422 results about "Load management" patented technology

The invention relates to the technical field of ship power systems, and discloses a ship comprehensive power system based on composite energy storage, comprising an energy generation module which comprises a diesel generator, a gas turbine and a renewable energy sub-module and is used for generating electric energy; the energy storage management module comprises a lithium battery, a super capacitor and a flywheel energy storage system and is used for storing and releasing electric energy; the energy distribution and scheduling module is used for controlling energy distribution between the energy generation module and the energy storage management module; the load management module is used for adjusting the load power requirement according to the load priority; and the health management and fault monitoring module is used for monitoring the operation states of the energy storage management module and the system in real time. Through cooperative work of multiple energy storage units and combination with optimization control of the energy distribution and scheduling module, characteristics of different energy storage devices are fully exerted. Therefore, loss in the energy conversion process is remarkably reduced, distribution and utilization of electric energy are optimized, and the overall energy utilization efficiency of the system is improved by about 15%-20%.

The invention relates to the technical field of intelligent control of transformer substations, in particular to a standardized intelligent control system of a transformer substation, which realizes real-time response to the running state of equipment by acquiring the current, voltage, power factor, temperature and humidity, operation state, insulation state and environment temperature and humidity of a power transformation unit in real time. A gradient boosting decision tree is combined with a variational auto-encoder and a self-attention mechanism, state vector features are extracted, complex abnormal states are accurately recognized, potential faults are detected in an early stage, and the monitoring efficiency and the early warning precision are greatly improved. The future power demand is accurately predicted by combining the long-short-term memory network model with historical and real-time load data, and the limitation of traditional static load management is overcome. Based on the predicted power demand, the reinforcement learning model is adopted to dynamically adjust the operation number of the power transformation units, optimal configuration of resources is achieved while the demand is met, and the overall operation efficiency of the transformer substation is remarkably improved.

The invention discloses a method and a system for realizing mine communication signal improvement based on edge computing, and relates to the technical field of mine communication signal improvement, and the method comprises the following steps: integrating a real-time monitoring system on each edge node, so as to continuously detect the fluctuation of communication flow and data request quantity, the real-time monitoring system identifies a potential communication peak period by collecting real-time data and generates an early warning signal to notify a network administrator or automatically trigger a load management program. According to the invention, through the real-time monitoring and early warning system on the edge node, active monitoring and peak prediction of mine communication are realized, the overload risk caused by traffic surge is reduced, and the stability of data transmission is ensured. And intelligent scheduling and dynamic resource allocation are combined, so that efficient execution of tasks under high load is ensured, and node overload is prevented. A self-adaptive load balancing and feedback mechanism enables the system to dynamically adjust distribution, quickly respond to a bottleneck and improve self-adaptability and stability.

The invention discloses an intelligent load management and allocation method for an electric meter box, relates to the technical field of intelligent power grid management and energy optimization, and solves the problems that the adaptability of load management in an existing electric meter box is insufficient, the prediction accuracy is influenced by data prejudice, and the dynamic adjustment capability is limited. According to the method, diversified data are collected and analyzed through a real-time data interface and a gradient boosting tree technology, a power consumption prediction model is constructed in combination with a long-short term memory (LSTM) network, and meanwhile, prediction performance is optimized by adopting a data enhancement algorithm and an adaptive enhancement algorithm; fast response and dynamic adjustment are realized by using a sliding window prediction method based on Kalman filtering, a load distribution strategy is optimized through an adaptive depth deterministic strategy gradient algorithm, and collaborative distribution scheduling and management are performed on cross-regional electric meter boxes through a distributed collaborative scheduling system; according to the invention, the stability and efficiency of the power system are greatly improved, and the energy utilization efficiency and economic benefits are remarkably improved.

The invention relates to the technical field of power equipment load management, in particular to a station electric equipment steady-state feature extraction system based on load awareness, and the system comprises a load data processing module which obtains load data based on the operation state of power equipment, analyzes the interaction effect between each type of load data, extracts the correlation features between parameters, and outputs the correlation features between the parameters; and identifying periodic characteristics and abnormal fluctuation of the load data to obtain a standard load data set. According to the method, more accurate and comprehensive steady-state feature extraction of the power equipment can be realized through multi-dimensional parameter analysis and processing of the load data. Meanwhile, the load data interaction effect is calculated, the incidence relation between the parameters can be better recognized and analyzed, the data consistency is ensured, and the feature extraction accuracy is improved. In data quantile analysis, data subsets of different quantiles are constructed, parameter characteristics under the steady-state condition are extracted, and subtle differences of equipment under different steady-state conditions can be captured.

The invention discloses an optimized dispatching control method and system for transformer area energy storage, and relates to the technical field of energy storage dispatching, and the method comprises the following steps: integrating an intelligent load management system with an energy storage system, thereby monitoring the electrical load of a transformer area in real time, and feeding back the real-time data to the energy storage system; historical load data and electricity price data are collected, a prediction model is trained, future load and electricity price are predicted in real time, and prediction data are generated. And according to a prediction result, a preliminary energy storage system scheduling strategy is formulated, and a target function R is constructed, so that the target function R can dynamically adapt to changing load and electricity price conditions. According to the invention, through tight integration of the intelligent load management system and the energy storage system, real-time monitoring of the power grid load and efficient scheduling of the energy storage system are realized; in other words, the energy storage system can charge or discharge at the best time in combination with accurate load and electricity price prediction and scheduling strategy rules, power grid resources are utilized to the maximum extent, and unnecessary resource waste is avoided.

The invention discloses a water-cooling central air conditioner load management and control method based on artificial intelligence, and relates to the technical field of load management and control. Load prediction is carried out by combining a long and short-term memory time sequence model and a physical constraint neural network in a water chilling unit load prediction link and utilizing historical data; errors are corrected through an energy balance equation of the water chilling unit, and the prediction accuracy is improved; multi-objective optimization control is adopted, COP maximization of a water chilling unit, energy consumption minimization of a cooling tower fan and cooling water supply temperature stability serve as optimization objectives, environment temperature and humidity prediction is combined, and a cooling water supply temperature set point and a cooling tower fan start-stop strategy are dynamically calculated; based on a cooling water supply temperature set point and a fan start-stop strategy, a water chilling unit, a cooling tower fan and a water pump are dynamically adjusted, and the high-frequency operation phenomenon is reduced through fan start-stop optimization.

The invention relates to a load regulation and control method and system based on reinforcement learning, and the method comprises the steps: 1, decomposing a multi-time scale optimization problem into a plurality of layers in a source network load storage management and control scene through employing a layered optimization frame, enabling each layer to correspond to a different time scale, and carrying out the optimization; a model prediction control algorithm is adopted in the short-term optimization layer, a mixed integer linear programming algorithm is adopted in the medium-term optimization layer, and a reinforcement learning method is adopted in the long-term optimization layer to solve a multi-objective optimization problem; and 2, long-term load regulation and control decision making: controlling the power grid to make different load regulation and control decisions through an actually adjustable reward mechanism based on reinforcement learning, so that the intelligent power grid load regulation and control system adapts to continuously changing environments and targets, and the flexibility and adaptability of the system are improved. According to the invention, the reliability and stability of power supply can be ensured, fine management and regulation of power loads are realized, and the operation efficiency, reliability and safety of a power system are improved.

The invention discloses a power grid intelligent scheduling decision-making system and method based on multi-source heterogeneous data fusion, and relates to the technical field of power grid intelligent scheduling, the power grid intelligent scheduling decision-making method based on multi-source heterogeneous data fusion specifically comprises the following steps: 1, collecting multi-source heterogeneous data, constructing a meteorological feature vector set, and predicting power grid load change; the method comprises the following steps of: 1, outputting a load prediction value, 2, fusing the load prediction value and an equipment health coefficient to construct a double-risk collaborative analysis matrix, generating a risk entropy value and mapping the risk entropy value into a standard risk mode, and 3, executing generator output pre-adjustment, energy storage charging and discharging control and interruptible load management in a grading manner according to the standard risk mode. Micro-grid resources are coordinated through the block chain; according to the method, the demand side prediction risk and the equipment health risk are orthogonally decomposed into multiple state modes by constructing a two-dimensional risk collaborative decision architecture, and the one-sidedness of a single risk factor decision is avoided.

The invention provides a high and low speed top pouring self-adaptive satellite on-orbit reconstruction method and system, and belongs to the field of satellite on-orbit reconstruction, and the method comprises the following steps: S1, providing a long packet reconstruction file with a fixed length; s2, in a high-speed uploading mode, the long packet reconstruction packet forms a high-speed uplink frame and then the high-speed uplink frame is uploaded; s3, in a low-speed uploading mode, splitting the long packet reconstruction packet into paired or clustered short packets, forming a remote control transmission frame, and uploading the remote control transmission frame; s4, in the uploading process, the satellite-borne management software checks the reconstructed packets one by one, checks the number and continuity after uploading is completed, returns missing and wrong packet information and supplementarily injects until all the reconstructed packets pass the check; and S5, after all the reconstructed packets pass the verification, the satellite-borne management software automatically processes the reconstructed packets of the long packets or the short packets according to the type of the uploading channel, and forwards the reconstructed packets to a terminal reconstruction unit according to a ground instruction. According to the method, adaptive switching of the length of the reconstruction packet along with the type of the upper injection channel is realized, and the efficiency and the reliability of satellite on-orbit reconstruction are improved.

The invention provides a distributed power supply communication gateway resource scheduling method and system based on dual-mode communication, and relates to the technical field of carrier wireless dual-mode communication, and the system comprises a time division module, a node evaluation module, a channel real-time monitoring module, a channel strategy making module, an efficiency monitoring module and a security analysis module. According to the invention, the output of the distributed power supply is monitored in real time and the access parameters are automatically adjusted to match the power grid demand, so that the efficiency and reliability of energy management are remarkably improved, the data loss is reduced, the communication security is enhanced, the nodes of carrier wireless dual-mode communication are identified, and the time distribution of the nodes in communication is verified; according to the method, the communication network can flexibly cope with load changes, load management of the network is optimized, resource waste or congestion caused by fixed time allocation is reduced, encryption keys are dynamically updated, abnormal data modes are identified, and data safety and tamper-proof capacity are greatly improved.

The invention relates to the technical field of big data analysis and data processing, and provides an intelligent power utilization load management method based on big data analysis, which constructs an accurate power utilization load prediction model by integrating historical power utilization data, climate data, a power grid equipment state and user behavior data. According to the method, the security and traceability of prediction data are improved by adopting a block chain technology, and automation of an electrical load management process is realized by means of an intelligent contract. The method comprises the specific steps of data acquisition and preprocessing, load prediction model construction and verification, prediction data storage and hash value generation, intelligent contract writing and execution, and process node data processing and evaluation. The method effectively solves the problems of load data abnormity and model errors, and improves the stability and management efficiency of a power grid system.

The invention relates to the technical field of intelligent power control, and discloses an intelligent power control system based on the Internet of Things, and the system comprises a monitoring terminal, a power execution device and a cloud platform control center which are in communication connection. The monitoring terminal collects current and voltage signals; the power execution equipment receives an instruction to switch the switch state; a load monitoring unit of the cloud platform control center determines a fault section and generates and maps a load characteristic curve, a prediction processing unit corrects a power supply path to generate an execution strategy, and a steady state regulation and control unit and a transient state regulation and control unit of the power control unit control execution operation under normal and abnormal working conditions respectively. The monitoring terminal comprises a data acquisition device and the like, and the power execution equipment comprises a circuit breaker and other modules. The system realizes intelligent monitoring, fault positioning and load management and protection of a power system, and improves reliability and efficiency.

The invention discloses a remote load removal and reset method for a large-current switch built-in electric energy meter, and relates to the technical field of intelligent power grids, and the method comprises the steps: collecting current data and voltage data in real time through a dynamic load monitoring module, and generating an early warning signal when the current data and the voltage data exceed a load threshold value; load data are synchronized in the distributed network, and a master control node sends an instruction to control load removal of the electric energy meter; and detecting the stable state of the load, and executing remote reset after a reset condition is met. According to the method, the system response speed and the overload detection capability are improved, the potential damage risk caused by overload to equipment and the system is reduced, the high efficiency and the reliability of load management are ensured, the efficiency and the reliability of load removal are improved, the safety and the stability of power grid operation are ensured, and the economic benefit is increased. The stability and reliability of power supply recovery are improved, the fault tolerance of the system is improved through an exception handling mechanism, and the stability of reset operation is guaranteed.

The invention provides a power load control method based on a multifunctional flexible adjusting unit, and belongs to the technical field of power load control. The power load control method based on the multifunctional flexible adjusting unit comprises the following steps: collecting current data and voltage data, monitoring the load condition of a special transformer user, and carrying out load identification by utilizing edge calculation so as to distinguish the power load type and the power load working state; constructing a load prediction model; acquiring historical load data stored in the terminal and the master station software; generating a prediction result in the load prediction model based on the historical load data, the power load type and the power load working state; and dynamically adjusting the operation state of the electric equipment based on the prediction result. According to the power load control method based on the multifunctional flexible adjustment unit, the refinement degree of load management and the accuracy of load prediction can be improved, and dynamic optimization scheduling can be realized.

The invention discloses a load management system based on a load model in the plastic product industry. The load management system comprises a load time sequence model building module which classifies and marks equipment according to operation behaviors of the equipment to obtain a load time sequence model; the data acquisition and fusion module acquires power, current, voltage and start-stop state data of equipment in real time through a monitoring point position, and generates a real-time load data set in combination with real-time production state data; the load prediction and adjustability evaluation module generates a load prediction curve by using a long short-term memory network, generates an adjustability score by adopting a support vector machine model, and determines an adjustable process list in combination with real-time production state data; and the scheduling execution module determines candidate adjustment equipment according to the load prediction curve, the adjustability score and the adjustable process list, constructs a multi-objective optimization function through a multi-objective optimization algorithm, and generates a load adjustment strategy by using a particle swarm optimization algorithm to execute scheduling on the equipment. According to the invention, the refinement level of load management is improved.

The invention relates to the technical field of power grid demand response, and discloses a power grid dispatching demand response system and method.The system comprises a state vector generation module, a state sequence generation module, a demand factor extraction module, a factor correlation analysis module, a weighted feature generation module and a resource dispatching module; the method comprises the following steps: generating a state estimation value of a power grid, carrying out vector coding to obtain a state vector, carrying out splicing and dimension reduction to obtain a state sequence, extracting demand factors from demand data, calculating a relationship among the demand factors through correlation analysis, weighting the demand factors according to factor correlation to obtain demand weighting characteristics, and finally, obtaining a state estimation result. And a load management strategy is generated based on the characteristics and the state sequence, so that resource scheduling is performed on the power grid according to the load management strategy, and the accuracy of power grid scheduling demand response is improved.

An adaptive IoT power plug system for intelligent load management and remote control, consisting of: a power plug housing configured to be inserted between a power outlet and an electrical appliance; an embedded sensor array comprising at least one voltage sensor, at least one current sensor, and at least one power sensor and configured to continuously monitor the electrical parameters of the connected device; a microcontroller unit (MCU) operatively coupled to the sensor array and configured to execute a load prioritization technique that dynamically determines power allocation based on real-time consumption data and user-defined priority levels for one or more connected loads; a semiconductor switching module electrically connected to the MCU and configured to selectively interrupt or modulate the power supply to the connected device based on commands from the load prioritization technology; a wireless communication module integrated into the MCU for bidirectional data exchange via at least one wireless protocol selected from Wi-Fi, Zigbee or Bluetooth Low Energy; a user interface that can be accessed remotely via a mobile or web application and enables the configuration of load priorities, real-time monitoring of power consumption, scheduling of device operation, and manual override of switching commands; and a power management subsystem including a power harvesting module configured to provide supplemental power to the system's electronic components, thereby reducing dependence on the main power source; The system autonomously adjusts the power distribution between multiple connected devices to load fluctuations and predefined user priorities in order to optimize energy efficiency and prevent overloading of the circuit.

The invention relates to the field of intelligent feeding control, in particular to a feeding control system for silicon steel sheet production, which comprises a conveying unit for conveying materials, a sensing feedback unit, an induction shooting unit, a laser positioning unit and a feeding control unit, the feeding control unit comprises a feeding control unit. The system comprises a communication interaction unit, a data analysis module, an image processing module, a control strategy module, a feeding management module, a fault monitoring module and an execution report module. Intelligent feeding control can be achieved, feeding accuracy is controlled by calculating and analyzing elaboration changes in the feeding process and combining feeding requirements and feature information such as the size, the shape and the surface quality of silicon steel sheets, and feeding control over the silicon steel sheets of different specifications can be adapted by monitoring and adjusting feeding strategies in real time; the overall efficiency of the production line is improved; and human errors and redundant time consumption are reduced, the production cost is reduced, and the production efficiency and the product quality are improved.

Systems and techniques are provided for wireless dynamic load management for electric vehicle (EV) charging stations. An example process includes receiving load usage data indicative of electric power consumed by EV charging station(s) on a site. Each of the EV charging station(s) may be simultaneously charging a respective EV. The example process includes determining a total electric power that has been consumed by an entire set of EV charging station(s) on the site based on the load usage data, comparing the total electric power that has been consumed by the entire set of EV charging station(s) on the site and a power threshold for the site, and based on the comparison of the total electric power that has been consumed by the entire set of EV charging station(s) and the power threshold, transmitting, to the EV charging station(s), a signal to control the electric power consumed by the EV charging station(s).

A facility for predicting on site electric power requirements for maintaining a fully electric fleet of vehicles in a mining operation to ensure sustainable electric operations, comprising a server comprising communications module configured to receive data and to transmit load management instructions; plurality of electrical charging stations; plurality of electric vehicles configured to be recharged by a selected electrical charging station; wherein the server comprises processor coupled with non-volatile memory, the non-volatile memory storing processing instructions that, when executed by the processor, causes the processor to simulate a total electrical power demand of the mine site due to the plurality of cabled mine equipment and the plurality of electric vehicles for each electric vehicle and each charging station within the facility over a prescribed period thereby to simulate and determine an energy storage capacity requirement of the charging stations of the facility through the prescribed period; thereby to forecast the electrical load management needs of the facility through the prescribed period.

The invention belongs to the technical field of charging pile management, and discloses a charging pile intelligent management method and system. Comprising the following steps: carrying out data acquisition on a target area and charging piles needing to be managed in the target area to obtain corresponding charging pile data and area load data; uploading the data to a pre-constructed scheduling block chain; performing electric pile diagnosis on the corresponding charging pile based on the collected electric pile data to obtain a corresponding fault diagnosis result, judging whether the charging pile has a fault based on the fault diagnosis result, and if not, marking the corresponding charging pile as a healthy electric pile; if the fault exists, fault information is generated and fault early warning is carried out; performing power distribution load management on the corresponding healthy electric piles in combination with the collected regional load data; according to the invention, intelligent management of the charging pile is realized, the operation efficiency and safety of the charging pile are improved, and more efficient power distribution load management is realized in combination with the charging demand of a user.

The invention discloses a load management operation method for comprehensive energy optimal configuration, and relates to the technical field of energy management, and the method comprises the following specific steps: microclimate partition division: carrying out the comprehensive field exploration of a target region, collecting the landform, building layout and vegetation coverage data, analyzing the influence of each factor on the microclimate formation, and carrying out the calculation of the microclimate; according to the method, a partition division basis is determined according to the difference between airflow and heat caused by topographic relief, the influence of a building on sunlight and ventilation and local microclimate characteristics of vegetation construction, and a linkage model comprehensively considering the relationship among a microclimate partition state, a building adjustment behavior and an energy load is established; the complex relation among microclimate parameter changes, building adjustment action changes and energy load changes is accurately reflected, meanwhile, according to state changes after building adjustment, the energy management system can dynamically optimize an energy configuration scheme, unnecessary energy transmission and conversion links are reduced, and the energy utilization rate is improved. And deep optimization configuration of comprehensive energy of the whole area from generation, transportation to use is realized.

The invention relates to the technical field of load management, in particular to a model and data driving combined user side load non-intrusive identification method. Comprising the following steps: extracting steady-state features and transient-state features of typical electric equipment; constructing a user side load non-intrusive identification architecture based on decision tree classification; the invention discloses a user side load non-intrusive identification algorithm based on multi-feature fusion. According to the design of the invention, through extraction of steady state features and transient state features of typical electric equipment, multi-dimensional feature quantity identification is carried out on load samples based on a decision tree classification criterion, and non-intrusive load identification is realized through feature quantity matching of similar loads; an identification criterion based on decision tree classification is established, and various types of electric equipment can be quickly decomposed from a user sample; the steady-state and transient-state multi-feature fusion of the electric equipment is applied to a load non-intrusive identification algorithm, so that the accuracy of the algorithm can be improved, and the calculation amount and time of the algorithm can be greatly reduced.

The invention relates to the technical field of deep learning, in particular to an airport charging pile load management method and system based on load prediction and a medium. Acquiring a current load data set in the airport power grid; inputting the current load data into an improved particle swarm algorithm-long short-term memory neural network model, and predicting predicted load data in a future preset time period, the improved particle swarm algorithm including an adaptive Cauchy variation mechanism; determining a plurality of charging pile load management strategies of the airport according to the predicted load data; on the basis of an improved raccoon optimization algorithm, an optimal charging pile load management strategy in the multiple charging pile load management strategies is determined, and the improved raccoon optimization algorithm comprises a first-time improved search strategy; and carrying out load regulation and control on each charging pile in the airport based on the optimal charging pile load management strategy. The objective of the invention is to solve the problems of how to predict load changes of different power utilization systems in an airport in advance and how to optimize and adjust the load state of an electric vehicle charging pile system in a transformer substation.

The invention belongs to the technical field of power equipment, and discloses a smart energy system based on a power electronic transformer and a monitoring method, and the method comprises the steps: installing a sensor; equipment operation data is collected in real time, and environment monitoring equipment collects environment data; the data processing module preprocesses the collected data; the abnormity monitoring module judges whether an abnormal condition exists or not; the fault detection module judges whether the system has a fault hidden danger or has a fault; the energy scheduling control module formulates an energy scheduling strategy; the electric energy quality collaborative optimization module ensures that the electric energy quality of the whole system meets the standard; and the load management unit manages different types of loads according to the hierarchical load control strategy. According to the invention, abnormal conditions and potential fault hidden dangers can be found; intelligent energy scheduling can be realized, energy utilization efficiency can be improved, electric energy quality can be cooperatively optimized, hierarchical load management can be realized, and key load power supply can be guaranteed; and a hierarchical load control strategy is adopted to carry out differential management on loads.

The embodiment of the invention discloses a load identification method and device for an industrial park, equipment and a medium. The method comprises the following steps: acquiring power consumption data of load equipment in an industrial park; inputting the power consumption data into a load feature recognition model to obtain initial load feature data; wherein the load feature recognition model is obtained by iterating a first model through a power consumption data sample set; matching the initial load characteristic data with a set load rule base to obtain a characteristic matching result; and determining a target load feature according to the feature matching result and the initial load feature data. According to the technical scheme, the load characteristics can be comprehensively recognized according to the load characteristic recognition model and the set load rule base, the accuracy and efficiency of load recognition can be improved, and the requirement of intelligent load management can be met.

The invention relates to the technical field of automobile charging station load systems, in particular to a new energy automobile charging station dynamic load optimization integration system and method based on multi-source data collaboration and elastic compensation. According to the system, charging pile power, meteorological data and user behavior information are fused in real time through a multi-source time sequence data set construction module, an LSTM neural network optimized by an improved sparrow algorithm is adopted to predict the remaining power capacity of a charging station, and Bootstrap resampling is combined to generate a confidence interval to realize safety boundary control; the self-adaptive firefly algorithm dynamically adjusts the charging pile power, establishes a multi-dimensional priority queue including SOC emergency degree, compensation willingness and social value, and guides users to charge in a peak shifting manner; the system comprises a 5G communication gateway, an IGBT power control module and a three-level early warning mechanism, and millisecond-level flexible adjustment of charging power is realized. The utilization rate of the transformer is improved to 91%, the peak-valley load ratio is reduced to 1.7: 1, the user waiting time is shortened by 63.5%, and a dynamic load management system of power grid-station-user collaborative optimization is formed.

The invention belongs to the field of power system optimization scheduling, and particularly relates to a virtual power plant optimization scheduling method based on machine learning. Firstly, real-time data such as generating capacity and load demand of a distributed power supply, an energy storage device and a load management system in a virtual power plant are collected, cleaned and standardized; then, a comprehensive objective function is constructed, and multiple factors including economic benefits, environmental benefits and electricity market price fluctuation are covered; then, an improved NSGA-II algorithm is adopted for optimization, a dual selection mechanism is combined with local and global optimality to accelerate convergence, crowding degree measurement is improved to accurately evaluate individuals, and self-adaptive crossover and mutation operation is dynamically adjusted according to a population. Through the method, maximum balance of economic benefits and environmental benefits can be realized, equipment operation constraints are met, the operation efficiency and stability of the virtual power plant are improved, and an innovative scheme is provided for optimization of a power system.

The invention relates to a double-generator unmanned aerial vehicle power distribution system architecture power distribution system and a power distribution method, and solves the problem that a main generator and a standby generator of an existing power distribution system fail when an engine fails. Comprising a primary power distribution system, a secondary power distribution system, a bus bar control unit BPCU and two electrical load management centers ELMC, the BPCU is responsible for primary power distribution control, and the ELMC is responsible for secondary power distribution control; the BPCU is provided with five power input sources, namely a left generator, a right generator, two ground power supplies and an emergency storage battery pack, and the BPCU distributes the power input sources to seven internal bus bars according to preset logic, namely a left / right generator bus bar, a left / right task bus bar, a left / right key bus bar and a storage battery bus bar; and the two electrical load management centers respectively obtain electric power from the front seven bus bars, and distribute the electric power to the terminal loads through internal SSPCs or direct connection lines. The method can prevent task equipment faults from affecting whole-aircraft power supply, and improves the reliability of fault isolation.