62 results about "Load optimization" patented technology

The invention relates to the technical field of server testing, in particular to a server multi-core computing processor load optimization testing method, device and equipment and a medium, and the method comprises the following steps: automatically identifying hardware configuration information of a server; generating a multi-dimensional pressure test plan based on the hardware configuration information; executing the test plan, and monitoring the load rate, the memory bandwidth, the cache hit rate and the I / O performance index of each CPU core in real time; dynamically adjusting a task allocation strategy based on a set load difference threshold to realize task dynamic optimization, and if the difference between the maximum core load rate and the minimum core load rate is monitored to exceed the threshold, triggering a task migration operation; system performance data are collected again, performance indexes before and after optimization are compared and analyzed, and system performance bottlenecks are recognized; and automatically generating a performance test report. The utilization rate and the overall task throughput of the multi-core processor are improved, and the problem that a static task allocation strategy is difficult to adapt to dynamic load changes is solved.

The invention is suitable for the technical field of electric vehicle and power grid interaction, and provides an electric vehicle charging and power grid load optimization scheduling method based on reinforcement learning, and the method comprises the steps: collecting power grid operation state data, electric vehicle user behavior data, weather environment data and traffic flow data; constructing a power grid dynamic model and a user state model; constructing a reinforcement learning scheduling model, wherein the reinforcement learning scheduling model comprises a state space, an action space and a reward function; a deep Q network is adopted to train and learn an initial strategy for the discrete action space, the continuous charging and discharging power is optimized based on a deep deterministic strategy gradient, and an optimized reinforcement learning scheduling model is obtained; the state space input of the optimized scheduling model is updated according to the collected data, the weight coefficient of the reward function is dynamically adjusted, a real-time charging and discharging scheduling instruction is generated, the electric vehicle charging requirement and the power grid load can be balanced, the power grid resource utilization rate can be optimized, and the system operation cost and the electric energy loss can be reduced.

The invention discloses a building flexible load regulation and control method, equipment and a medium, relates to the technical field of Internet of Things and intelligent control, and solves the problems of high communication cost and low response speed of an existing regulation and control method. The method comprises the following steps: acquiring environmental parameters and equipment operation data in a building, and transmitting the environmental parameters and the equipment operation data to an edge computing node through a low-power wide area network; the environmental parameters and the equipment operation data are preprocessed, logic judgment is conducted on the preprocessed data through a machine learning model, and a preliminary regulation and control instruction is generated; performing load prediction on the global information of the building and the preprocessed data abstract, generating a load optimization strategy, and issuing the load optimization strategy to an edge computing node; and regulating and controlling the preliminary regulation and control instruction according to a load optimization strategy to generate a final regulation and control instruction. Through a hierarchical architecture of edge computing and cloud collaboration, dual effects of fast local response and high global efficiency are obtained, and at the same time, low-cost control equipment is used to reduce deployment and communication costs.

The invention discloses a load optimization scheduling method, system and device for a virtual power plant and a medium, and the method comprises the steps: obtaining the target output data of a power grid system and the target electricity price data of the virtual power plant; a double-layer model is constructed, the double-layer model comprises a lower-layer uncertainty prediction model and an upper-layer multi-load optimization scheduling model, and the lower-layer uncertainty prediction model is used for predicting probability distribution of electricity price and renewable energy source output of the virtual power plant in a future time period; the upper-layer multi-load optimal scheduling model is used for generating a multi-load optimal scheduling strategy of the virtual power plant; inputting the target electricity price data and the target output data into the double-layer model to obtain a multi-load optimization scheduling strategy output by the double-layer model; and performing multi-load scheduling control on the virtual power plant according to the multi-load optimal scheduling strategy. The method can effectively improve the virtual power plant load optimization scheduling effect. The invention relates to the technical field of power dispatching.

The invention relates to the technical field of sewage treatment, discloses a sewage treatment dynamic load optimization method and system based on rhodobacter online monitoring, and aims to solve the problems of unstable process, effluent fluctuation, increase of energy consumption and material consumption and the like caused by lack of real-time accurate biological phase indication when the existing sewage treatment is used for coping with dynamic change of inflow load. According to the method and the system, biomass and physical and chemical parameters are obtained through online monitoring of rhodobacter and sewage parameters; after data preprocessing, dynamic load analysis is carried out to predict inflow water / biological load and a rhodobacter growth trend; the optimization decision module generates and controls the execution module to implement key operation parameter adjustment; and the man-machine interaction alarm module carries out visual management. According to the method, real-time quantitative evaluation of the biological phase is realized, the dynamic load adaptability, the operation efficiency and the effluent stability of the system are remarkably improved, and the energy consumption and the material consumption are reduced.

The embodiment of the application discloses a distributed cooperative load optimization scheduling method and system for power distribution cabinets. The technical scheme provided by the embodiment of the application accurately calculates the target power value and the corresponding maximum sustainable time of the second power distribution cabinet target load which can be safely reduced according to the adjustable type of the second power distribution cabinet target load and the set comfort constraint boundary, and executes scheduling control, realizes accurate quantization of adjustable capacity and dynamic matching of time dimension, improves the accuracy and execution success rate of cooperative response between distributed power distribution cabinets, and effectively realizes dynamic balance and optimization of regional load on the premise of ensuring equipment safety and user experience.

The application discloses a hydrogen refueling charging collaborative control method based on real-time load prediction and relates to the technical field of new energy vehicle hydrogen refueling charging control, which comprises the following steps: collecting multi-dimensional operation data through a hydrogen refueling station multi-scene load monitoring and analysis platform, mining load correlation and coupling relationship through a hydrogen refueling station load response adaptive model, deducing fluctuation trends and generating regulation and control parameters by using a load fluctuation compensation prediction algorithm, outputting load balance regulation and control instructions by using a dynamic load balance prediction model, and then constructing a collaborative control strategy set to dynamically regulate and control equipment operation parameters, energy distribution ratios and response time sequences. The method solves the defects of insufficient data fusion and lack of regulation and control collaboration in the prior art, realizes accurate multi-scene load adaptation and closed-loop regulation and control, and improves system operation efficiency and load optimization effect.

The invention provides an economic dispatching method and system for a steel smelting production process under demand response, and belongs to the technical field of steel industry load optimization dispatching. The method comprises the following steps: establishing an objective function of price and incentive joint demand response according to power demand response; establishing a state task network model of the iron and steel smelting production process according to the iron and steel smelting process flow; wherein the state task network model is used for representing a coupling relationship between a material flow and a process; establishing production constraint conditions of steel smelting according to the state task network model; and jointly solving the objective function and the production constraint conditions to obtain a scheduling scheme of the steel smelting production process. The method can fully excavate the potential of the industrial load participating in the demand response, effectively optimizes the production scheduling scheme of steel smelting under the demand response, and achieves the balance of economic benefit, production flow and production safety.

The invention discloses a source network load intelligent enhanced storage optimization operation method and a related device. Comprising the following steps: inputting topological structure information of a graph model of the source network load storage system, feature information of graph nodes in the graph model of the source network load storage system and feature information of graph edges in the graph model of the source network load storage system into a trained physical information graph neural network model, the physical information graph neural network model is trained based on a physical constraint equation set of a graph model of the source network load storage system to obtain an optimized operation strategy of the source network load storage system, the source network load storage system is controlled according to the optimized operation strategy of the source network load storage system, and the physical information graph neural network model is trained based on a physical constraint equation set of the graph model of the source network load storage system. According to the method and the related device, the physical consistency and reliability of source network load storage optimization can be improved.

The invention discloses a flexible load optimal scheduling method and device based on chaotic mapping, terminal equipment and a storage medium, and belongs to the field of flexible load scheduling. The method comprises the following steps: clustering a plurality of flexible loads according to user behavior data and a power curve to generate a plurality of load clusters; the method comprises the steps that a constraint function set is established, a load curve and a load adjusting range of the cluster center of each load cluster are determined, a plurality of initial scheduling schemes are generated through chaotic mapping according to the load curve and the load adjusting range of each cluster center, and iterative optimization is carried out on the initial scheduling schemes according to the target function under the constraint of the constraint function set to obtain the optimal scheduling scheme. Generating a target scheduling scheme; and scheduling the flexible load according to the target scheduling scheme. Therefore, the method solves the problem that the existing method does not consider the space-time association rule and the dynamic adjustment capability of the load and is difficult to realize the efficient calling of the flexible resources.

The invention relates to the technical field of energy internet control, and discloses a virtual power plant load optimization control method based on demand response. The method comprises the steps that real-time operation data and a power grid instruction are automatically obtained, dynamic behavior characteristics such as the load change rate and the fluctuation period are mined after data cleaning, and a load control strategy draft is generated according to the dynamic behavior characteristics. And then configuring control node parameters and collecting performance data, obtaining a current dynamic operation constraint of the system through simulation calculation, carrying out load distribution optimization solution on the condition, and finally generating a control instruction sequence and carrying out deployment execution. According to the method, the matching degree of the control strategy and the actual load response capability is improved through load dynamic behavior characteristic analysis, the feasibility of the optimization result is ensured by utilizing the dynamic constraint defined by simulation feedback, and more accurate and safer virtual power plant load regulation is realized.

The invention relates to the technical field of power systems, and discloses a multi-time-scale computing power load management method and system, and the method comprises the steps: obtaining the historical operation data of all types of data centers; sequentially analyzing computing power load characteristics and corresponding processing adaptation rules of various types of data centers under multiple time scales on the basis of the historical operation data; in response to the load optimization signal, performing integration processing on the obtained real-time operation data of the target data center based on computing power load characteristics and corresponding processing adaptation rules to obtain multi-source real-time data under multiple time scales; inputting the multi-source real-time data into the computing power load dynamic prediction model to obtain computing power load prediction results of the target data center under different time scales; and carrying out migration scheduling on the time-adjustable task of the target data center based on the calculation power load prediction result so as to realize load management optimization of the target data center. According to the method, the utilization efficiency of the computing power load is improved.

The invention discloses a load optimization method of an automobile controller and related equipment, which can configure codes of application software in an initial software integration stage so as to control a rack on which the codes are established, and can optimize the load of the application software after each time of code submission. Resource reports such as a static resource report and a stack use report and a real vehicle load test result are automatically generated and are finally used as a basis for enabling the load rate to meet a standard, and analysis reports and alarm mechanisms in the two aspects are integrated into a development and integration process by positively monitoring static resources of a controller and the use condition of a stack area; the load problem can be actively found and solved in the early stage of a project, and the maturity and reliability of controller software are greatly improved, so that the problems of operation clamping stagnation caused by over-high load of the controller, vehicle function failure caused by resetting and the like are solved, and traffic safety is guaranteed. The invention is widely applied to the technical field of automobiles.

The invention relates to the technical field of hydropower dispatching operation, in particular to a real-time load optimal distribution method and device between cascade hydropower stations and a medium, a hydropower station group system is generalized according to a hydraulic relationship and reservoir inflow, and a cascade reservoir group is simulated; constructing a load distribution model according to the constraint relationship, building a solving framework, designing an environment state, a reward function and an intelligent agent of the solving framework, and training the intelligent agent; and solving the load distribution model based on the solving framework, screening selectable load distribution schemes according to constraint conditions and distribution requirements, and outputting a final load distribution scheme in combination with a water level control target and water energy utilization efficiency, thereby realizing dynamic simulation of a real-time operation process of the cascade power station and optimization of an inter-station load distribution scheme. In a novel electric power system, regulation and control of multi-target tasks such as flood control and power generation can be taken into consideration, the decision-making efficiency in the model solving process is effectively improved, and quick response to load distribution under the high-intensity peak regulation and frequency modulation background is achieved.

The application discloses a kind of screen projection type HUD system load optimization method, system and storage medium, the method includes: HUD display screen is divided into multiple regions, including basic information display area and dynamic screen projection display area, basic information display area simultaneously as resource buffer area;Real-time monitoring HUD end and the system resource state of mobile terminal, according to the display mode of the display mode of basic information display area according to monitoring result;Dynamic frame selection effective UI display partition, only transport the image data of effective UI display partition, monochrome filling is carried out to non-UI display partition;According to the display refresh rate of each region of vehicle driving scene dynamic adjustment.The application reduces system load effectively by resource collaborative allocation, invalid data transmission reduction and scene adaptive refresh rate adjustment, and improves screen projection fluency.

This invention discloses an AI-based method for cross-border e-commerce logistics scheduling and load optimization, belonging to the field of cross-border e-commerce logistics technology. It includes deep data preprocessing and priority scheduling, multi-mode backtracking search algorithm matching for quotations, physical and business dual verification, global multi-objective competitive optimization, end-to-end dynamic cost calculation, and instruction-based output and execution. This invention achieves three-dimensional loading optimization and dynamic load allocation through AI constraint solving algorithms, improving container space utilization to the algorithm's optimal level and shortening the manual container arrangement process from several hours to seconds. It enables rapid response to order and container changes, thereby improving the efficiency and space utilization of cross-border e-commerce logistics. Furthermore, by constructing a nested hash index and a dynamic cost engine, it traverses supplier quotations across the entire chain in milliseconds, uncovering low-price combinations that cannot be identified manually, reducing overall logistics costs, and increasing enterprise profitability, thus achieving optimal end-to-end costs.

To address the problem that existing technologies, which do not consider torque mismatch under fault ride-through and low-frequency oscillation conditions, cannot avoid system oscillations and shutdowns caused by torque mismatch during fault conditions, this invention provides a load optimization control method for voltage source wind turbines. This method optimizes the power coordination characteristics between the wind turbine's main control system and the converter under voltage source control mode, avoiding system oscillations and shutdowns caused by torque mismatch. Simultaneously, it reduces the load impact on the drive train shaft system of voltage source wind turbines under different grid conditions such as voltage surges, voltage dips, and low-frequency oscillations, thereby improving the mechanical lifespan of the wind turbine throughout its entire lifecycle. By calculating and superimposing electromagnetic torque disturbances based on different control objectives before and after a fault in the voltage source wind turbine, it avoids shutdowns caused by torque mismatch during fault ride-through. Furthermore, by calculating and superimposing electromagnetic torque disturbance components based on the expressions for stator and rotor current disturbance components caused by voltage disturbance components, it avoids load oscillations caused by system oscillations.

The invention discloses a load optimization distribution method and device considering frequency safety under deep peak regulation. The method comprises the following steps: constructing a first objective function with the lowest total coal consumption and a second objective function with the lowest NOx emission; constructing a single-objective optimization function based on the first objective function and the second objective function; constructing general constraint conditions by using power balance constraint, output upper and lower limit constraint and primary frequency modulation capability, and constructing frequency safety constraint; according to the single-target optimization function, the general constraint condition and the frequency security constraint, constructing a load optimization distribution model considering the primary frequency modulation capability; and performing optimization calculation based on the load optimization distribution model to obtain a load optimization distribution result.

The invention relates to the technical field of three-dimensional data processing, and discloses a three-dimensional data loading optimization method and system. Comprising the following steps of S1, request interception mechanism establishment, S2, cache key value extraction and mapping, S3, cache state maintenance and dependency relationship construction, S4, cache hit judgment and local return, S5, multimedia resource independent caching, S6, cache life cycle management and S7, Cesium engine integration. The three-dimensional data caching system provided by the invention provides a feasible solution for efficient loading of large-scale three-dimensional geographic space data, has good expansibility and application prospects, and can be further expanded to support more three-dimensional engines and data formats along with continuous development of technologies such as digital twinning, smart cities, VR / AR and the like; and in combination with edge calculation, intelligent preloading and cross-platform application, the data loading efficiency and user experience under multiple scenes are improved, and a solid foundation is provided for constructing a high-performance and low-delay three-dimensional visualization system.

The present application relates to the technical field of ship operation, and provides a container loading optimization method based on real-time scheduling and discrete event simulation. The method establishes a loading scene model containing multi-platform loading demand, container characteristic parameters and resource parameter configuration, adopts a double-layer coding scheme of loading sequence priority sequence and loading mode identification generated by a genetic algorithm, dynamically advances a time pointer to handle loading events such as vertical operation and hoisting operation by using discrete event simulation, solves resource contention problems in combination with loading priority, takes the total loading time as a fitness index, iteratively optimizes through selection, crossover and mutation evolution operations, and finally outputs a loading sequence and mode combination scheme that minimizes the loading time. The present application effectively coordinates loading resources, reduces operation waiting time, and improves overall loading efficiency in a multi-ship parallel operation scene. Meanwhile, the combination of the genetic algorithm and the discrete event simulation enhances the optimization capability and adaptability for complex loading processes.

The invention discloses a metering transformer fault intelligent prediction method and system based on machine learning, and relates to the technical field of electric power metering monitoring, and the method comprises the steps: collecting the electrical parameters, load data and environmental parameters of a metering transformer, and carrying out the multi-modal fusion analysis to extract a key feature sequence; constructing a degradation analysis model based on machine learning in combination with historical operation data and shared data of equipment of the same model; and predicting the degradation state of the core component by using the degradation analysis model, calculating a health state score, performing fault risk assessment, and performing intelligent load distribution optimization according to a fault risk assessment result. The technical problems that in the prior art, fault early warning is difficult to carry out in the early stage, load distribution cannot be dynamically adjusted, and the service life of equipment is affected in a traditional method are solved, early fault early warning of the metering transformer is achieved through degradation analysis and health assessment of the core component, and the service life of the equipment is prolonged. And the service life of the equipment is prolonged through load optimization.

This invention discloses a method for optimizing load distribution in planetary roller screws based on multi-source error matching. It relates to the field of model correction technology. The method includes the following steps: S1, based on a preset multi-roller load distribution theoretical model, a complete dataset of multi-roller load distribution coefficients is obtained through simulation calculations and data acquisition; S2, using this dataset as samples, a neural network surrogate model is constructed to establish a precise mapping relationship between multi-source errors and multi-roller load distribution coefficients. This invention can accurately and efficiently determine the optimal solution for load distribution uniformity and the corresponding optimal matching scheme for multi-source errors. It utilizes a neural network to establish a complex nonlinear mapping relationship from multi-source errors to load distribution, replacing time-consuming high-precision physical simulation. Simultaneously, it employs a two-level collaborative optimization strategy: first optimizing load distribution among the rollers, and then optimizing load distribution on each thread tooth of the roller screw and nut, solving the problem of uneven load distribution between multi-roller and threaded pairs in engineering.

The invention discloses a load optimization method, device and equipment for vehicle machine network flow query, and a storage medium, and relates to the technical field of vehicle network communication, and the method comprises the steps: triggering a flow query request under the condition that a query condition is satisfied; verifying the traffic query request to obtain a query result corresponding to an effective traffic query request; and under the condition that the query result is abnormal, taking the network flow state stored in a cache region within a preset time as a target query result. Due to the adoption of the technical means of combining on-demand triggering and cache exception rollback, the problem of network state misjudgment caused by instantaneous overload or exception of an operator interface is solved; the technical effects that available network state data can still be provided for the vehicle machine when the network interface fluctuates, and therefore stable operation of core functions such as voice and navigation is guaranteed are achieved.

The invention discloses a frequency conversion control system based on load optimization, which belongs to the technical field of motor control, and comprises a frequency converter, the output end of the frequency converter is connected with an output cable, the length of the output cable is not more than 100 meters, the frequency converter is a three-phase voltage type frequency converter, an insulated gate bipolar transistor is adopted as a power switch device, and the power switch device is connected with the output cable. The output end is connected with the motor through an output cable. And the filtering assembly is connected to an output cable of the frequency converter and comprises a plurality of filtering bands, and each filtering band is used for suppressing harmonic waves with specific frequencies. According to the invention, the length of the output cable does not exceed 100 meters, and the cable is connected with the filtering assembly, so that harmonic waves in pulse width modulation waves output by the frequency converter are effectively suppressed, and the problems of peak voltage and peak current caused by long cable transmission are avoided, thereby protecting motor insulation and bearings from being damaged, and prolonging the service life of the motor. The problems of harmonic superposition, peak voltage and peak current caused by an overlong cable are effectively solved.

The invention discloses an intelligent regulation and control method for a medical image equipment power distribution system based on artificial intelligence, relates to the technical field of medical equipment power distribution, and solves the problems that an existing medical equipment power distribution method lags in response, is low in key parameter monitoring precision, is insufficient in fault recognition accuracy, is difficult to find potential hidden dangers in time, and is poor in fault recognition accuracy. And finally, medical power distribution is not efficient enough. Acquiring power diagnosis data; generating a plurality of diagnostic data based on the power diagnostic data; inputting the diagnosis data into a fault diagnosis model to obtain a diagnosis result, wherein the fault diagnosis model is constructed by a CNN-SVM hybrid model and an LSTM model; the diagnosis result comprises a fault diagnosis result and a fault prediction result; generating an execution strategy based on the diagnosis result; acquiring diagnosis and treatment equipment data and real-time power load data; inputting the execution strategy, the diagnosis and treatment equipment data and the real-time power load data into a load optimization model to obtain a load optimization decision; and efficient power distribution of medical equipment is realized.

The application discloses a hydropower station load distribution method based on a DDPG algorithm and a deep learning model, first, the operation condition parameters of the hydropower station are acquired, the hydropower station comprises a plurality of hydropower generating units; a hydropower generating unit load distribution model is constructed, a target function and constraint conditions of the hydropower generating unit load distribution are determined with the minimization of total water consumption in the hydropower station dispatching period as a target, a calculation model of the target function is based on a deep learning model of an improved long short-term neural network; a solution target of the hydropower generating unit load distribution model is converted into a Markov decision process, variables include a state space, an action space and a reward function; a hydropower generating unit load optimization distribution model based on the DDPG algorithm is established and trained; and an optimal distribution scheme is solved according to the trained model. The hydropower generating unit load distribution model based on the DDPG algorithm has efficient task completion capability and can adapt to complex and changeable working conditions of the hydropower generating unit.

This invention provides an industrial load optimization scheduling method and system that integrates AI intelligent agents and dynamic boundary constraints. The method utilizes AI intelligent agents to analyze production intentions and dynamically adjust process constraint boundaries to achieve optimized scheduling of industrial loads driven by price signals. This method can maximize the potential for cost reduction and peak avoidance for enterprises while ensuring production continuity and product quality. The actual measured target is to reduce electricity costs by more than 15% compared to the traditional static model.

The invention discloses a load optimization method and device for a supercritical traditional generator set in closed-loop operation. The method comprises the following steps: acquiring load operation data of the supercritical traditional generator set in a closed-loop operation state; analyzing a response relationship between each operation parameter and a load instruction in the load operation data, establishing a closed-loop operation model of the supercritical traditional generator set, and constructing an optimization constraint condition and a load optimization objective function in combination with a plurality of optimization dimensions; and solving the load optimization objective function by adopting a multi-objective evolutionary optimization algorithm in combination with the optimization constraint condition to obtain an optimal load instruction solution set and determine an optimal load instruction. By constructing a closed-loop operation model of the supercritical traditional generator set and combining an optimization constraint condition and a load optimization objective function, an issued load instruction is softened and corrected, so that the load instruction is more in accordance with an actually reachable dynamic behavior of the supercritical traditional generator set; therefore, stable and efficient operation of a supercritical traditional generator set in a high-proportion new energy system is supported.

The present disclosure relates to a load optimization method, device, equipment, medium and vehicle of a vehicle, wherein the load optimization method of the vehicle comprises: obtaining first monitoring data, wherein the first monitoring data is monitoring data directly collected by a monitoring and measuring system; obtaining second monitoring data from a vehicle-mounted operation system, wherein the second monitoring data is data corresponding to the monitoring and measuring system performing a preset monitoring task generated by the vehicle-mounted operation system in the running process; and analyzing and processing the first monitoring data and the second monitoring data to obtain a monitoring result of the vehicle. According to the embodiment of the present disclosure, part of the data generated by the vehicle-mounted operation system in the running process can be used as the second monitoring data, and then when the vehicle is monitored, the monitoring and measuring system can directly use this part of the data for monitoring without the monitoring and measuring system re-collecting, thereby reducing the load of the vehicle-mounted operation system and ensuring the normal operation of the vehicle.

This invention discloses a distribution cabinet load optimization system based on ant colony optimization, belonging to the field of power system automation technology. It includes a data acquisition module, a load analysis module, an ant colony optimization module, an execution control module, and a data storage module. These modules are electrically connected sequentially and work together to dynamically optimize the distribution cabinet load. The ant colony optimization module uses "load balancing, reduced distribution losses, and guaranteed power supply stability" as multi-objective optimization goals. It constructs an optimization model based on load analysis results and solves the optimal load allocation scheme using an improved ant colony algorithm. The improved ant colony algorithm uses a "maximum-minimum multiplication and minimum" strategy to update pheromones. Through the collaborative work of these modules, combined with the improved ant colony algorithm and multi-objective optimization strategy, this system effectively solves the technical problems existing in current distribution cabinet load optimization, such as poor algorithm performance, uneven load allocation, insufficient power supply stability, and low operation and maintenance efficiency.