50results about How to "Optimizing Scheduling Strategy" patented technology

The invention relates to the technical field of traffic management, and discloses a road obstacle clearance rescue enterprise automatic scheduling method comprising the following steps: S1, through multi-source data fusion and a dynamic convolutional neural network, generating a three-dimensional road model, and predicting accidents and congestion; s2, dynamically adjusting the priority of the rescue task by using a multi-target genetic algorithm in combination with real-time data; s3, path planning and cooperative scheduling are optimized through deep reinforcement learning and game theory algorithms; s4, dynamically correcting the path by using a vehicle-mounted sensor, and optimizing the flow and the energy consumption; s5, in an emergency, an emergency module based on reinforcement learning starts a plan and adjusts resources; and S6, after the task, analyzing an optimization strategy through collaborative learning, and carrying out self-improvement. According to the method, multi-source dynamic data fusion is carried out, a dynamic convolutional neural network is used for processing data in real time, a high-precision three-dimensional road environment model is generated, accidents and congestion are predicted, and it is ensured that a rapid and accurate scheduling decision can be made in a complex and changeable road environment.

The invention belongs to the field of power distribution network low-carbon economic optimization scheduling, and provides a power distribution network source network load storage low-carbon optimization scheduling increment reinforcement learning method and system, and the method comprises the steps: carrying out the intelligent agent division of a power grid, obtaining a plurality of intelligent agent regions, and collecting the observation data of each intelligent agent region; on the basis of the observation data, constructing a low-carbon economic dispatching model of source-grid-load-storage cooperation by taking the operation cost and carbon emission of each agent regional power grid as objective functions; designing the source-network-load-storage coordinated low-carbon economic dispatching model into a reinforcement learning model in a multi-agent environment according to a state space, an action space, an environment and a reward function; and solving the reinforcement learning model in the multi-agent environment to obtain an optimal scheduling solution. According to the incremental optimization method, the environment can help the intelligent agent to detect environment changes in training, excessive exploration risks are avoided, the training time is shortened, and meanwhile the flexibility of the system is improved.

The invention relates to the field of data processing, in particular to an instruction optimization scheduling method based on a large model and a related device. The method comprises the following steps: for a to-be-processed target model, carrying out dynamic and static analysis on the target model to convert the target model into a calculation task graph; determining a scheduling priority of each instruction in the target model based on a calculation task graph; the scheduling priority is associated with the importance and timeliness of the instruction path of each instruction in the calculation task graph; dynamically adjusting an instruction scheduling strategy in the calculation task graph based on the scheduling priority; and dynamically optimizing the instruction scheduling strategy according to the register pressure state monitored in real time, and executing the optimized instruction scheduling strategy. According to the method, instruction scheduling optimization can be achieved, the resource utilization efficiency is improved, the calculation requirement of a large model is met, and the overall model performance is improved.

The invention relates to the technical field of energy storage configuration, in particular to an energy storage configuration method and system for photovoltaic power generation. The method comprises the following steps: acquiring information data of a photovoltaic power generation energy station; performing distributed synchronous energy storage network construction on the photovoltaic power generation energy station information data to obtain a distributed synchronous energy storage network; performing real-time power generation data acquisition on the distributed synchronous energy storage network to obtain standard real-time photovoltaic power generation data; performing photovoltaic power generation prediction on the standard real-time photovoltaic power generation data to generate real-time photovoltaic power generation prediction data; performing historical electricity load data acquisition on the distributed synchronous energy storage network to obtain historical electricity load data; and performing load curve curvature trend analysis on the historical electricity load data to generate load curve curvature trend data. According to the invention, through real-time photovoltaic power generation prediction, load demand dynamic analysis and adaptive energy storage strategy optimization, the accuracy and flexibility of photovoltaic energy storage configuration are improved.

The invention discloses a distributed photovoltaic short-time output dynamic prediction method and system. The method comprises the following steps: acquiring micro-meteorological data, a cloud picture image and historical output data of a target area; calculating a building shadow shielding coefficient, and generating shadow influence factor time sequence data; obtaining cloud image occlusion index time series data based on the cloud image and a pre-constructed cloud image occlusion prediction model; fusing the data, and constructing and training a short-time output dynamic prediction model based on a long short-term memory network; predicting photovoltaic output by using real-time data and the trained model, and adjusting the model according to a prediction error and a confidence interval; according to the method provided by the invention, various factors such as microclimate, building shadow and cloud layer shielding are comprehensively considered, and the complex nonlinear relationship between the factors and the photovoltaic output is captured by using the deep learning model, so that the accuracy and robustness of distributed photovoltaic short-time output prediction are improved.

The invention relates to the technical field of smart power grids, in particular to a virtual power plant real-time regulation capability assessment method and system, and the method comprises the steps: obtaining real-time power consumption data and historical power consumption data of each power device in a virtual power plant, determining a power minimum interval unit, correcting data abnormity, and the like. Accurate evaluation of the real-time adjustment capability of the virtual power plant is realized; the method specifically comprises the following steps: acquiring power consumption data and historical data of power equipment, generating a load curve, determining a power minimum interval unit based on the historical data, and further performing anomaly correction on the data; on this basis, the maximum and minimum real-time adjustment capability of each power device is evaluated, and the overall adjustment capability of the virtual power plant is comprehensively evaluated; through the implementation of the method, the precision and efficiency of virtual power plant scheduling can be improved, and the stability and flexibility of a power grid under different load conditions are ensured; the scheme has high real-time performance and accuracy, and is suitable for scheduling optimization of a modern intelligent power grid.

The invention discloses a robot intelligent scheduling and management and control system and method for hospital delivery services, and relates to the technical field of realizing material delivery services by using robots. The scheduling platform determines the execution category according to the attribute of the transport work order, and when the execution category is robot execution, the scheduling platform assigns the transport work order to the robot according to an order insertion, sequential and / or proximity strategy; a shortest-time-consumption planning strategy is adopted, and the path of the robot assigned to convey the work order is planned; and when executing the work order, the robot interacts with the scheduling platform in real time and reports the task completion condition. The scheduling strategy of the transport work order is further optimized, the transport efficiency and the load rate of the transport robot are improved, and the scheduling platform can master the information of each node in the transport path in real time, so that reference is provided for subsequent planning of the transport path, and the transport efficiency of the transport robot is further improved.

The invention relates to the technical field of intelligent buildings and elevators, and discloses an intelligent elevator passenger flow analysis and optimization system which comprises a flow monitoring module used for monitoring the passenger flow of an elevator waiting area in real time and obtaining passenger flow data; the data processing module is used for analyzing the passenger flow data and predicting the passenger flow in a future time period; the elevator dispatching module optimizes the dispatching strategy of the elevator according to the prediction result of the data processing module, and improves the efficiency of passengers to get on and off the elevator; and the energy efficiency optimization module adjusts the acceleration and deceleration process of the elevator according to the running state of the elevator so as to reduce the energy consumption of the elevator. By monitoring the passenger flow in the elevator waiting area in real time and conducting accurate analysis, the passenger flow in the future time period can be predicted, the elevator dispatching strategy is optimized, the waiting time of passengers is shortened, the waiting efficiency is improved, and intelligent dispatching is conducted on the elevator based on the shortest waiting time and the minimum energy consumption target.

The invention relates to the technical field of solid waste sorting scheduling, in particular to a real-time monitoring optimization method and device for a solid waste collection, transportation and sorting ERP system. The method comprises the following steps: obtaining a real-time solid waste sorting log based on a solid waste collection, transportation and sorting ERP system; solid waste carrying vehicle tracking is carried out on the real-time solid waste sorting log, and a carrying track distribution visual view is constructed; acquiring an omnibearing monitoring image of a real-time sorting site; equipment sorting behavior visual identification is carried out on the real-time sorting site omnibearing monitoring image, dynamic sorting evolution is carried out, and a dynamic sorting twinborn model is constructed; carrying out multi-time-point solid waste sorting simulation on the dynamic sorting twinborn model, carrying out sorting load demand prediction, and generating a sorting load demand prediction value; and carrying out vehicle load calculation on the sorting load demand prediction value one by one, and then carrying out dynamic vehicle scheduling decision making to obtain a dynamic vehicle scheduling strategy. According to the invention, efficient and real-time solid waste sorting scheduling optimization is realized.

The invention provides an energy optimization scheduling method and system based on data analysis, and the method comprises the steps: collecting power generation data, load demands and meteorological data of solar energy, wind energy and an energy storage system in real time, and recognizing a power generation mode and a load change trend through a data analysis technology; based on an analysis result, a double-layer energy scheduling model is constructed, the main target is to maximize system reliability and scheduling flexibility and minimize carbon emission, and the secondary target is to minimize scheduling cost; introducing the uncertainty of wind and light output and the multi-joint constraint of information gap decision; and performing optimization solution by adopting a non-dominated sorting genetic algorithm NSGA-II in combination with a crowding distance and an elitist strategy, and outputting a Pareto leading-edge solution set to obtain an optimal scheduling strategy. According to the method, the timeliness and accuracy of scheduling decision making are ensured, the utilization efficiency of renewable energy sources is effectively improved, carbon emission is reduced, and powerful support is provided for an intelligent power grid and sustainable development.

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.

The invention discloses a load demand-based cross-period dynamic hydrogen storage planning method, which relates to the technical field of energy utilization and comprises the following steps of cross-period hydrogen storage system modeling, typical day selection and feature extraction, comprehensive energy system planning model establishment, random-robust two-stage optimization method solving and objective function design. By designing the introduction and modeling of the IHS, the energy transfer function is realized, the problem that energy storage equipment in a traditional power system cannot store energy across seasons is solved, the technical challenge of unbalanced power supply and demand is overcome, the permeability of renewable energy sources is improved, wind and light abandoning phenomena are reduced, and carbon emission is reduced. And the realization of low-carbon and green energy targets is promoted.

The invention provides a model training method and device, electronic equipment and a storage medium, and relates to the technical field of distributed computing. The method comprises the steps of dividing a context into context tasks based on structural analysis of a to-be-trained model; performing dependency relationship analysis on the context task to determine a task dependency graph; configuring priorities for the context tasks according to the task dependency graph, distributing the context tasks with the configured priorities to corresponding computing nodes, training according to an execution sequence, and obtaining load information and task execution information of the computing nodes; and according to the load information and the task execution information of the computing nodes, scheduling context tasks among the computing nodes, adjusting the execution sequence of the context tasks in the computing nodes, and outputting a training result. According to the real-time load condition of each node, task allocation is adjusted, load balancing of the computational nodes is realized, the utilization efficiency of computational resources is improved, a context task scheduling strategy is optimized, the utilization rate of the computational resources is improved, and the training time is shortened.

The invention discloses a CAN (Controller Area Network) bus test experiment system, which relates to the technical field of data processing and comprises a data acquisition and processing module for acquiring data frames from a CAN bus, adding timestamps and executing tasks such as data analysis, synchronization, filtering and caching; the control and display module is used for generating and sending a control instruction according to the vehicle state data and obtaining and updating the state information of the vehicle; the experimental report generation unit is used for sorting experimental data such as bit error rate, time sequence analysis and waveform detection into an experimental report; a plurality of test functions and experiment modules are integrated, and comprehensive support is provided for teaching and research of the CAN bus.

The invention provides an active distribution network scheduling optimization method comprising a micro-grid group, a medium and a system, and belongs to the technical field of active distribution network scheduling, and the method comprises the steps: obtaining an active distribution network parameter and a micro-grid parameter of each micro-grid in an active distribution network; calculating the similarity between any two micro-grids by using a preset micro-grid similarity function; establishing an active power distribution network stable scheduling equation set considering the power distribution network parameters and a micro-grid stable scheduling equation set considering the micro-grid parameters; a double-layer optimization model based on a grey wolf hunting optimization algorithm and a genetic algorithm is constructed, the grey wolf hunting optimization algorithm is used for active power distribution network optimization, and the genetic algorithm is used for microgrid optimization; when the grey wolf population is initialized, setting an initial population of a genetic algorithm for each micro-grid to represent various possible scheduling schemes in the micro-grid; by not executing outer-layer optimization and inner-layer optimization, the problem that the characteristics of the whole active power distribution network and the interior of the micro-grid are difficult to consider in the prior art is solved.

The invention belongs to the field of hydrological forecasting, and discloses a reservoir level prediction method based on a graph convolutional neural network (GCN). The method aims at solving the reservoir level prediction problem under the rainfall condition, and effective support is provided for reservoir dispatching. Rainfall image data are trained mainly through a graph convolutional neural network (GCN), and a bidirectional long-short term memory network (BiLSTM) is combined to extract time sequence features of the reservoir water level, so that a model capable of predicting the reservoir water level through rainfall images is constructed. Specifically, the GCN is used for extracting spatio-temporal features of a rainfall image and fusing the features by using a multi-head attention mechanism. In BiLSTM, an input time series data sequence is processed through LSTM networks in two directions, so that past and future information is captured at the same time. By combining the hidden states in the two directions, the model can understand the internal law of the time series data more deeply, so that the prediction precision of the reservoir level is improved.

The invention relates to the technical field of tracking management, in particular to an electric power building engineering material tracking and management system, which comprises a material identification module, a material management module, a material management module and a material management module, and is characterized in that all materials entering and exiting from a warehouse are identified and tracked in real time by using an RFID technology to ensure the traceability of material flows; the database management module is used for storing material related information; the material scheduling module is used for automatically analyzing project requirements and optimizing material distribution and scheduling strategies based on a scheduling algorithm; the environmental adaptability analysis module is used for evaluating the influence of different environmental factors on the material performance; the data analysis and prediction module is used for evaluating a material demand trend and price fluctuation by adopting a big data analysis technology; and the material compatibility and life cycle evaluation module is used for evaluating compatibility among different materials. According to the method, the high traceability of the material flow is ensured, the material distribution and scheduling strategy is optimized through the artificial intelligence algorithm, the resource waste is remarkably reduced, and the material use efficiency is improved.

The invention provides an AI-based zero-carbon park energy management method and system, and a medium, and aims at achieving the purposes of efficient utilization and zero-carbon emission of energy in a park through an intelligent scheduling strategy. According to the method, energy consumption demand estimation, carbon emission optimization, multi-energy system management and other technologies are utilized to carry out real-time monitoring and optimal scheduling on various energy use conditions of the park. Specifically, the system collects the power use condition in the park, and performs energy consumption demand estimation and carbon emission calculation through an AI model. And then, according to a demand estimation result and a carbon emission optimization model, an optimal energy scheduling strategy is selected, real-time feedback is obtained after scheduling execution, and a decision model is further optimized. And finally, realizing collaborative optimization of an environmental protection target and economic benefits by adaptively adjusting a discount factor and a weight balance mechanism.

The invention relates to an Internet of Things equipment deployment and control management method, in particular to a building Internet of Things equipment deployment and control management method. Comprising the following steps: deploying various sensors including an infrared sensor, a camera and an air quality sensor in a building, and collecting personnel flow and environment change data in real time; through data analysis and scene classification, the data are converted into scenes including office peaks, night modes and emergency evacuation of the building; training a scene recognition model by using a random forest classifier; a time sequence prediction model is adopted to predict scene change in a future short period, and a corresponding equipment control instruction is generated; the method comprises the following steps: establishing an incidence matrix of use frequency, spatial position and function interaction between devices by using sensor data, and identifying a device cooperation mode; dynamically generating an equipment deployment scheme through a graph theory algorithm based on the incidence matrix; issuing the generated deployment scheme to each equipment control node; and performing fine adjustment according to real-time data feedback.

The invention provides a mobile energy storage scheduling method and device based on a knowledge constraint depth expectation Q network, and studies charging and discharging decisions taking mobile energy storage as a main load support component, including emergency resource space-time coupling, uncertainty of an extreme meteorological scene, energy storage charging and discharging and time-space transfer constraint. Establishing a load recovery-oriented mobile energy storage elastic optimization scheduling model; based on a mobile energy storage elastic optimization scheduling model, integrating emergency resource space-time coupling, uncertainty of an extreme meteorological scene, energy storage charging and discharging and time-space transfer constraints into mathematical derivation of machine learning preprocessing so as to establish an energy storage Markov decision process covering optimization constraint knowledge fusion; and based on an energy storage Markov decision process, establishing an elastic scheduling process training agent based on a depth expectation Q network algorithm so as to optimize a scheduling strategy of the mobile energy storage system. According to the method, the elasticity of the system is enhanced, the calculation efficiency is ensured, and the problem of uncertainty is effectively solved.

The invention relates to the technical field of electric power regulation and control, in particular to an electric power regulation and control method and system based on a power characteristic matrix. The method comprises the following steps: obtaining distributed power plant equipment data, carrying out abnormal value replacement, generating complete equipment data, screening out standard operation parameters, carrying out equipment unit simulation processing, generating a simulation power plant equipment unit, and carrying out combined power generation simulation to obtain various simulation data; historical power output data are obtained, power demand analysis is carried out, power output data and power demand peak and valley data required by prediction are generated, based on the data, intensity adaptation screening is carried out on combined power generation simulation, an operation period is adjusted, and finally a distributed equipment scheduling instruction is generated, so that efficient regulation and control of the intelligent virtual power plant are realized. According to the invention, a more efficient and more reliable intelligent power regulation and control method is realized.

The invention discloses a distributed energy storage aggregator shared transaction method based on an improved particle swarm algorithm, and relates to the technical field of power systems, comprising: establishing an operation mode in which a distributed energy storage aggregator participates in demand response; establishing an energy storage model by considering the relationship between the charging and discharging times and the actual capacity of the battery; considering a power grid power balance constraint and a battery electric quantity constraint, and establishing a target function with the maximum daily income of the load aggregator; and solving by using an improved particle swarm algorithm. According to the distributed energy storage aggregator shared transaction method based on the improved particle swarm algorithm provided by the invention, a global optimal solution or a near-optimal solution can be found in a complex search space, so that a scheduling strategy of distributed energy storage equipment can be optimized more effectively; the profit of the aggregator is maximized or the effect of participating in the demand response transaction is achieved.

The present invention discloses an elevator call control method and system, the method comprising: receiving a user's call request for an elevator in a building, wherein the call request is sent through a mobile terminal or a fixed terminal, and the call request includes the user's current floor position and the destination floor position; calculating the request response time according to the call request and the current status information of each elevator in the building; sorting all elevators according to the request response time, screening the elevators whose request response time is lower than a preset threshold as preliminary response elevators; performing a secondary screening on the preliminary response elevators to obtain the final response target elevator. By using the embodiments of the present invention, the dispatching strategy of the elevator can be optimized, the waiting time of the user can be reduced, the operation efficiency can be improved, and the user's calling experience can be enhanced, meeting the needs of modern buildings for intelligent and humanized services for elevators.

The invention relates to the technical field of meteorological observation instrument power supply, and discloses a multi-source intelligent power supply management system and method for a meteorological observation instrument, and the method comprises the steps: obtaining prediction information data which comprises weather prediction data and solar power supply prediction data; according to the prediction information data, analyzing and processing the prediction information data through a weather judgment strategy to form analysis data; according to the analysis data, judging and processing the analysis data through a data adjustment strategy to form an adjustment result; adjusting the power supply module according to the adjustment result; through a weather judgment strategy and a data adjustment strategy, the utilization rate and the power supply quality of a power supply system are effectively improved, and energy waste and cost expenditure are reduced; through comparison of historical prediction data and forecast data, optimization of a scheduling strategy and improvement of stability and reliability of a power supply system are facilitated; the efficiency and economical efficiency of a solar power supply system can be integrally improved, and sustainable energy can be better utilized.

The present invention belongs to the technical field of lake and reservoir water ecology improvement and restoration, and discloses a method for suppressing thermal stratification of reservoirs by stimulating water flow oscillations through daily regulation and scheduling of reservoirs. The daily regulation and scheduling process of the reservoir causes gravity waves to form in the main stream of the reservoir, and induces high-frequency water flow oscillations in the tributary bay; the water level in the bay has high-frequency fluctuation characteristics through the water flow oscillation process, and the flow velocity of the water body in the bay is intermittently increased or reduced; the water body is intermittently mixed through the periodic high-frequency oscillation process, causing high-frequency fluctuations in water temperature, thereby achieving the effect of suppressing water temperature stratification. The present invention generates water level fluctuations in front of the dam by regulating the downstream flow of the hydropower station, triggering gravity waves in the main stream, and then inducing high-frequency water flow oscillations in the tributary bay. The present invention can effectively improve the density stratification characteristics of deepwater lakes and reservoirs. Compared with the currently commonly used engineering measures such as stratified water intake, water pumping and aeration, the present invention has the advantages of simple operation, easy implementation, and obvious effect.

The invention relates to a self-adaptive closed-loop context engineering method and device based on an intelligent agent, and belongs to the technical field of intelligent agents, and the method comprises the steps: outputting a context scheduling action intention for a current task stage through a reinforcement learning scheduling model in a decision-making layer based on a task type, a task demand and a current task state prediction decision; wherein the context scheduling action intention of the current task stage is an execution action in a predefined action space; mapping the action intention into at least one specific operation which can be triggered and executed on the execution layer on the execution layer, scheduling the action intention based on the context of the current task stage, and setting an execution condition for triggering the specific operation; and triggering and executing the corresponding specific operation based on the execution condition of the specific operation to obtain the task execution result, so that the intelligent agent can dynamically manage at least one of the context window, the associated memory network and the sub-intelligent agent cluster of the LLM intelligent agent, thereby being beneficial to improving the application efficiency of the intelligent agent.

The invention discloses a power generation scheduling optimization method and system based on power generation capacity prediction, and solves the problems of low power generation strategy formulation accuracy and low demand change response capability in the prior art, and the method comprises the steps: constructing a power generation capacity prediction model, defining key influence factors, and constructing a power generation capacity prediction model; dynamically adjusting the weight of each influence factor in different periods of power generation; calculating and analyzing the variation trend of the power generation cost along with time, analyzing and predicting the future power generation cost trend by using a time sequence, and establishing a cost saving strategy; combining the assessment indexes with a compensation mechanism, establishing an excitation model, and adjusting excitation model parameters according to the influence of equipment defects on the power generation capacity; and formulating a combined power generation scheduling strategy, and dynamically adjusting and optimizing the power generation scheduling strategy in combination with different operation scenes according to the execution effect. And by enhancing an excitation mechanism, the flexibility and response speed of a power system are improved, and safe and stable operation of a power grid is ensured.

The invention discloses a method for aggregating single small loads into large loads by considering uncertainty, and relates to the technical field of electric power systems, and the method comprises the following steps: dividing the single small loads into the following classes according to the uncertainty: the first class is that only the upper and lower bounds of the power of the single small loads are known; the second class is that the mode is known on the basis of knowing the upper and lower bounds of the power of the single small load; the third type is the distribution condition of most of power of the known single small load, that is, the power data set has been obtained; acquiring information of a series of single small loads, and classifying the information according to the information adequacy; establishing a probability density function for each single small load according to the classification; and discretizing different monomer small-load probability density functions in sequence and carrying out numerical convolution on every two of the different monomer small-load probability density functions to obtain a new probability density function, continuously carrying out convolution until only one probability density function is left, and taking the left probability density function as a probability density function of a large load formed after all small loads are aggregated.

The invention relates to the technical field of capacity credibility evaluation of capacity market subjects, in particular to a capacity credibility evaluation method for flexible resources participating in a capacity market. Comprising the following steps: sampling to generate a plurality of conventional generator set available output sequences; randomly generating output sequences of a plurality of new energy units; determining an energy storage output sequence according to the energy storage scheduling strategy; according to the available output sequence of the conventional generator set, the new energy output sequence and the energy storage output sequence, calculating an original reliability index value of the system added with the to-be-evaluated power generation resource; power generation resources to be evaluated are removed, a perfect unit with a certain capacity is connected, and a corresponding reliability index value is calculated; correcting the perfect unit capacity in the access system until the reliability index result is consistent with the original reliability index value or less than a limited error; the added perfect unit capacity is the credible capacity of the to-be-evaluated power generation resource, and the credible capacity is divided by the installed capacity of the to-be-evaluated power generation resource to obtain the capacity credibility.