Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

28results about How to "Solve scheduling problems" patented technology

Gravity energy storage device with function of uninterruptible loading and unloading of weight blocks

The invention provides a gravity energy storage device with a function of uninterruptible loading and unloading of weight blocks, the gravity energy storage device comprises a transportation module and a loading and unloading module, the transportation module comprises a rotating wheel part, a chain part and a bearing mechanism, the bearing mechanism is arranged on the chain part, the rotating wheel part is arranged at the end part of the transportation module, and the chain part moves around the rotating wheel part; the loading and unloading module comprises a conveying channel, a supporting mechanism and a weight block body, the supporting mechanism is arranged on the conveying channel, the weight block body is arranged on the supporting mechanism through driving of the conveying channel, and the supporting mechanism and the bearing mechanism can be coupled or decoupled to drive the weight block body to be separated from or connected with the supporting mechanism. According to the gravity energy storage device with the function of uninterruptible loading and unloading of the weight block, stable and continuous electric energy can be generated during power generation and energy storage under the condition that the device is uninterruptible when the weight block body is loaded and unloaded and the transportation module generates power, and under the condition that equipment does not need to be added, the power generation power and the operation efficiency are improved, and the cost is reduced.
Owner:BEIJING SHIDAI CHONGSHU TECHNOLOGY CO LTD

Reservoir group scheduling interval multi-objective optimization method under uncertain condition

The invention discloses a reservoir group scheduling interval multi-target optimization method under an uncertain condition, and belongs to the technical field of reservoir optimization scheduling. The method comprises the following steps: firstly, establishing an innovative cascade reservoir group interval multi-target scheduling model; secondly, providing a double-population dynamic coordination interval optimization method for solving the interval multi-target scheduling model, and further obtaining an optimal scheduling scheme of the reservoir group; and finally, outputting an optimal scheduling scheme set of the reservoir group. According to the optimization method, through organic combination of a chaos-order mapping initialization strategy, a dynamic adaptive mutual promotion updating strategy and an elite guidance optimization strategy, optimization is rapidly and efficiently carried out to obtain a group of reliable and accurate scheduling scheme sets considering runoff uncertainty; an effective decision-making technical means for solving the cascade reservoir group optimization multi-target complex engineering problem is provided for a scheduling decision maker, the intelligent level and comprehensive benefits of water resource management are improved, and the capacity of a water resource system for coping with complex environments and uncertain factors is further enhanced.
Owner:HOHAI UNIV

Collaborative resource scheduling method and system based on programmable network

The invention discloses a collaborative resource scheduling method and system based on a programmable network. The method comprises the following steps: performing performance modeling on heterogeneous computing resource data in all computing resource data to obtain a uniform resource performance index; defining target computing resource data required by multi-dimensional resource demand services, and determining matching relationship information between each multi-dimensional resource demand service and the current computer cluster; in the deployment process, according to all the matching relation information, the correspondingly selected multi-dimensional resource demand service is deployed to each computer cluster; determining a shortest deployment path between the routing nodes in each computer cluster based on a Floyd algorithm; and in the actual scheduling process, executing the computing power arrangement scheme generated in the deployment process. According to the collaborative resource scheduling method and system based on the programmable network provided by the embodiment of the invention, the utilization rate of computing power resources in a wide area network can be improved, and a computing power scheduling strategy is dynamically generated.
Owner:STATE GRID ZHEJIANG ELECTRIC POWER CO LTD

Integrated energy system scheduling method based on optimized reinforcement learning DDPG

The invention discloses a comprehensive energy system scheduling method based on optimized reinforcement learning (DDPG), and aims to improve the scheduling efficiency and adaptability of the system by establishing a comprehensive energy system model containing four energy sources of electricity, heat, cold and hydrogen and performing optimized scheduling based on an optimized depth deterministic policy gradient algorithm (DDPG). A simulation result shows that under a typical daily working condition, the convergence of the DDPG algorithm is optimized, the efficient scheduling of the integrated energy system is realized, and the four kinds of energy storage equipment operate in a reasonable working condition. According to the method, the optimization performance and the stability in a complex continuous decision problem are remarkably improved by processing a continuous action space, efficient strategy learning, experience playback, a target network and other mechanisms. The research of the invention provides theoretical support for the application of the deep reinforcement learning technology in the multi-energy coupled integrated energy system.
Owner:LIYANG RES INST OF SOUTHEAST UNIV +2

Dynamic flexible job shop scheduling method considering multiple types of events

The invention discloses a dynamic flexible job shop scheduling method considering multiple types of events, which realizes simulation of shop scheduling and design of rules through establishment of a model, completes identification of dynamic events, and realizes scheduling of the multiple types of events when a single dynamic event occurs by means of a deep reinforcement learning model. Recording the occurrence number of the dynamic event scheduling rules of the type, counting a scheduling rule set with the highest occurrence frequency, and recording the scheduling rule sets with the highest occurrence frequency corresponding to different dynamic events in the same manner; when a corresponding dynamic event occurs, the corresponding action space set is used for production scheduling; by recording the tardiness, images of the tardiness and the delivery period and the completion time of each iteration are recorded, and the minimum tardiness is obtained through a tardiness iteration graph. Compared with a traditional heuristic-based scheduling strategy, the scheduling capability of the dynamic flexible job space is effectively improved, the tardiness is reduced, the operation complexity is effectively reduced, and the operation speed is improved.
Owner:ZHEJIANG UNIV OF TECH

Flood season anchorage ground-wharf channel ship scheduling optimization method and system based on multi-population genetic algorithm

The invention provides a flood season anchoring ground-wharf channel ship scheduling optimization method based on a multi-population genetic algorithm, and belongs to the field of ship scheduling, and the method comprises the steps: building a flood season anchoring ground-wharf channel ship scheduling model with the purpose of minimizing the waiting time of a ship at an anchoring ground and the departure delay time of the ship at a transfer wharf, and optimizing the ship scheduling model; establishing constraint conditions satisfied by ship scheduling of the anchorage ground-wharf channel in the flood season; respectively solving a flood season anchoring ground-wharf channel ship dispatching anchoring ground departure time decision problem, a water flow limiting channel distribution problem and a transfer wharf berth distribution problem based on the satisfied constraint conditions to obtain a flood season anchoring ground-wharf channel ship dispatching initial scheme; and based on a multi-population genetic algorithm with a hybrid coding strategy, an elitism strategy and a self-adaptive mechanism, carrying out iterative solution on a ship scheduling problem to obtain an optimized ship scheduling scheme. The ship transportation efficiency of a water-land combined transportation mode is improved, and the navigation pressure of the hydro-junction ship lock is relieved.
Owner:WUHAN UNIV OF TECH

Integrated offshore wind power jacket foundation grouting operation platform and grouting operation method

The invention discloses an integrated offshore wind power jacket foundation grouting operation platform and a grouting operation method thereof. The operation platform comprises a main body frame with a horizontally arranged platform plate, and a through hole is formed in the center of the platform plate; a grouting raw material storage area, a grouting equipment placement area, a grouting preparation area and a grouting operation area are sequentially arranged at four edge positions in the circumferential direction of the platform plate; two cement-based grouting material storage boxes are fixed in the grouting raw material storage area; a grouting tool container, a generator set container and a diving tool container are fixed in the grouting equipment placement area; two grouting stirring tanks, two fresh water storage tanks and two grouting conveying pumps are fixed in the grouting preparation area, and a crane and a high-pressure flushing machine are arranged in the grouting operation area; according to the operation platform and the grouting operation method thereof, grouting operation can be started after the operation platform is pre-assembled at a wharf and is directly transported and installed at the top of the jacket, the construction difficulty is reduced, the cost is saved, and the construction efficiency and the operation safety are improved.
Owner:天津港航工程有限公司

Concrete mixer truck dispatching system and method for continuous concrete pouring

The invention provides a concrete mixer truck dispatching system and method for continuous concrete pouring. The concrete mixer truck dispatching system comprises a mixer truck module, a pouring point module and a control module. The mixer truck module comprises a forward and reverse rotation module, a Beidou positioning module, a terminal display module and a first network communication module, and the mixer truck module is arranged on a mixer truck; each pouring point module comprises an RFID module, an acousto-optic prompt module and a second network communication module, and the pouring point modules are arranged at all pouring point positions; the control module comprises a cloud server and a control terminal module; the mixer truck module and the pouring point module are connected with the cloud server through the network communication module. Through a mixer truck scheduling algorithm deployed at the control terminal module and related hardware installed at the mixer trucks and the pouring points, statistics of data such as task scheduling of the concrete mixer trucks, the distribution condition of the concrete mixer trucks and the pouring strength of the pouring points can be realized, and the concrete pouring efficiency is effectively improved.
Owner:THE FIRST CONSTRUCTION COMPANY OF CCCC SECOND HARBOR ENGINEERING CO LTD +1

Casting heat treatment production scheduling method based on grey wolf optimization algorithm

The invention provides an improved grey wolf optimization algorithm for casting heat treatment production scheduling. According to the method, the swarm intelligence and natural heuristic characteristics of the grey wolf optimization algorithm are combined, and the global search capability and the local development capability of the algorithm are enhanced by improving a population initialization strategy, a weight strategy and a nonlinear convergence factor. By optimizing the diversity and weight parameters of the initial population, the algorithm can more effectively solve the complex workshop scheduling problem. The scheduling rule of the production task is analyzed by adopting an optimization algorithm method, and resources and time are reasonably allocated, so that the production efficiency and the product quality are improved. The method is of great significance in improving the flexibility and robustness of casting heat treatment workshop scheduling, and a new path is provided for achieving intelligent production and energy conservation and emission reduction.
Owner:HENAN UNIV OF SCI & TECH

Data security acquisition scheduling system based on big data

The embodiment of the invention provides a data security acquisition scheduling system based on big data, and the method comprises the steps: an encryption strategy determination step: customizing an encryption rule through the data type and sensitivity analysis of a big data source; a data acquisition step: encrypting information extracted from a data source by using the determined encryption strategy; based on application steps of a task scheduling algorithm with dual requirements of security and efficiency, the algorithm optimizes resource utilization and distributes encrypted data sets among multiple nodes to ensure a rapid and safe data processing process. Through the scheme of the embodiment of the invention, the problem of how to safely and efficiently perform data acquisition and scheduling in a big data environment can be solved.
Owner:HENAN NORMAL UNIV

Iterative adaptive large neighborhood search method for large-scale communication satellite measurement and control scheduling problem

The invention provides an iterative adaptive large neighborhood search method for a large-scale communication satellite measurement and control scheduling problem, which is used for quickly solving the communication satellite measurement and control scheduling problem, and different from the traditional measurement and control problem, the communication satellite measurement and control scheduling problem considers an inter-satellite link to promote the quick completion of a measurement and control task. In the method, a heuristic initial solution is improved by an adaptive large neighborhood search algorithm, and then a frequent pattern mining method is embedded into an iteration mechanism to guide a search process of the algorithm: on one hand, a poorer structure is mined from a low-quality solution to guide a removal process of the adaptive large neighborhood search algorithm; on the other hand, a dominant structure is excavated from a high-quality solution to guide the construction of a new solution; experimental test results of different task scales show that the iterative adaptive large neighborhood search algorithm can effectively process the communication satellite measurement and control scheduling problem, and the performance of the algorithm is superior to that of the three most advanced algorithms.
Owner:NAT UNIV OF DEFENSE TECH

Interrupt processing circuit in on-chip subsystem, interrupt processing method and chip

PendingCN119066000AReduce processing dependenciesSolve scheduling problemsArchitecture with single central processing unitEnergy efficient computingEmbedded systemComputer engineering
The embodiment of the invention discloses an interrupt processing circuit in an on-chip subsystem, an interrupt processing method and a chip. The circuit comprises an interrupt receiver, an interrupt analyzer, an interrupt pre-configuration register and an interrupt transmitter, the interrupt receiver receives the interrupt information; the interrupt analyzer is connected with the interrupt receiver and is used for acquiring and analyzing the interrupt information; reading an interrupt type list in an interrupt pre-configuration register, and determining a target interrupt type corresponding to the interrupt information; reading an interrupt address list in an interrupt pre-configuration register, and determining a corresponding target interrupt address according to the target interrupt type; and the interrupt transmitter is connected with the interrupt analyzer and is used for acquiring each target interrupt address and the interrupt information, generating an interrupt packaging file and transmitting the interrupt packaging file to each target interrupt address of the interrupt information specified processor so as to process the interrupt. The interrupt is classified and processed as required through hardware, so that the software processing dependency on an upper-layer processor is reduced on the basis of improving the interrupt processing flexibility and universality.
Owner:SUIYUAN INTELLIGENT TECH (CHENGDU) CO LTD

Shared vehicle scheduling method and server

PendingCN119539415ASolve scheduling problemseasy to operateCommerceApplication procedureEngineering
The invention discloses a shared vehicle scheduling method and a server. The scheduling method comprises the following steps: receiving a pre-scheduling request sent by a mobile terminal; enabling an application program of the mobile terminal to display the scheduling task group; receiving a scheduling starting request of the mobile terminal; if the target vehicle is located in the vehicle pulling point, the target vehicle is included in a scheduling task group; if the target vehicle is not located in the vehicle pulling point, sending prompt information that the target vehicle is not located in the vehicle pulling point; receiving a scheduling ending request for the target vehicle; the position of the target vehicle is judged, and if the target vehicle is located in the vehicle delivery point, the scheduling request is completed; and if not, sending prompt information that the target vehicle is not in the vehicle delivery point. After the operation and maintenance personnel open the application program of the mobile terminal, the system automatically creates the scheduling task group and displays the scheduling task group in the electronic map, the operation and maintenance personnel can schedule the shared vehicles according to the vehicle pulling points indicated by the electronic map, the scheduling method is simple and clear, operation is convenient, and the operation and maintenance personnel can be rapidly and effectively guided to schedule the shared vehicles.
Owner:NINGBO XIAOLIU SHARING INFORMATION TECH CO LTD +1

Optimization method for solving flexible job-shop scheduling with resource constraints

The present application relates to the technical field of flexible job shop scheduling in intelligent manufacturing and production scheduling, and particularly relates to an optimization method for solving flexible job shop scheduling with adjusted resource constraints. The method comprises the following steps: initializing parameters and randomly generating an initial population; using a crossover operator and a mutation operator in sequence to evolve the current population; executing a hybrid decoding strategy on the current population; sorting the individuals in the current population in ascending order of maximum completion time to form an elite population, and updating the elite population through problem-specific local search; judging whether the evolution condition is met, and if yes, executing mathematical evolution based on CP, and outputting a final solution when the running time reaches the total running time. The present application has the positive effects of reducing resource waiting time, improving machine utilization, and improving the resource utilization efficiency and scheduling performance of the entire workshop production.
Owner:LIAOCHENG UNIV

A method and system for collaborative optimization of task scheduling and data caching

PendingCN122093399Aeasy to handleDynamically optimize task execution paths
This invention discloses a method and system for collaborative optimization of task scheduling and data caching, belonging to the fields of edge computing and mobile network technology. The method includes: constructing an edge computing environment through multiple edge servers, cloud servers, and a data cache; performing service chain-aware matching on arriving tasks within the edge computing environment to reuse computation results; scheduling tasks using a particle swarm optimization algorithm; obtaining a task scheduling scheme based on a comprehensive fitness function and task scheduling; executing the task scheduling scheme to obtain intermediate result data items; evaluating the value of the intermediate result data items using a multi-dimensional evaluation model to obtain a value evaluation result; updating the content of the data cache based on a genetic algorithm and the value evaluation result; and achieving collaborative optimization between repeated task scheduling and data caching. This invention achieves effective processing of tasks combining multiple services through a service chain-aware matching mechanism and establishes a bidirectional feedback collaborative optimization mechanism for task scheduling and data caching.
Owner:XIAN UNIV OF POSTS & TELECOMM

Mass stratum data scheduling and visualization method, device, equipment and medium

The invention relates to the technical field of computer visualization, and discloses a mass stratum data scheduling and visualization method, device, equipment and medium, and the method comprises the steps: initializing an LOD model according to user interaction parameters to obtain attribute display parameters, and determining a data display range according to the attribute display parameters; scheduling data block index numbers in a data display range by using a multi-resolution data scheduling algorithm; judging whether a target data block corresponding to the data block index number exists in a buffer area or not; when the target data block exists in the buffer area, displaying the target data block through a display thread; when the target data block does not exist in the buffer area, sending the target data block into the buffer area through the data read-in thread, and returning to the step of displaying the target data block through the preset display thread; and performing data assembly drawing on the displayed target data block to obtain visual stratum data. According to the invention, the efficiency of mass stratum data scheduling and visualization can be improved.
Owner:CHINA PETROLEUM & CHEMICAL CORP +1

A method for dividing a star cluster and a method for handing over a slave star in coordination with multiple star clusters

The present invention discloses a method for dividing star clusters and a method for handing over slave satellites in collaboration with multiple star clusters, and relates to the field of space-based detection technology. The specific implementation of the method includes: for each slave star of any star cluster, calculating the first distance from the slave star to the central control center of each star cluster; comparing multiple first distances to determine the minimum value of the first distance; determining the star cluster to which the central control center corresponding to the minimum value of the first distance belongs as the target star cluster of the slave star. This implementation can compare the distances of each satellite in the star cluster relative to the center of each star cluster, determine the optimal star cluster to which the satellite belongs, thereby improving the satellite utilization rate during the execution of observation tasks, and rationally utilizing on-board resources, and the slave satellites between star clusters can be flexibly switched based on the distance relative to the center of each star cluster, so as to observe the observation target, so that the observation effect of the entire star cluster is optimal, and is suitable for various mission scenarios.
Owner:CHINA ACADEMY OF SPACE TECHNOLOGY +1

Hybrid transmission rate optimization method of electric power multimedia exchange network and related device

PendingCN119254722AReduce transmission delaySolve scheduling problemsTransmissionExchange networkEngineering
The invention belongs to the field of communication transmission, and discloses a power multimedia exchange network hybrid transmission rate optimization method and a related device, and the method comprises the steps: obtaining a to-be-transmitted data volume; solving a preset mixed transmission rate optimization model according to the to-be-transmitted data volume to obtain scheduling information of each transmission time slot of a circuit packet switching (EPS) switch and an optical circuit switching (OCS) switch of the electric power multimedia switching network; dispatching an EPS switch and an OCS switch of the power multimedia exchange network according to the dispatching information of each transmission time slot of the EPS switch and the OCS switch of the power multimedia exchange network; wherein the hybrid transmission rate optimization model is constructed in combination with a series of constraint conditions by taking maximization of the average transmission rate of all transmission time slots of the hybrid switching network as an optimization target. By using the EPS switch and the OCS switch in the hybrid switching network to the maximum extent, the problem of composite path scheduling in the hybrid switching network can be effectively solved, and the data transmission efficiency of the electric power multimedia switching network is effectively improved.
Owner:CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +4

Equipment access system and method based on dynamic registration

The invention relates to the technical field of Internet of Things, in particular to a device access system and method based on dynamic registration, the system comprises a dynamic registration service system and an Internet of Things platform system, the dynamic registration service system is used for obtaining a dynamic registration request sent by a device to be accessed and authenticating the dynamic registration request, the Internet of Things intermediate station system matches a target Internet of Things intermediate station according to the device type and the protocol type of the device to be accessed, and sends scheduling information to the dynamic registration service system; business of a traditional system is separated, the dynamic registration service system is only responsible for registration and authentication of the equipment and does not involve the function of a business level, the traditional business part is separated to a platform system in the Internet of Things to be carried out, the overall safety of the system is greatly improved, and the security of the system is greatly improved. And unified management of devices of different types and different protocols is facilitated.
Owner:WASION GROUP HLDG

A multi-source and multi-target cryptographic resource scheduling method

The present invention belongs to the technical field of cryptographic resource scheduling, and specifically relates to a multi-source and multi-target cryptographic resource scheduling method, including initializing relevant parameters of cryptographic resource nodes and cryptographic task nodes; determining whether each cryptographic resource node is a focus node or a peripheral node, and determining the convergence domain of the focus node; for each cryptographic task node, calculating the single node protection capability, for each focus node, calculating the focus weight; updating the speed of each cryptographic resource node according to the single node protection capability and the focus weight, each cryptographic resource node updates its position according to the calculated speed, and after repeated iterations, finally obtains the optimal position and optimal overall layout of each cryptographic resource node. The present invention can ensure that when a cryptographic resource demand appears at a cryptographic task node, under the condition that the overall protection capability meets the requirements, the cryptographic resources can be deployed to the cryptographic task node in the shortest possible time, and at the same time, there will be no excessive aggregation of multiple cryptographic resource nodes.
Owner:Chinese People's Liberation Army Cyberspace Force Information Engineering University

A master satellite handover method for multi-satellite coordination

ActiveCN115941020BSolve scheduling problemsGuaranteed normal executionComputer networkEngineering
The present invention discloses a star-coordinated master star handover method, which relates to the field of space-based detection technology. The specific implementation of the method includes: the current master star in the star cluster generates a master star handover instruction; wherein the master star handover instruction indicates the handover time, the master star identifier of the current master star and the slave star identifier of the master star to be handed over; according to the master star identifier of the current master star and the slave star identifier of the master star to be handed over, the current master star sends the task arrangement information of the star cluster to the master star to be handed over; the current master star receives the first handover response result of the master star to be handed over; when the first handover response result is that the handover is allowed, at the handover time, the current master star switches to the slave star of the star cluster, and the master star to be handed over switches to the master star of the star cluster. This implementation method can flexibly switch the master star of the star cluster based on the distance of each satellite in the star cluster relative to the central control center, the observation task requirements, etc., so as to efficiently and clearly observe the target, so that the observation effect of the entire star cluster is optimized and adapted to various task scenarios.
Owner:CHINA ACADEMY OF SPACE TECHNOLOGY

Multi-target flexible workshop scheduling method based on NSGA-II and ant colony hybrid algorithm

The invention discloses a multi-target flexible workshop scheduling method based on an NSGA-II and ant colony hybrid algorithm, which aims at minimizing the maximum completion time and minimizing the total machine load and provides a solution for flexible workshop scheduling. According to the method, an NSGA-II and ant colony hybrid algorithm is used, and through application in an actual production environment, high-efficiency utilization of production resources is realized, and the flexibility and the response capability of a production line are remarkably improved.
Owner:HEFEI UNIV OF TECH

Matrix type workshop scheduling method based on genetic algorithm

InactiveCN119247908ASolve scheduling problemsRealize reasonable deploymentProgramme total factory controlMachine selectionAlgorithm
The invention discloses a matrix workshop scheduling method based on a genetic algorithm, and the method comprises the steps: S1, generating a related data case through a case generator according to the characteristics of a matrix workshop; s2, generating a chromosome through MSOSAS coding; s3, performing initialization setting on the population, and performing global selection, local selection and random selection according to a preset proportion to obtain a selected initial solution; s4, carrying out fitness calculation on the plurality of chromosomes; s5, according to the fitness and the crossover probability, selecting a preset number of populations to carry out machine crossover and process crossover; according to the fitness value and the mutation probability, selecting a preset number of populations to carry out machine mutation and process mutation, and generating an optimal chromosome; and S6, decoding the optimal chromosome, and generating the machine selection, the process sequence, the preset capability and the processing time of the workpiece during processing. According to the invention, the scheduling problem of the matrix type workshop is solved, and the production scheduling of the matrix type workshop with high flexibility and high adaptability is realized.
Owner:SOUTHWEST CHINA RES INST OF ELECTRONICS EQUIP

A method for dispatching and path planning of AGV vehicles

The present invention discloses an AGV trolley scheduling and path planning method, including a given AGV trolley layout and data constraints, a given starting position and a target position of the AGV trolley movement, a given AGV trolley path task, data training based on an algorithm combining a genetic algorithm and a neural network algorithm to obtain its parameters, analyzing the data fed back by program monitoring, and making optimization; this scheme determines the guide line and the work station position, as well as the allowed running direction of the AGV on each path segment by given constraints such as workshop layout, AGV size, AGV performance, and path handling load, so as to optimize a certain performance of the system; this scheme improves the fitness of the genetic algorithm based on a smoothness function on the basis of a traditional genetic algorithm, and solves the problem by using an algorithm formed by mixing the improved genetic algorithm with a deep learning neural network algorithm, so as to achieve accurate, fast, and efficient solutions to the AGV scheduling problem.
Owner:SHENZHEN AMITEK AUTOMOTIVE INFORMATION CO LTD

Natural gas power plant and power system cooperative scheduling method and device, medium and equipment

The invention discloses a natural gas power plant and power system cooperative scheduling method and device, a medium and equipment. According to the method, operation parameters of each natural gas power plant and power demand data of a power system are obtained in real time, a natural gas pipeline network topological graph is firstly constructed, then operation indexes of the power plants are updated through the graph, and the real-time power generation hours are calculated in combination with a preset formula. Then, according to the operation index, the reported data and the number of hours capable of generating power, calculating a declared gas amount surplus and gas consumption early warning information; and finally, the data and the real-time power demand are combined to carry out optimal scheduling on the natural gas power plant. According to the invention, the scheduling accuracy and response speed are improved, and the resource allocation is optimized, so that the problem that the natural gas power plant cannot be accurately scheduled according to the requirements of the power system in the prior art is solved.
Owner:GUANGDONG POWER GRID CO LTD +1

Control method for workpiece machining scheduling based on multi-dimensional edge weighted graph attention reinforcement learning

The present invention provides a control method for workpiece processing scheduling based on multi-dimensional edge weight graph attention reinforcement learning, the method comprising: constructing a multi-dimensional edge weight feature directed graph based on the workpiece processing target; constructing a scheduling model, inputting the multi-dimensional edge weight feature directed graph into the scheduling model, generating a pre-processing sequence set, and optimizing the scheduling model based on an offline reinforcement learning algorithm; optimizing the pre-processing sequence set using a hybrid beam search and priority scheduling rule algorithm to obtain a production processing sequence set; obtaining a workshop scheduling processing plan based on the production processing sequence set and the workpiece processing target. The present invention uses a graph attention mechanism encoder with multi-dimensional edge weight features to effectively learn the implicit features of the scheduling problem; adopts a context feature decoding method with inherited features to solve the problem characteristics of the scheduling problem; integrates a hybrid reinforcement learning algorithm with priority scheduling rules and beam search decoding to obtain an optimal scheduling plan, thereby obtaining a high-efficiency and high-quality scheduling plan.
Owner:BEIJING INST OF TECH

Optimized scheduling method and device for multi-energy complementary system

The invention provides an optimal scheduling method and device for a multi-energy complementary system. The optimal scheduling method comprises the following steps: acquiring the on-grid price of the multi-energy complementary system; and solving a pre-constructed optimal scheduling model according to the on-grid price of the multi-energy complementary system to obtain the generation power and the pumping power of the pumped storage power station in the multi-energy complementary system. And solving the preferentially constructed unit combination model according to the generation power and the pumping power of the pumped storage power station to obtain the state, the generation power and the pumping power of each pumped storage unit in the pumped storage power station. According to the method, each pumped storage unit is considered, the characteristics of the pumped storage units are fully combined, and the optimization scheduling precision is improved.
Owner:CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +6