1127 results about "Majorization minimization" patented technology

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 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 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 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 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.

Techniques for host fleet management in a cloud provider network are described. Forecast data including a forecasted demand for virtual machines in each capacity pool of a set of capacity pools is obtained. A mathematical optimizer application is executed to generate a first optimal fleet plan, the mathematical optimizer application having an objective function to minimize a number of new host computer systems to add to the set of host computer systems to satisfy the forecasted demand for each capacity pool, the first optimal fleet plan includes an identification of a set of hardware types and, for each hardware type in the set, a quantity of new host computer systems of the hardware type. A plurality of new host computer systems is deployed, based on the first optimal fleet plan, for a hardware type in the set of hardware types into the set of host computer systems.

The invention relates to a heterogeneous computing-based task scheduling method and device, a storage medium and equipment. The method comprises the following steps of: obtaining an inference task of a large language model; in the execution process of the reasoning task, at least based on the memory access intensity and the current reasoning stage, memory access intensive operators and calculation intensive operators in the reasoning task are recognized; allocating the memory access intensive operator to a first computing unit for executing a memory intensive task, and allocating a computing intensive operator to a second computing unit for executing a computing intensive task; obtaining estimated execution time of the two calculation units for executing the corresponding tasks and data transmission time between the two calculation units; according to the pre-estimated execution time and the data transmission time, the task starting moments of the first calculation unit and the second calculation unit are determined with the purpose of minimizing the overall execution delay of the reasoning task; and controlling the first calculation unit and the second calculation unit to asynchronously execute the corresponding tasks in parallel according to the task starting time.

The invention relates to the technical field of computing resource allocation, in particular to a joint optimization method for a task processing sequence and resource allocation, and provides an end-side collaborative MEC computing architecture, and a joint optimization model for a task scheduling sequence and computing resource allocation is constructed on the basis of the MEC computing architecture and a partial unloading mechanism; meanwhile, by considering limited computing resources of the terminal equipment, time delay constraints of tasks and maximum task number constraints of parallel processing allowed by the terminal equipment, an optimization problem with the purpose of minimizing system overhead is formulated. And then the original optimization problem is decoupled into a task unloading decision sub-problem and a joint task processing sequence and computing resource allocation sub-problem, an alternating iterative optimization method is adopted for solving, the sub-problems are optimized one by one in combination with a convex optimization technology, and the optimal solution of the original problem is solved step by step through a continuous alternating iterative optimization process. Simulation results show that system time delay and energy consumption expenditure are reduced, and the completion rate of tasks and the utilization rate of computing resources are improved.

A full-automatic packaging scheduling method based on a multi-objective optimization algorithm, which method relates to the technical field of intelligent production scheduling in packaging workshops. The method comprises: on the basis of work orders to be packaged of a production line, extracting production data of the production line, and initializing parameters; constructing a multi-objective optimization model of the packaging production line; to address the problems of premature convergence and susceptibility to local optima in an INSGA-II algorithm, using the INSGA-II algorithm to improve an initialization method, crossover and mutation strategies and crossover and mutation factors, and performing solving on the basis of objective functions such as minimizing the maximum makespan, minimizing the maximum energy consumption and minimizing the total machine load, so as to generate an optimized scheduling scheme; and starting packaging operations on the basis of the generated optimized scheduling scheme. The method can increase the unit-time production capacity of a production line, and effectively solve the problems in packaging production scheduling, thereby reducing the production costs of enterprises and improving the packaging production efficiency.

The invention discloses a multi-source cooperative power distribution network fault self-recovery and recovery optimization method, system and device and a storage medium, and relates to the technical field of power system power distribution networks, and the method comprises the steps: collecting the electrical quantity and parameters of each node in real time, and obtaining system state information through data processing; detecting faults by using a multi-criterion algorithm, and determining types and severity; determining a fault section according to a result and minimizing isolation; a collaborative recovery strategy is formulated by integrating multiple sources, and network reconstruction and switching operation optimization are carried out; and finally evaluating a recovery effect, and combining with a historical data feedback adjustment strategy to improve the recovery efficiency. The fault recovery capability of the power distribution network can be remarkably improved, the fault isolation is fast, the load recovery rate is high, the recovery time is short, the economic loss is reduced, the self-healing of different fault scenes is strong, and the unification of technology and economic benefits is realized.

The invention provides a data center calculation, electricity and heat collaborative optimization scheduling method and system, and relates to the technical field of comprehensive energy scheduling. According to the scheduling method and system, a collaborative scheduling model of computing power, electric power and thermal power is constructed, and a user side thermal demand response mechanism is introduced, so that mismatching of waste heat supply of a data center and user thermal demand in time and space is dynamically relieved, and the waste heat utilization rate and the overall energy efficiency of the system are remarkably improved; by establishing a joint optimization framework, a complex coupling relationship among computing power, electric power and heating power is accurately described and coordinated, so that the comprehensive operation cost of the data center is minimized on the premise of ensuring the service quality of the workload of the data center; and a large language model-assisted deep learning algorithm is further adopted to solve the scheduling model so as to cope with multiple challenges of workload fluctuation, electricity price change and heat demand uncertainty, and a self-adaptive, intelligent and interpretable scheduling decision is realized.

The invention discloses an adjustable resource unified data external characteristic modeling, regulation and control method and system oriented to various transaction scenes. The method comprises the following steps: collecting real-time data of an internal adjustable resource of a virtual power plant; the climbing time, the duration, the response capacity and the responsible frequency are quantized and defined as a group of external characteristic parameters, an adjustable resource data external characteristic model is constructed, adjustable resources are classified according to the external characteristic parameters of the model, and an adjustable resource characteristic library is established; in combination with the response characteristic and the load state of each adjustable resource, generating an optimal regulation and control strategy meeting the regulation and control requirements, and allocating a corresponding regulation and control instruction to each adjustable resource; each adjustable resource adjusts power output according to the regulation and control instruction, and meanwhile, the calling cost of each adjustable resource is calculated; in combination with the real-time state and the adjustment cost minimization target, the regulation sequence and proportion are optimized; according to the method, the economy and flexibility of the virtual power plant in multi-scene regulation can be effectively improved, and meanwhile, the accuracy of power grid frequency modulation response and the system stability are enhanced.

The invention relates to the technical field of high-performance computing resource management, and discloses a computing resource allocation method for a distributed supercomputing center. The method comprises the following steps: on the basis of obtaining real-time computing task and supercomputing center resource data and uniformly quantifying, integrally predicting resource requirements of future tasks; constructing a mixed integer linear programming model with the minimization of the total operation cost as a single target, wherein the total operation cost is the sum of the energy cost, the carbon emission cost, the data transmission cost and the SLA default penalty cost; solving the model by taking the time-varying electricity price, the green energy ratio, the resource capacity and the network parameters of each center as constraint conditions to generate an optimal resource allocation scheme; and then, by dynamically monitoring the resource state and the task progress, the model is triggered to resolve when the resource utilization rate is detected to be unbalanced or default risks, so that self-adaptive adjustment is realized. According to the invention, global collaborative resource allocation across super computing centers is realized, and operation economy, environmental sustainability and service reliability are considered.

The invention provides a gateway data transmission control method and system based on an improved token bucket method. According to the method, a traditional token bucket flow limiting method is improved by introducing a parameter self-optimization mechanism, a burst flow self-adaptive adjustment mechanism and a multi-node cooperative control mechanism. The method comprises the following steps: firstly, generating tokens according to a specified frequency and distributing the tokens to token buckets, and requesting to perform access control according to token acquisition conditions by a client; dividing the data into a plurality of independent data groups, queuing and processing the data groups in corresponding token buckets, and solving the optimal token bucket capacity and issuing rate to minimize data processing delay by analyzing the arrival rate and queuing probability of data packets; when a single-channel or group-level burst traffic event is detected, the token bucket rate and capacity are automatically adjusted to achieve traffic limiting adaptation and cooperative stabilization. According to the invention, system load balance and rate convergence can be maintained under a high concurrency condition, time delay and jitter caused by flow fluctuation can be substantially reduced, and continuity of data transmission and gateway scheduling efficiency can be improved.

The invention discloses an inference task collaborative scheduling system and method oriented to multiple terminals of a swan gap. The inference task collaborative scheduling system comprises a communication module Broker, a system monitoring module SystemProfilter, a scheduling module Scheduler and an inference task execution module Worker. According to the method, a structured resource state vector is constructed based on an NDK native interface so as to comprehensively represent the real-time availability of equipment; a lightweight MQTT protocol is adopted to support low-overhead and high-robustness cross-terminal state synchronization and task distribution; a comprehensive load scoring mechanism fusing task priorities and dynamic weights is designed, a multi-objective optimization problem based on a non-dominated sorting genetic algorithm (NSGA-II) is introduced, task delay is minimized in a combined mode, terminal loads are balanced, and energy consumption is controlled; meanwhile, the execution time delay is efficiently estimated in combination with a proxy model based on linear regression, and the scheduling overhead caused by real reasoning and calling is avoided; the whole architecture is deeply adaptive to a swan-mong system, and is compatible with an Android platform through modular packaging and unified communication interface design, and efficient, self-adaptive and cross-platform collaborative scheduling oriented to a swan-mong multi-terminal reasoning task is realized for the first time.

The invention relates to an internet of vehicles edge computing task unloading and resource scheduling optimization method, which comprises the following steps: constructing an internet of vehicles edge computing system model fusing a task jump mechanism and dual-priority scheduling, the system model comprising a road test unit deployment model, a communication model, a computing model and a task jump model; establishing a joint optimization function aiming at minimizing the total time delay and the total energy consumption of the system; decomposing a joint optimization problem into three sub-problems of unloading decision, computing resource allocation and communication strategy selection; a deep reinforcement learning algorithm is adopted to intelligently sense a road environment state, an optimal communication priority strategy combination is dynamically selected, and a task unloading decision and computing resource allocation are collaboratively optimized; and in each scheduling time slot, the edge server allocates communication bandwidth and computing resources to the vehicle tasks according to the selected strategy, and triggers a task preemption and cross-server jump mechanism, thereby realizing maximization of system throughput and minimization of task processing time delay.

The invention relates to the technical field of reservoir flood control scheduling, and discloses a reservoir group flood discharge gate scheduling method, device and equipment and a storage medium, and the method comprises the steps: firstly building a scheduling model with the minimization of downstream flood peak flow and gate adjustment times as optimization targets, and carrying out the constraint of the scheduling model according to the operation rule of a reservoir group; then, the model is mapped into a deep reinforcement learning framework, information reflecting the operation condition of the reservoir group is used as a state, a specific combination of each gate opening degree is defined as an action, and a function which is in negative correlation with an optimization target is used as an award; and finally, adopting a deep reinforcement learning algorithm to train and solve the frame so as to directly generate a scheduling scheme containing the specific opening state of each flood discharge gate. The executable gate opening scheme is directly output, and the problems that in the prior art, a scheduling scheme is disjointed with actual operation, optimization space exists, and the real-time requirement is difficult to meet are solved.

The invention discloses a method for applying linear programming to CDN (Content Delivery Network) scheduling, which relates to the technical field of content delivery networks and comprises the steps of data preparation, strategy layer version smooth configuration, macroscopic layer and microscopic layer linear solution and online execution. Basic data are collected, cleaned and repaired, and a version change rule is set; the macroscopic layer constructs a linear programming model, and the cross-provincial bearing quota is solved with the aim of minimizing the cross-provincial cost; the micro layer takes the quota as a boundary and generates domain name class-node weight vectors in parallel; and adapting a routing request online through weighted rendezvous hashing and request features. According to the method, a dynamic cost matrix and a weight granularity control technology are integrated, the engineering problem of linear programming is solved, second-level response, approximate global optimal scheduling and accurate execution of floating-point-level weight are realized, memory overhead is reduced, smooth updating of a strategy and system stability are guaranteed, and CDN service quality and operation efficiency are improved.

The invention discloses a multi-type energy scheduling method based on a trusted data space, and the method comprises the steps: accessing a multi-type energy provider through a block chain node, and constructing a cross-domain trusted data space; obtaining energy data of each party; processing to obtain an energy data set; calling a federated learning model, training a load prediction neural network, and predicting to obtain a future load demand; constructing a multi-target optimization model by taking the maximum consumption efficiency and the minimum energy abandoning rate of each type of energy as targets, and solving the multi-target optimization model based on the predicted future load demand and the output curve of each type of energy to obtain an optimal scheduling strategy; and storing the optimal scheduling strategy on the chain, and obtaining the optimal scheduling strategy on the chain by each type of energy providers to perform energy scheduling. A decentralized trusted data space is constructed through a block chain technology, data source traceability and non-tampering operation are realized, a centralized platform trust risk is avoided, and data privacy zero leakage during cross-domain sharing is ensured by adopting privacy calculation.

The invention discloses an industrial park virtual power plant reactive voltage control method of multi-target multi-agent deep reinforcement learning considering energy storage life, and belongs to the technical field of virtual power plant reactive voltage control methods based on industrial data acquisition. The problem that in the prior art, a traditional industrial park virtual power plant reactive voltage control method is difficult to consider park network loss optimization and energy storage life protection at the same time is solved. According to the method, a multi-objective optimization model including network loss minimization, node voltage deviation minimization and energy storage battery service life maximization is constructed, a virtual power plant is divided through a distributed multi-agent framework, each agent trains multiple strategies in parallel through a multi-objective multi-agent deep reinforcement learning algorithm based on local observation, the Pareto front is approached, and the energy storage battery service life is maximized. High-efficiency control is realized, and each intelligent agent independently generates an energy storage reactive power regulation and active power charging and discharging instruction. The reliability of the energy storage equipment is improved, and the method can be applied to an industrial park active power distribution network scene with high renewable energy source permeation.

The invention relates to the technical field of electric power system dispatching, in particular to a multi-microgrid collaborative optimization dispatching method based on an improved ADMM, and the method comprises the steps: constructing a microgrid operation cost minimization objective function based on a microgrid mathematical model, and carrying out the operation constraint of each microgrid; iteratively updating a local variable, a global variable and a Lagrange multiplier by using an ADMM model to solve the operation cost of the micro-grid; and income distribution is carried out based on the asymmetric Nash negotiation model. According to the method, the problem that the convergence speed and the calculation complexity need to be further improved when an existing model is used for multi-microgrid dispatching optimization is solved.

The invention discloses a multi-energy fusion system cooperative scheduling method and device in a port dynamic scene, and relates to the field of port energy system optimization scheduling, and the method comprises the steps: constructing a dynamic coupling relation model according to port data; according to the energy system power of each area at the current time point, a multi-objective optimization model is constructed, and objective functions of the multi-objective optimization model include operation cost minimization, total carbon emission minimization, energy storage equipment service life maximization, energy storage equipment power optimization and energy storage equipment power optimization. The constraint conditions of the multi-objective optimization model are power balance, energy storage charge state, electric hydrogen equipment capacity, berth distribution continuity and load demand priority; according to the multi-target optimization model and the port data of each region at the current time point, determining a target collaborative scheduling operation strategy of each region at the current time point, the target collaborative scheduling operation strategy comprising a multi-energy output distribution scheme, a load response instruction and an equipment operation parameter; and executing the target collaborative scheduling operation strategy of each region at the current time point.

The invention discloses a power distribution network collaborative optimization scheduling method and system considering asymmetric Nash bargaining and producer and consumer renting shared energy storage. The method comprises the following steps: constructing a wholesale market, a retail market and a P2P market, and a multi-agent collaborative transaction framework of mutual influence among a power distribution network operator, a shared energy storage operator and producer and consumer, wherein the multi-agent collaborative transaction framework comprises the wholesale market, the retail market, the P2P market and the mutual influence among the power distribution network operator, the shared energy storage operator and the producer and consumer; constructing a multi-agent optimization scheduling model for renting shared energy storage by the consumer and introducing a bargaining factor to measure the contribution degree of each consumer during electric energy transaction; a cooperative game Nash bargaining theory is introduced to re-model an original multi-body optimization scheduling model, and the model is decomposed into two sub-problems of total cost minimization and payment benefit maximization; a self-adaptive step size ADMM algorithm is adopted to perform distributed optimization solution on the sub-problems to obtain the electricity quantity purchased and sold from the power grid by the producer and the consumer and the shared energy storage, the P2P transaction electricity quantity and the transaction electricity price; and an improved IEEE33 node power distribution system is adopted to carry out example analysis, and a scheduling plan arrangement of multi-agent collaborative optimization operation is obtained.

The invention provides a packaging test workshop intelligent scheduling algorithm based on multi-scale information fusion driving, and belongs to the field of intelligent optimization scheduling, and the method comprises the steps: firstly analyzing a workshop production process and constraint conditions, and constructing a multi-target optimization model with the target of minimizing the maximum completion time, the total mold change time and the total tardiness time; a scheduling framework fusing an LSTM-Informer prediction model and an ITD3 algorithm is provided, prediction features are generated through multi-source data collection and fusion, multi-scale prediction of a buffer area state is realized by using the LSTM-Informer, and the ITD3 algorithm is driven based on prediction information to carry out dynamic decision making; and meanwhile, a composite scheduling rule and a layered reward mechanism are designed to improve the solving efficiency. According to the method, the dynamic scheduling problem in actual production can be effectively solved, and the maximum completion time, the total die change time and the total tardiness time are remarkably shortened.

The invention provides a transaction and scheduling optimization method and system for a virtual power plant participating in a spot market, relates to the technical field of energy systems, and solves the problem of electricity purchase cost minimization of the virtual power plant participating in spot transaction and the problem of how to report and regulate adjustable resources in the virtual power plant containing multiple distributed energy main bodies. The method comprises the following steps: acquiring first data and second data; according to the spot transaction price, the static data, the first data and the second data, constructing an optimization target for minimizing the overall power purchase cost of the virtual power plant, and setting a comprehensive power constraint condition and an energy storage system constraint condition; and solving through a linear programming solver to obtain an optimal spot declaration strategy and a regulation and control strategy of corresponding equipment. The method is used in the virtual power plant transaction and scheduling optimization process, the declaration strategy of the electric power spot market is considered, the electric quantity of the real-time market is adjusted through adjustable resources such as adjustable equipment and energy storage equipment on the user side, and the electricity purchase cost can be reduced and the marketization risk can be controlled.

The invention discloses a resource scheduling method and device, electronic equipment, a storage medium and a product. Relates to the technical field of wireless communication. The method comprises the following steps: collecting user side parameters, network side parameters and environment parameters; according to the multi-dimensional input parameters, a resource scheduling scheme is generated based on a multi-objective optimization model, and optimization objectives of the multi-objective optimization model comprise resource utilization rate maximization, user experience balance degree maximization of different services and base station power consumption minimization; and according to the resource scheduling scheme, performing joint scheduling on the time-frequency resource, the space resource and the power resource. According to the technical scheme, on the basis of considering the coupling relationship and mutual influence between different types of resources, the optimal compromise scheduling scheme with relatively high resource utilization rate, balanced user experience and relatively low base station power consumption can be found by utilizing the multi-objective optimization model; combined scheduling of time-frequency resources, space resources and power resources is achieved, and the resource utilization rate and the comprehensive communication performance are improved.

The invention relates to the technical field of intelligent manufacturing, and particularly discloses a space-time constraint modeling-based multi-AGV-mechanical arm collaborative carrying system, which comprises a space-time constraint modeling module, a task decomposition and priority evaluation module, a collaborative path planning module, a dynamic collision prediction and adjustment module and an energy consumption and efficiency optimization module, according to the method, the total energy consumption, the total duration and the congestion index are subjected to normalization weighting, the unified fitness function is constructed, and the genetic algorithm and the particle swarm optimization are adopted for joint optimization, so that energy consumption minimization and operation period minimization can be taken into consideration at the same time, and a high-congestion section is actively avoided on path selection. According to the multi-target fusion, side effects caused by single index optimization are avoided, the sustainable operation capacity of the system is improved, the actual time length fed back after task execution, energy consumption and collision near-loss information are improved, model parameters are updated through a reinforcement learning or online incremental learning module, and self-evolution of a strategy is achieved.

The invention discloses a micro-grid off-grid operation distributed control method based on consistency cooperation, belongs to the field of new energy micro-grid control, and aims to solve the problems of high single-point fault risk and single control target of existing centralized control. The method is operated in a three-layer architecture formed by a distribution network master station control layer, a micro-grid coordination control layer and an equipment distributed coordination control layer, a distributed communication network is constructed through edge agents, and weight coefficients and security constraints are configured; the edge agent receives a master station total power target, collects and interacts equipment data, calculates and limits amplitude to obtain a final power instruction based on a consistency updating law fusing global power difference distribution, energy storage SOC balance and system loss minimization, and then decomposes the final power instruction into equipment-level instructions to be issued and executed. According to the method, a single-point fault is eliminated, multi-target collaborative optimization is realized, control is simplified, expansibility is high, and power balance and stable and efficient operation when the micro-grid is off-grid are effectively guaranteed.

The invention provides an electric power computing network multi-dimensional resource scheduling method, device and platform and a storage medium, and belongs to the technical field of electric power computing power networks, and the method comprises the steps: obtaining the request information of a current service terminal and the computing power resource information of a cloud side computing node; determining an end-to-end time delay constraint, a cloud edge computing power resource constraint and a cloud edge end network bandwidth constraint of the intelligent server; according to the cloud edge computing power unit price and the network bandwidth unit price, determining an objective function of computing network multi-dimensional resource scheduling optimization by taking minimization of the network bandwidth and the cloud edge computing power overhead as an optimization objective; solving the plurality of scheduling constraint models to obtain an optimal solution; and outputting a computing network multi-dimensional resource scheduling strategy according to the optimal solution. According to the method, under the condition that different computing network resource service quality requirements of multiple services are considered, by dynamically deploying multi-dimensional resources such as network bandwidth, cloud computing power and edge computing power, the low response delay requirements of key services such as environmental risks and equipment faults in power grid operation are effectively met, and meanwhile it is ensured that the computing network resource consumption economical efficiency is optimal.