1729 results about "Majorization minimization" patented technology

The invention discloses a BIM-based electromechanical installation project progress planning and resource scheduling method and system, and belongs to the technical field of intelligent construction. The method comprises the following steps: 1) collecting multi-dimensional parameters (real-time construction parameters, prediction model parameters and external constraint parameters) in construction in a classified manner, and constructing a dynamic knowledge graph; 2) detecting progress and resource deviation based on a preset threshold value of the BIM model, and dynamically correcting a resource demand curve through the model; 3) in combination with constraint conditions such as policies and weather, optimizing an equipment scheduling path by adopting an algorithm, and screening compliance candidate schemes; 4) performing multi-objective optimization (minimizing progress deviation, maximizing resource utilization rate and controlling supply chain risk) on the scheme by using a genetic algorithm, and verifying through simulation iteration; and 5) outputting the optimal scheme and synchronizing the optimal scheme to a visual interface. According to the invention, real-time closed loop of data is realized through hardware-algorithm cooperation, and an efficient, dynamic and extensible intelligent management scheme is provided for electromechanical engineering.

A source-grid-load-hydrogen storage multi-stage planning method and system considering flexible resources, relating to the technical field of source-grid-load-hydrogen storage system planning. The method comprises: collecting source-grid-load-hydrogen storage data for data preprocessing; constructing a flexibility supply and demand characteristic model and a source-grid-load-hydrogen storage multi-stage dynamic planning model; calling a solver to solve the source-grid-load-hydrogen storage multi-stage dynamic planning model to obtain an optimal solution; and outputting a multi-stage source-grid-load-hydrogen storage investment result, a multi-stage source-grid-load-hydrogen storage operation policy, and a multi-stage flexibility supply evaluation result within a planning period. Using the minimization of investment costs, operation costs, and insufficient flexibility penalty costs within the whole planning period as target functions, various constraints such as a new energy permeability constraint and a load loss rate constraint are introduced, a dynamic planning method is proposed, and a source-grid-load-hydrogen storage multi-stage planning solution that has sufficiently economical planning operation and is sufficiently flexible is obtained. According to a processing method based on piecewise linearization, the model is simplified, and the computation speed is increased.

The invention relates to the technical field of energy scheduling, and discloses a smart city energy dynamic scheduling system and method based on big data analysis, and the method comprises the following steps: the operation state of a transformer substation, the basic parameters of a charging pile and regional load prediction data are collected in real time, data cleaning and abnormal value filtering are carried out; constructing a complete power grid-charging facility dynamic information base; calculating the power supply margin of each region based on the capacity loss of the faulty transformer substation, establishing a weight scoring system of charging pile power adjustment in combination with the charging demand urgency, and determining the reduction or recovery priority of each charging load; and generating a charging pile power adjustment instruction through a multi-target optimization model, and iteratively correcting a power distribution scheme and generating a final scheduling instruction set by taking minimization of user satisfaction loss as a target while meeting the power grid capacity. According to the invention, by constructing a dynamic response mechanism and a multi-target collaborative optimization model, accurate and rapid regulation and control of the traffic load are realized in the scene of sudden power shortage of the power grid.

The invention relates to the technical field of software defined networks, in particular to an SRv6-based SDN (Software Defined Network) data center load balancing method and system, and the method comprises the steps: obtaining node real-time load and SRv6 routing available resource information through an SDN controller, constructing a load balancing model, and recognizing an overload node and a congestion link; generating a flow scheduling path in combination with segmented routing characteristics; in combination with network state information, monitoring the load condition in real time when the node is unbalanced or the link packet loss rate is gt; when 5%, a load balancing adjustment mechanism is triggered, unbalance types are distinguished, a related flow set is determined, optimization is performed by using a DQN algorithm, and a flow scheduling strategy is generated and dynamically adjusted by taking throughput maximization and unbalance degree minimization as targets; and issuing the scheduling strategy to the data center network equipment, updating the flow table through the Netconf protocol, and redistributing the flow. Therefore, the problems of low load balancing efficiency, insufficient dynamic adaptability, low resource utilization rate and the like in the prior art are solved.

The invention relates to the technical field of cloud computing and distributed storage, and discloses a distributed metadata management method and storage system based on cloud computing, and the method comprises the following steps: S1, collecting the access frequency of a plurality of metadata objects in a set time period; s2, performing weighting processing on the access frequency, and constructing access heat distribution under multiple time scales; s3, obtaining the available cache capacity of a plurality of cache nodes, and constructing cache resource weight distribution; s4, assessing the access cost and migration cost between each metadata object and each cache node; and S5, generating a scheduling strategy between the metadata object and the cache node based on a preset optimization target, wherein the optimization target is access cost minimization. According to the method, a heat, resource and cost joint modeling mechanism is constructed, and optimal scheduling and feedback adaptive control are combined, so that accurate decision, dynamic adjustment and migration cost controllability of copy deployment are realized, and the performance and stability of distributed metadata management are effectively improved.

The invention relates to a multi-vehicle intelligent driving cooperative training method based on a block chain in the Internet of Vehicles, and belongs to the technical field of mobile communication. Aiming at the problems of data privacy leakage, too high synchronous federated learning time delay, inaccurate node contribution degree evaluation, insufficient single-chain block chain expandability and the like existing in intelligent driving cooperative training in the Internet of Vehicles, an asynchronous federated learning framework with fusion of a cloud-edge-end three-layer architecture and a double-layer block chain is constructed. A local training strategy is optimized through multi-agent reinforcement learning to minimize the total time delay of a system, a dynamic reputation evaluation mechanism based on training interaction timeliness, confirmed site occupancy and model quality contribution is designed to screen high-reputation nodes, and asynchronous model verification and PBFT main chain global aggregation are realized by adopting a DAG block chain. According to the method, on the premise of guaranteeing data privacy, the model sharing efficiency is improved by more than 30%, the training time delay is reduced by 40%, the convergence stability of a global model is effectively enhanced, and the expansibility bottleneck of a traditional architecture is solved.

The invention discloses a virtual power plant global optimization scheduling method, system and device based on cloud edge collaboration, and a storage medium, and belongs to the technical field of power system scheduling. The method comprises the following steps: based on a cloud edge coordinated regulation and control framework comprising a cloud layer, an edge layer and an end side layer, taking minimization of the total operation cost of a system as a target, comprehensively considering a power balance constraint, a main network interaction constraint, a distribution network transmission constraint, a distributed resource operation constraint, an energy storage equipment constraint and a renewable energy consumption constraint; establishing a global optimization scheduling model; edge collaborative optimization is realized by adopting an alternating direction multiplier method, a global coupling problem is decomposed into local optimization sub-problems and a cloud coordination problem of each region, and aggregation power information is sent to the cloud after the local optimization sub-problems are solved in parallel in each region; and the cloud performs global coordination optimization to generate an optimal scheduling strategy, and issues a scheduling instruction to the edge layer to control the actual operation of the distributed power supply, the energy storage equipment and the controllable load, thereby realizing the collaborative optimization scheduling of the virtual power plant. The problems that in virtual power plant large-scale distributed resource coordination optimization, calculation complexity is high, communication burden is heavy, and real-time performance and global optimality are difficult to consider at the same time are effectively solved.

The invention relates to the field of power systems and automation thereof. The invention relates to a power distribution network energy storage optimization configuration method considering dynamic uncertainty and multi-target cooperation. The method is characterized by comprising the following steps: 1) constructing a two-stage robust optimization model: constructing the two-stage robust optimization model with a min-max-min structure; in the first stage, the energy storage construction position and capacity are determined with the lowest annual investment cost of energy storage as the target; in the second stage, the system scheduling cost is minimized in the worst new energy output scene; 2) convex relaxation processing of network constraint; 3) implementation of an iterative solution algorithm: based on a KKT principle and a column constraint generation algorithm, decomposing an original problem into a mixed integer linear main problem and a sub-problem; the main problem optimizes an energy storage configuration scheme, and the sub-problems solve a scheduling strategy in the worst wind and light output scene and feed back to the main problem through cut plane constraint; and carrying out iterative calculation until the solutions of the main problem and the sub-problem converge, and obtaining an optimal energy storage configuration scheme. According to the method, more accurate and efficient energy storage planning can be realized.

The invention discloses an intelligent operation and maintenance distributed cloud native application computing method, and relates to the technical field of cloud computing, and the method comprises the steps: collecting heterogeneous data of an application layer, a middleware layer, a container layer and a service governance layer, constructing a dynamic multilayer dependency graph, and explicitly modeling a cross-layer dependency relationship and implicit dependency caused by resource competition; based on the spatio-temporal features of the spatio-temporal diagram neural network learning map, predicting a cascade fault risk and outputting a high-risk sub-graph; candidate operation and maintenance operations are generated through reinforcement learning, indirect negative influences of the operations on non-target components are evaluated in combination with a causal inference model, and risk filtering operations are verified through a multi-dimensional safety threshold value; and after the safety operation is executed, continuously optimizing the model and the atlas through a feedback closed loop. According to the method, deep insight, accurate risk prediction and self-adaptive decision making of side effect minimization can be carried out on a complex dependency relationship, and the system stability and the operation and maintenance efficiency are remarkably improved.

The invention relates to the technical field of power system source-grid-load-storage collaborative planning, and discloses a source-grid-load-storage collaborative planning method, system and device and a medium, and the method comprises the steps: obtaining the structure, operation and economic parameters of a power system; dividing extreme scenes and establishing a frequency response model; setting a frequency security constraint based on the extreme scene; a three-layer optimization planning model is constructed, the three-layer optimization planning model comprises an objective function and constraint conditions, and the third layer comprises frequency security constraints; the model is solved to determine a planning scheme. According to the method, the minimization change point detection technology is utilized, artificial truncation of the wind-light load output features in sample selection is avoided, and the extreme scene is accurately extracted. The constructed frequency response model comprises nine frequency modulation resources and comprehensively reflects the frequency modulation capability of the novel power system. According to the provided three-layer iterative planning method, the construction investment is properly increased, so that the frequency safety of a power supply, a power transmission line, energy storage and a demand side response scheme in an extreme scene is ensured, and the frequency instability risk and the economic loss are avoided.

The invention discloses an active power distribution network optimal scheduling method and system considering a multi-agent cooperative game, and relates to the technical field of power distribution network optimal scheduling, and the method comprises the steps: considering the interaction among multiple market agents in an active power distribution network, and constructing a multi-agent cooperative transaction architecture; based on a multi-subject collaborative transaction architecture, taking cost minimization as a target, and combining constraint conditions to build an operation and income model of each subject; wherein a distributed energy storage operator is used as one of main bodies, and the operation of distributed energy storage is restrained by using a distributed energy storage distribution strategy based on distributed energy storage SOC balance; according to the Nash bargaining theory, a multi-subject operation and income model is integrated, and a multi-subject cooperative game model is constructed; and solving the multi-agent cooperative game model based on the actual energy demand quantity of the user side to obtain an optimal scheduling strategy of the energy in the active power distribution network, and performing energy scheduling according to the scheduling strategy. The charging and discharging power balance between the DES units can be realized, and the economic benefit is improved.

The invention relates to a ship port resource coordinated scheduling method and device, and belongs to the technical field of port resource optimized scheduling, and the method comprises the steps: building a target function with the maximization of the anchor ground utilization rate, the maximization of the berth utilization rate and the minimization of the ship waiting time as targets; solving the objective function by using MILP and a particle swarm algorithm to obtain an initial scheduling scheme meeting constraint conditions; the initial scheduling scheme comprises anchor ground distribution, berth distribution, berthing time and leaving time; clustering the initial scheduling scheme based on the multi-core weighted distance of the initial scheduling scheme to obtain a clustered scheduling scheme; and optimizing the clustered scheduling scheme based on a game theory model to obtain a target scheduling scheme. According to the ship and port resource coordinated scheduling method provided by the invention, global optimization of ship berth allocation, channel use and anchor ground scheduling is realized, and high efficiency and safety of ship operation are ensured while channel resource conflicts are reduced.

The invention discloses a production scheduling method, a production scheduling system and electronic equipment, and belongs to the technical field of production management and scheduling. The production scheduling method comprises the steps that according to production requirements and a preset production correlation model, a fitness function and an initial production scheduling scheme set are determined, and the fitness function comprises at least two of the following production scheduling strategies: total delay time minimization, resource utilization rate maximization, production line load balancing and intermediate product minimization; at least two preset algorithms are fused, the initial production scheduling scheme set is optimized based on the fitness function, the optimal production scheduling scheme is obtained, and the preset algorithms comprise any one of a genetic algorithm, a simulated annealing algorithm and a tabu search algorithm. The method can solve the problems of insufficient processing of resource constraints, low production scheduling efficiency and incapability of effectively finding the optimal production scheduling scheme in related technologies.

The invention belongs to the technical field of logistics information, and discloses a multimodal transport trusted data space construction method based on privacy calculation and a block chain. The method comprises the following steps: deploying a modular intelligent data gateway at a core node of a multimodal transport line, unifying the format of multi-source heterogeneous original data, and chaining a hash value; after the multi-source heterogeneous data is subjected to customization processing, key metadata attributes of all the data are registered and linked in real time; constructing a core ontology model, and establishing a cross-domain semantic interoperation capability; establishing a privacy calculation and block chain collaborative dual-channel architecture, and cooperatively training an ETA prediction model in a local data isolation environment by adopting transverse federal learning to ensure that original trajectory data is not out of a domain; constructing a dispute arbitration and credible verification system, and realizing an arbitration process of judicial verification when a transportation dispute occurs; data minimization disclosure and compliance sharing are achieved through dynamic access control. According to the method, multimodal transport data can be available and invisible, and the whole operation process can be audited.

The invention discloses a distributed energy system source load coordinated optimization method based on a quasi-potential game method, and the method comprises the steps: constructing a distributed energy system model, inputting system parameters, and predicting renewable energy power generation and initial load demands. In a source side optimization stage, a leader layer potential function of a quasi-potential game is established by taking minimization of source side cost # imgabs0 # as a target, and an initial power generation plan is generated by comprehensively considering economical efficiency and carbon emission constraints; and then, based on a scheduling result, calculating a carbon potential epsilon t of each node and a dynamic carbon emission factor # imgabs1 # of each stage, optimizing a load side response based on an LCDR scheme, constructing a local potential function of a follower layer, reflecting a relationship between a user profit maximization target and carbon emission, and adjusting user behaviors through a distributed decision. And the updated load demand is fed back to the source side, and the source side optimizes the output plan of each unit based on the updated load, so that an iterative process of source side potential function optimization-load side equilibrium response is formed, and an optimal scheduling strategy and scheduling result of the energy supply side are obtained. According to the framework, the global consistency requirement of a traditional potential game is relaxed, independent optimization of source-load two sides under the guidance of respective potential functions is allowed, and a Nash equilibrium state is finally achieved only by ensuring monotonous convergence of total potential energy of a system in an iteration process. According to the method, the convergence advantage of the potential game is reserved, the method is also adapted to the characteristics of a source-load heterogeneous decision subject, efficient consumption of renewable energy and collaborative optimization of carbon emission are realized through bidirectional transmission of the carbon potential signal, and the overall efficiency of the system is remarkably improved.

The invention discloses a flexible job shop scheduling method based on deep reinforcement learning, and belongs to the field of intelligent manufacturing and intelligent scheduling, and the method comprises the steps: firstly, taking the minimization of the maximum job completion time and the maximization of the average machine utilization rate as optimization targets, and obtaining a target model; then representing a flexible job shop scheduling problem by using a disjunction graph model to obtain a scheduling state; according to the scheduling state and the target model, an end-to-end learning framework is constructed, and the framework is combined with a multi-attention network for deep feature extraction and a decision network for extensible decision, and a Markov decision process is utilized to obtain a job scheduling model; and finally, the multiple attention network constructs a production adaptability operation-AGV-machine scheme by using the complex relationship among the operation, the AGV and the machine to support the decision of the decision network, and obtains a scheduling schedule by using the job scheduling model to complete flexible job shop scheduling. According to the method, complex modes and relations in data can be better captured, and the performance and generalization ability of the model are improved.

The invention discloses an electric vehicle V2G micro-grid energy storage capacity optimization method based on dynamic planning, particularly relates to the technical field of micro-grid energy storage optimization, and aims to solve the problem of energy storage capacity optimization defects caused by spatial dynamic characteristics caused by mobility of an existing electric vehicle. Performing geographic grid division on the node position, generating a space-time matrix by combining with a timestamp, and identifying a high-frequency access node; constructing a state transition equation based on the inter-node impedance matrix, and setting a node-level safety boundary by taking a line capacity change rate as a dynamic constraint; a staged reverse dynamic programming algorithm is adopted, spatial dimension optimization is preferentially executed on the high-frequency access nodes, and charging and discharging constraints fusing voltage deviation and capacity overrun penalty terms are generated; carrying out global optimization by taking the minimization of the total operation cost as a target after the constraints are integrated, and outputting an energy storage capacity configuration strategy of each time period; and finally generating an energy storage deployment scheme.

The present application discloses an optimization method and apparatus for a transportation strategy under a feeder logistics network, an electronic device and a storage medium. The method comprises: acquiring logistics information under a feeder logistics network, wherein the logistics information comprises information of each logistics node; inputting the logistics information into a digital twin model, by means of the digital twin model and by taking transportation rules of the feeder logistics network as a constraint condition and transportation cost minimization as an objective, performing route planning to generate a transportation strategy to be optimized, and simulating a transportation process of goods between the logistics nodes on the basis of the transportation strategy to be optimized, so as to obtain a simulation result; and on the basis of the simulation result, optimizing the transportation strategy to be optimized, so as to obtain an optimized transportation strategy. In the present application, on the basis of the computing power of the electronic device, the transportation strategy during logistics transportation can be quickly obtained; and by simulating the logistics transportation process, the reliability of the transportation strategy can be improved.

The invention relates to the technical field of digital intelligent supervision, in particular to a supervision method based on industrial chain digital collaboration, which comprises the steps of realizing efficient and credible collection and fusion of industrial chain heterogeneous data through a block chain and federated learning technology, ensuring data privacy and constructing a unified data basis; the graph neural network is used for dynamically learning an industry chain entity relationship, a key path and a vulnerability node are accurately identified, a hidden risk structure is revealed, and the risk positioning capability is improved; by fusing policies, behaviors and topological data, the risk entropy value is calculated in real time, early warning is generated, multi-dimensional risk quantification and dynamic monitoring are achieved, and the early warning accuracy is enhanced; a supervision instruction matched with the risk is automatically triggered based on the intelligent contract, so that timeliness and accuracy of supervision measures are ensured, and human intervention errors are reduced; map and risk model parameters are dynamically adjusted through a reinforcement learning mechanism, and continuous optimization of a supervision strategy and minimization of service interference are realized.

The invention discloses a resource collaborative awareness-based Storm flow calculation dynamic scheduling method, and provides the following technical scheme aiming at the problem that the performance of a Storm default scheduling algorithm is reduced in node abnormity, resource fluctuation and rescheduling scenes: firstly, dynamically sensing node busy, downtime and data flow fluctuation events through a real-time monitoring module; triggering a rescheduling process; secondly, constructing a resource collaborative optimization model based on historical task instance resource requirements, node performance indexes and communication overhead, and generating a task instance allocation scheme by taking minimization of inter-node communication cost as a target and combining CPU / memory dynamic threshold constraints; further, a greedy algorithm is adopted to sort high-relevance task instances, the high-relevance task instances are preferentially distributed to nodes with the optimal historical performance, and it is ensured that the node resource utilization rate does not exceed a dynamic threshold value; meanwhile, node load balancing parameters are corrected in real time through time window smoothing processing, and the remaining resource state is updated; and finally, outputting an optimized topology division result, so that the system delay after rescheduling is remarkably reduced, and the throughput is improved. According to the method, rapid recovery and stable operation of the heterogeneous cluster are realized through resource collaborative modeling, historical data driven dynamic scheduling and load balancing optimization.

The invention relates to the technical field of data center high availability, in particular to a cross-data center fault isolation and switching method and system in a multi-tenant environment. The resource mapping table is constructed by taking the tenants as the minimum control units, the affected tenants are accurately identified, logic isolation is executed, the problem of waste of full-tenant service migration resources caused by node-level or cluster-level switching in the prior art is avoided, and the fault influence range is minimized. The optimal data center is dynamically selected by combining the multi-factor objective function with the tenant SLA level, the defects that an existing scheduling strategy is opaque and tenant priorities cannot be distinguished can be overcome, and it is ensured that key tenant services are preferentially recovered. And finally, through combination of a gray takeover mechanism and health feedback confirmation and multi-dimensional recovery verification after migration, the condition that an existing recovery mechanism is extensive can be changed, the fault processing precision and the resource scheduling efficiency of the data center in a multi-tenant environment are remarkably enhanced, and the service continuity is guaranteed.

The invention is suitable for the technical field of mobile edge computing, and provides a hybrid energy WPT-MEC system-based task unloading and resource allocation method, which comprises the following steps of: establishing a system model; an optimization problem with the goal of minimizing the long-term average power grid energy consumption is drawn up and converted into a Markov decision process; implementing an action space reduction strategy, and executing data normalization processing; constructing an enhanced depth deterministic policy gradient (EDDPG) algorithm; and generating and outputting an optimal strategy according to a real-time system state by using the trained network. According to the method, the wireless power transmission (WPT) technology, the green energy harvesting technology and the mobile edge computing technology are combined, so that the energy use duration and the computing capacity of the wireless equipment are improved. The online decision-making mechanism based on the EDDPG algorithm can dynamically optimize task unloading and resource allocation strategies, adapts to a dynamic environment, reduces energy cost and environmental pollution, and provides reliable technical support for large-scale deployment of the Internet of Things.

The invention belongs to the technical field of vehicle-mounted edge computing (VEC), and particularly relates to an unloading and resource allocation method for a DAG task in a vehicle-mounted edge computing environment. The method comprises the following steps: firstly, constructing a VEC unloading system in a two-way lane scene, and collecting task and equipment information and establishing an optimization model in combination with a vehicle moving model, a communication model and a calculation model; and secondly, aiming at a task in a directed acyclic graph (DAG), a task priority scheduling method based on a DAG topological structure is designed, so that a task scheduling strategy is optimized. On the basis, the problem is modeled as a Markov decision process by taking minimization of task completion time delay and system energy consumption as optimization objectives. The invention relates to the field of resource allocation, in particular to a task-dependent computing unloading and resource allocation algorithm based on a depth deterministic policy gradient (DDPG), and further provides a task-dependent computing unloading and resource allocation algorithm based on the depth deterministic policy gradient (DDPG) so as to solve the optimization problem.

The invention discloses a service migration method and device, a readable storage medium and a computer program product, and the method comprises the steps: obtaining multi-dimensional resource data of an initial node and a destination node, the initial node being a node where a to-be-migrated service is located, and the destination node being a node where the to-be-migrated service is migrated; the resource types of the multi-dimensional resource data comprise computing resources, storage resources and network resources; on the basis of multi-dimensional resource data and a prediction model, predicting a resource demand of the to-be-migrated service in a process of migrating from the initial node to the destination node; based on a target function and the resource demand, a resource allocation scheme in the migration process of the to-be-migrated service is formulated, and the target function takes minimization of a combination of time delay, cost and energy consumption generated in the migration process as an optimization target; and migrating the service to be migrated according to the resource allocation scheme.

The invention discloses a method for deploying an edge dynamic DAG (Directed Acyclic Graph) server-free function on line to realize quick starting, and belongs to the field of edge computing. The method comprises the steps of 1, defining a dynamic DAG and establishing a modeling criterion of function preheating processing, and 2, constructing a dynamic DAG model with preheating preparation and function scheduling, and the model achieves the minimization of the overall expected execution time through preheating and function deployment. And step 3, converting a quadratic programming problem into a convex optimization problem by processing a quadratic constraint condition. And for the converted problem, a search algorithm based on random rounding is adopted to solve an optimal solution. And step 4, designing an online preheating and function scheduling algorithm. The algorithm includes function weight calculation, warm container adjustment, and optimal container selection to handle multiple online arrival requests. According to the method, through an online preheating and dynamic scheduling strategy, the cold start problem is effectively relieved, and the execution efficiency of the server-free function in the edge computing environment is improved.

The embodiment of the invention discloses a power grid configuration operation cooperation method and device, electronic equipment and a storage medium. The method comprises the steps that an upper layer planning model with the purpose of minimizing the comprehensive planning cost of a power grid and with the installed capacity of a new energy unit and the installed capacity of an energy storage unit as optimization variables is constructed; a lower-layer operation simulation model with the aim of minimizing the comprehensive operation cost of the power grid and with the operation state of the thermal power generating unit, the operation state of the energy storage unit, the new energy abandoned power and the load shedding power as optimization variables is constructed; constructing a double-layer decision model based on the upper-layer planning model and the lower-layer operation simulation model, and enabling the output of the upper-layer planning model and the output of the lower-layer operation simulation model to be mutually influenced; and performing multi-round iterative optimization on the double-layer decision model based on a multi-time-sequence typical source load matching scene. The embodiment of the invention can improve the power supply reliability of the power grid on the premise of ensuring the safety of the power grid and the lowest comprehensive cost.

The invention provides a virtual power plant group resource scene adaptive scheduling method and system, and a storage medium, and the method comprises the steps: building a typical external feature model of a virtual power plant based on the resource characteristics and core parameters of different types of distributed resources; generating a feasible region of the single equipment based on power constraint, electric quantity constraint and climbing constraint of the single equipment in the virtual power plant, and aggregating the feasible region of the single equipment to form an aggregated feasible region of the virtual power plant; based on a typical external feature model of the virtual power plant and different service scene requirements, dynamically adjusting response capability index weights in different service scenes, and based on an aggregation feasible region of the virtual power plant, constructing a virtual power plant dynamic aggregation model adapted to multiple scenes; and solving the dynamic aggregation model of the virtual power plant by taking minimization of the power generation cost of the virtual power plant as a target to obtain an optimal scheduling scheme of the virtual power plant.

The invention discloses an air federated learning realization method for collaborative optimization of client scheduling and model compression. The invention realizes the air federated learning realization method for collaborative optimization of client scheduling and model compression. Along with rapid development of federated learning in a wireless network, air computing based on a multiple-input-multiple-output technology is widely concerned due to high communication efficiency of the air computing. However, in a resource-limited large-scale device scene, channel interference, device heterogeneity and limited spectrum resources significantly restrict the convergence rate and model performance of federated learning. In order to deal with the challenges, the invention provides an air federated learning framework combining compressed sensing and client scheduling, and by collaborative design of model parameter compression, multi-antenna beam forming and dynamic equipment selection strategies, the total communication overhead of each round of training is minimized, and meanwhile, the convergence of a global model is guaranteed. In order to balance training cost and model quality, a joint optimization problem based on calculation-communication cost and model precision loss is provided. In order to solve the non-convex optimization problem, an original problem is decoupled into two sub-problems. Firstly, an optimization problem of a pre-coding and post-processing matrix is designed for a given user scheduling result to minimize a gradient aggregation error. Then, a novel user scheduling algorithm based on channels and data is provided to obtain an air aggregation result.

The embodiment of the invention provides a localized large-scale language model service method and related equipment. The localized large-scale language model service method comprises the following steps: acquiring a request load index of an inference service in real time; according to the request load index, a five-dimensional parallelism strategy is determined in a calculation iteration period, and the five-dimensional parallelism strategy comprises parallelism degrees of five dimensions including data parallelism degree, tensor parallelism degree, pipeline parallelism degree, sequence parallelism degree and expert parallelism degree; and reconstructing the parallel execution mode of the current service into the five-dimensional parallel strategy without interruption, and executing the five-dimensional parallel strategy. According to the technical scheme provided by the embodiment of the invention, the system can be dynamically switched among a plurality of parallel dimensions under the condition of load fluctuation, and the overall calculation cost is minimized on the premise of ensuring the service quality.

The invention provides a processing and assembling combined production workshop scheduling optimization method considering dynamic disturbance, and the method comprises the steps: building a combined scheduling model: dividing a product production process into a part processing process, an assembling process and an assembling subsequent process, defining the correlation constraint of processing and assembling, and carrying out the processing and assembling operation; comprising part machining sequence consistency, part machining completion requirements before assembly, buffer area capacity limitation and a dynamic disturbance event response mechanism; establishing a multi-objective optimization function: taking minimization of maximum completion time, equipment idle time, processing energy consumption cost and tool switching times as optimization objectives, and generating a scheduling model in combination with process time dependence, machine selection uniqueness and tool switching time constraint; dynamic disturbance processing: when an equipment fault occurs or a new order is inserted, updating an available machine state or combining tasks to be processed, and triggering rescheduling to generate a new scheme; an improved MOEA / D algorithm is used for solving; and outputting and applying a scheduling scheme: selecting a final scheme for production guidance according to the non-dominated solution set.