time virtual impedance value is larger than or equal to the reference virtual impedance value of the control loop, transient current output by the network-building type converter is adjusted based on first-stage current limiting, and steady-state current output by the network-building type converter is adjusted based on second-stage current limiting; calculating an active power proportionality coefficient based on the real-time parameter and the reference parameter; calculating a target active power reference value according to the active power proportionality coefficient and the reference active power reference value; and executing power control based on the target active power reference value, and adjusting the output voltage of the network-forming converter. According to the method, when the power grid breaks down, the grid-forming type converter can have the functions of current limiting and transient synchronization stability improving at the same time.

The invention discloses a single-chip microcomputer hierarchical dormancy control method based on dynamic power consumption prediction, and relates to the technical field of single-chip microcomputer low power consumption control, and the method specifically comprises the steps: building a mapping relation between a load current and a clock frequency; setting a dynamic dormancy threshold value; constructing a dynamic power consumption prediction model; a dormancy strategy is designed, module-level power consumption management and single-chip microcomputer function-based power consumption management are adopted, the callable frequency or the maximum operation duration of each function is distributed according to task priorities and battery residual energy consumption, and single-chip microcomputer peripherals are triggered through events and are independently awakened; and executing the sleep strategy, automatically awakening the single chip microcomputer according to a preset awakening condition, and realizing abnormity positioning and processing based on threshold comparison and power consumption monitoring in the process of executing the sleep strategy. According to the invention, module-level power consumption management and single-chip microcomputer function-based power consumption management are realized, the limitation of traditional global dormancy is broken, the need of overall reset during wakeup is avoided, and the response speed is improved while the energy consumption is reduced.

The invention relates to the technical field of electric power control, in particular to a multi-virtual power plant collaborative scheduling method and system based on mixed games and carbon transactions. The method comprises the following steps: acquiring parameters of each virtual power plant, reading a carbon quota allocation scheme and a carbon transaction market price released by a power grid, and establishing a virtual power plant operation cost expression containing a carbon transaction cost; constructing a non-cooperative game model, and obtaining a preliminary optimal output strategy of each virtual power plant by taking minimization of the operation cost of the virtual power plant as a target; the operation state of the virtual power plant is detected, if the risk that renewable energy consumption is insufficient or the total carbon emission exceeds the standard exists, a cooperative optimization mechanism is triggered, a plurality of virtual power plants are selected to form a joint optimization group, and the joint optimization group is regarded as an independent participant to obtain an optimal output strategy again; and issuing the optimized scheduling instruction to each virtual power plant for execution according to the optimal output strategy, and participating in carbon market transaction according to the actual carbon emission and the quota difference in the settlement period.

The invention relates to the technical field of charging pile management and power dispatching, and particularly discloses a charging pile operation management method and system. The method comprises the following steps: acquiring charging request data and power grid load data, and generating and cleaning a task vector data set; predicting a charging demand based on the data set and generating electricity price gradient information; a multi-objective optimization scheduling function is constructed and solved, and a task allocation scheduling scheme is generated; executing power control according to the scheduling scheme and collecting charging state data; executing dynamic contract charging and incentive generation according to the state data; and finally, performing Hash packaging and privacy processing on an execution result, and performing uplink to generate a credible record. According to the method, the resource allocation efficiency and the charging incentive intelligence level in a multi-user multi-period concurrent charging scene can be improved, and efficient cooperation and credible execution of the whole charging scheduling and settlement process are realized.

The invention discloses a micro-grid power control method, system and device based on fuzzy modulation and a storage medium, and relates to the technical field of intelligent grid integration of a photovoltaic system and a micro-grid, and the method comprises the steps: firstly obtaining the real-time power data of a photovoltaic system, carrying out the control processing through fuzzy logic, and calculating a reference instruction; according to the reference instruction, hysteresis time is dynamically adjusted through modulation hysteresis control, and an inverter switching signal is generated; converting direct current into alternating current based on the switching signal and a power switching device, injecting the alternating current into the micro-grid, calculating active and reactive power reference values, ensuring that the system operates according to a unit power factor, and giving active power to the reference value; according to the method, the power control precision and adaptability of the micro-grid are improved, excessive switching of the inverter is avoided, loss is reduced, the service life is prolonged, power matching and stable transmission are achieved, reactive loss is reduced, bus voltage is stabilized, harmonic waves can be reduced, the electric energy quality is improved, and efficient and stable operation of the micro-grid is guaranteed.

The invention discloses an electric vehicle charging power aggregation distributed regulation and control method, and relates to the technical field of AC charging pile charging power regulation and control, and the method specifically comprises the following steps: carrying out the cleaning and stabilization processing of power load and new energy data, employing an ARIMA model to predict the load, and employing an LSTM-Transform model to predict the new energy generation power; the upper layer aggregates the total state of the charging station, including the electricity price, the load, the total vehicle energy, the total docking power of the lower-layer single vehicle model and the battery demand; based on an MCTS enhanced DDPG algorithm, the total charging power is optimized through cost discount rewards and energy penalty; an improved ADMM algorithm distributes total power to each pile, and battery stress and heat loss are minimized; and comparing the actual battery energy with the virtual battery energy, and updating the data and re-deciding when the energy is inconsistent. According to the invention, three industry bottlenecks of poor real-time response of electric vehicle charging, slow large-scale scheduling and difficulty in consideration of economy and battery health are overcome, and power grid dynamic response acceleration, decision-making efficiency jump and comprehensive benefit breakthrough are realized.

The invention provides a multi-source energy storage self-power supply method and system for an iron tower, equipment and a storage medium, and belongs to the technical field of iron tower power supply, and the method comprises the steps: inputting historical load data of the iron tower into a time sequence model, and obtaining a load demand of the iron tower; inputting meteorological data of the geographic position of the iron tower into the power prediction model to obtain wind power and photovoltaic power; determining a charging strategy of the energy storage battery based on the load demand, the wind power, the photovoltaic power and the charge state of the energy storage battery; and determining a self-power-supply control strategy according to the charging strategy of the energy storage battery, and selecting any one of a wind-solar power generation device, the energy storage battery or a power grid to supply power to the iron tower based on the self-power-supply control strategy. According to the multi-source energy storage self-powered method and system for the iron tower, the equipment and the storage medium, the overall operation cost of the iron tower is effectively reduced.

The invention relates to the technical field of power systems, in particular to a cloud edge computing power regulation and control method and system based on edge computing, and the method comprises the following steps: S1, collecting the resource state data of a cloud data center, edge nodes and terminal equipment in real time; s2, constructing a dynamic scheduling strategy based on a deep reinforcement learning model, and generating a computing power allocation scheme according to task types, priorities, real-time resource states and historical load data; s3, performing hierarchical processing on the task; s4, autonomously executing emergency task scheduling in a network disconnection or high-delay scene through a local autonomous module of the edge node; s5, global energy consumption is optimized based on a genetic algorithm, the steps S1 to S5 cooperatively achieve dynamic regulation and control of cloud edge computing power, and accurate input is provided for dynamic scheduling by collecting multi-dimensional resource data in real time; through a task layering mechanism, it is ensured that high-real-time tasks are preferentially processed locally, and end-to-end delay is reduced.

The invention relates to the technical field of energy storage systems, in particular to a dynamic charging and discharging strategy collaborative optimization method for prolonging the service life of an energy storage system, and the method comprises the steps: inputting historical electricity price time sequence data based on a preset long-short-term memory network model, so as to generate an electricity price prediction sequence; constructing a state vector, wherein the state vector comprises an internal state of the energy storage system at the current moment t and an electricity price prediction sequence; the state vector is input into a pre-trained deep reinforcement learning agent, and the deep reinforcement learning agent outputs a selected specific action based on a predefined discrete charging and discharging action set according to the input state vector; and converting the output specific action into a charging and discharging power control instruction, and issuing the charging and discharging power control instruction to the energy storage converter for execution. According to the method, through deep reinforcement learning, electricity price accurate prediction and battery health dynamic modeling are combined, and charge and discharge strategy collaborative optimization of the energy storage system in a complex market environment is realized.

The invention discloses a ship power system optimization control method and system based on a simulated annealing algorithm, and relates to the technical field of ship power control, and the method comprises the steps: obtaining operation parameters and historical energy consumption data in real time, and constructing a multi-objective optimization function of dynamic weight distribution; generating an initial temperature parameter and a solution set in combination with the navigation state and the environment data; a neighborhood search strategy disturbance solution set is improved, a new solution is evaluated by using a dynamic acceptance probability function, temperature parameters are adaptively adjusted for iterative optimization, and an optimal control parameter combination is output; and an adjustment instruction set is generated after multi-dimensional efficiency verification, and a propulsion device, a generator set and an energy storage module are cooperatively controlled, so that global energy consumption optimization is realized. According to the method, through data driving and intelligent algorithm fusion, energy efficiency and environmental adaptability are improved, and stable operation under complex working conditions is guaranteed. According to the ship power system optimization control method and system based on the simulated annealing algorithm, the energy efficiency level and the environmental adaptability of the ship power system are improved.

The invention discloses an expressway slope photovoltaic grid-connected power generation system for cross energy fusion, and relates to the technical field of expressway slope photovoltaic grid-connected power generation. Comprising a main power grid dispatching sensing module, a reverse power transmission characteristic data acquisition module, an impact strength evaluation and classification module, a graded power regulation and control execution module and a self-adaptive regulation and control feedback module, the reverse power transmission characteristic data acquisition module is used for acquiring electrical characteristic data and power fluctuation characteristic data of the photovoltaic grid-connected point in real time and constructing a reverse power transmission evaluation data set when the judgment result is that the photovoltaic grid-connected point encounters transient reverse power transmission; and the impact strength evaluation and classification module determines the impact strength of the reverse current when the photovoltaic grid-connected point encounters transient reverse power transmission based on the constructed reverse power transmission evaluation data set, and classifies the impact strength. According to the invention, the problem that the photovoltaic grid-connected point cannot be dynamically regulated and controlled under the impact of transient reverse power transmission is solved, and the self-adaptive power regulation and control effect of impact strength identification and grading response is realized.

The invention discloses a grid-connected power fluctuation active stabilization control method and system for multi-source new energy, and relates to the technical field of grid-connected power control, and the method comprises the steps: reading equipment data after a multi-source new energy management device is connected; executing data acquisition of environment data, establishing a time sequence environment data set, performing environment prediction, and establishing an environment prediction result; performing collaborative relation identification based on an active identification complementary window, and establishing a collaborative relation identification result; executing initialization of the dynamic response virtual collaboration body; obtaining a time sequence load demand task, and generating a collaborative scheduling result; and carrying out active stabilization control management on grid-connected power fluctuation by utilizing the collaborative scheduling result. The technical problems that in the prior art, during multi-source new energy grid connection, power fluctuation is large, and the stability and reliability of a grid connection system are low are solved, and the technical effects that active stabilizing control over multi-source new energy grid connection power fluctuation is achieved, and the stability and reliability of the grid connection system are improved are achieved.

The invention discloses an electric power control method based on a diesel generator, commercial power and photovoltaic grid connection. The method comprises the following steps: acquiring operation data of commercial power, a diesel generator and photovoltaic-energy storage through an energy management system, constructing a multi-target dynamic optimization model, and distributing power by taking the lowest comprehensive operation cost, the highest power supply reliability and the minimum carbon emission as targets; the power analysis and regulation unit adopts a double-loop mechanism of outer-loop Kalman filtering prediction compensation and inner-loop model prediction control, synchronizes the voltage, frequency and phase of the side to be connected with the grid and the power grid side, and smoothly switches the power change rate of each energy source in the process through a self-adaptive sliding mode control strategy; and the grid-connected switching unit intelligently pre-judges the grid-connected switching opportunity by using a long short-term memory (LSTM) network and fuzzy logic fusion model. According to the invention, the energy utilization efficiency and the power supply stability are improved, multi-energy intelligent dynamic regulation and control are realized, the comprehensive operation cost of the system is effectively reduced, and reliable power supply under complex working conditions is ensured.

The invention relates to the technical field of power supply equipment power control. The load power track simulation control method comprises the steps of obtaining voltage information and current information of target power supply equipment, determining power deviation information and a dynamic target voltage range generated on the basis of a preset load behavior prediction model, constructing a combined regulation and control weight vector on the basis of the power deviation information, and obtaining a load power track simulation control result. According to the combined regulation and control weight vector and the dynamic target voltage range, constructing a target power evolution trajectory curve by using a physical response inversion mechanism, executing time discretization processing on the target regulation and control trajectory curve, extracting voltage change values and current change values corresponding to each time step, and calculating the target power evolution trajectory curve; and combining the voltage change value and the current change value according to a time sequence to form a control parameter sequence, and generating an analog control instruction matched with the target power evolution trajectory curve according to the control parameter sequence. The method has the effect of improving the real-time response capability of the power supply equipment under complex working conditions.

The invention relates to a sodium electric energy storage system dynamic partition power control method based on string type cluster level management, which comprises the following steps of: firstly, realizing physical isolation of battery clusters through a string type framework, configuring an independent power conversion module and a cluster level controller for each cluster, acquiring voltage, current, SOC (state of charge) and SOH (state of health) of each cluster in real time, and on the basis of the data, in a discharging or discharging process, determining the state of charge of each cluster; a dynamic partition strategy and automatic adjustment of power distribution are realized according to inter-cluster SOC, SOH, voltage range, temperature range, power limit and other differences, and an energy storage system is dynamically divided into a high-energy high-health area, a high-energy medium-health area, a medium-energy high-health area, a medium-energy medium-health area, a low-energy or sub-health area and a fault early warning area in a discharging and charging mode; and rapid balance of electric quantity among clusters is realized through the converter module, so that power distribution is ensured to meet power grid requirements, overcharge and overdischarge of batteries are avoided, and the service life of a battery system is prolonged.

The invention discloses a response control method for a charging station participating in a low-voltage treatment scene, and the method comprises the following steps: S1, collecting the voltage data of a charging pile, calculating a deviation, and judging a low-voltage grade; s2, when the deviation is in a light interval, outputting reactive power support voltage in proportion; s3, when the deviation exceeds a heavy threshold value, reducing active power and starting V2G feedback; s4, constructing a graph structure model, and extracting inter-node power coupling and user behavior factors; s5, inputting the model into an improved prediction controller, predicting a future voltage state, and optimizing and outputting a current period power control value; s6, power adjustment is executed, and feedback power is slowly output in the V2G stage; and S7, comparing the control deviation with the behavior factor change, updating the node control priority, and feeding back for rolling optimization of the next period. According to the invention, while the charging regulation and control precision is improved, the user experience and the voltage stability are effectively considered, and the method is suitable for various low-voltage treatment scenes.

The invention relates to the technical field of inverter power control, and discloses a given current-based inverter power control method and system, and the method comprises the steps: calculating a fluctuation compensation parameter based on a bus voltage, and carrying out the real-time compensation of a q-axis basic current, and obtaining a first given q-axis current; predicting the bus voltage of the next period and correcting the first given q-axis current in advance to obtain a second given q-axis current; on the basis of the stator voltage saturation state, weak magnetic d-axis current given is generated, low-pass filtering is carried out on the second q-axis current given and the weak magnetic d-axis current given, and a d-axis current instruction and a q-axis current instruction are obtained; a PWM driving signal corresponding to a dq-axis current instruction is generated, an inverter switch is controlled, meanwhile, a power deviation signal is collected to update q-axis basic current, accurate prediction of bus voltage and advanced correction of given current are achieved, compared with traditional lag compensation, the dynamic response is faster, and the power control precision and the operation stability are improved.

The invention discloses a double-closed-loop cooperative control method of a direct-drive electric chassis and a power system, relates to the technical field of power control of electric special vehicles, and provides a rotating speed and torque double-closed-loop cooperative control architecture, and realizes double-core real-time cooperative operation and dynamic optimization of motor output characteristics through a 32-bit processor. A direct-drive transmission structure is combined, a traditional speed reduction device is omitted, a flat wire motor directly drives a rear axle through a transmission shaft, and a four-in-one controller is matched, so that the system loss is reduced by 33%, and the power density is improved by 15%; on the basis of real-time temperature / electric quantity data of a lithium iron phosphate battery management system, control parameters are adaptively adjusted, and the bottleneck of performance attenuation in a low-temperature environment of-35 DEG C is broken through; and a high-voltage interlocking and insulation monitoring module is integrated, and an emergency hydraulic system is automatically switched when an electrical fault occurs, so that multi-stage safety guarantee is formed. According to the technology, the energy recovery efficiency is remarkably improved by 20%, and the wind resistance stability and the extreme environment reliability are effectively enhanced.

A converter (2) supplies a load (3) with electrical energy from a supply network (4). Using a desired power (P1*) of the load (3) and a state (Z) of the supply network (4), a control device (9) of the converter (2) determines a power (P2*) to be output by the converter (2) to the load (3). The control device (9) determines, using the power (P2*) to be output, control signals (C, C1, C2) for the converter (2) and controls the converter (2) by means of the control signals (C, C1, C2) such that the converter (2) outputs the power (P2*) to be output to the load (3). The control device (9) determines the state (Z) of the supply network (4) using variables (UZK, a, f) on which the determination of the control signals (C, C1, C2) is based.

The invention discloses an Internet of Vehicles communication resource allocation method based on multi-agent deep reinforcement learning. In order to solve the problems of dynamic channel interference, low resource allocation efficiency and multi-target collaborative optimization when a V2V link multiplexes V2I orthogonal spectrum resources in a cellular Internet of Vehicles scene, the method realizes joint optimization of discrete spectrum selection and continuous power control through agent autonomous decision and global collaboration, and improves the efficiency of resource allocation. The problem of quantization errors caused by an existing resource allocation algorithm with discrete action space is solved, the low delay and reliability requirements of the V2V link and the high-capacity communication requirement of the V2I link are effectively balanced, and the V2I link capacity is improved as much as possible while the transmission reliability of the V2V link is met.

The invention relates to the technical field of charging pile management, and discloses a new energy vehicle charging pile operation management system comprising a data acquisition module used for acquiring charging pile operation data and vehicle arrival data; the vehicle priority calculation module is used for calculating vehicle priorities based on the vehicle arrival data and a preset congestion coefficient and generating a vehicle queuing sequence; the scheduling pricing module is used for constructing a state matrix, matching a current operation state, extracting an energy storage control label and a pricing additional parameter, and generating an energy storage power control instruction and a service gear price; the execution control module is used for executing charging power issuing according to the service gear price, the preset station-level power demand and the energy storage power control instruction; and the parameter updating module is used for counting the triggering times of the operation state item and the queuing waiting duration of the corresponding period, and performing regularization adjustment on the pricing additional parameter. According to the invention, integrated management of intelligent scheduling and dynamic pricing based on a multi-dimensional operation state is realized.