218 results about "Load scheduling" patented technology

The invention belongs to the technical field of power system load prediction, and discloses a cross-dimension multi-scale fusion load prediction method based on multi-user load time-space correlation, which comprises the following steps of: firstly, preprocessing user load statistical data, extracting time sequence dependence and periodic characteristics in a time sequence, and calculating the time sequence dependence and periodic characteristics of the user load statistical data; introducing a channel attention mechanism to adaptively mine key variable information; then, a multi-scale space-time fusion module is combined with frequency domain analysis and a graph convolutional network to realize depth feature interaction under different time scales and space levels; and finally, outputting a load prediction result under a plurality of time granularities in the future through a linear projection structure. Compared with an existing method, the method has the remarkable advantages in the aspects of capturing a complex load mode, improving model prediction precision and enhancing generalization ability, and is suitable for various application scenes such as power consumer energy consumption management and power grid load dispatching.

The invention discloses a virtual power plant building key load priority distribution method and system, and relates to the technical field of load dispatching management. The virtual power plant building key load priority distribution method comprises the following steps: S1, acquiring load switching scheduling data, and preprocessing the load switching scheduling data; s2, identifying an executable switching window between the main power supply and the standby power supply, quantifying a switching impact index of a load, and screening a candidate load set; s3, evaluating the switching priority of the load and generating a sorting list, and sequentially selecting according to the upper limit of the residual impact capacity of the bus to form a current period execution plan; and S4, executing a scheduling instruction, recording operation parameters before and after switching in real time, constructing a disturbance evaluation input set, evaluating a load switching disturbance degree, judging a switching state based on an evaluation result, and triggering a feedback mechanism to adjust a subsequent sorting weight and an impact tolerance. The problem of bus impact caused by concurrent access of multiple loads in the main and standby power supply switching process is solved.

The invention relates to the technical field of distributed computing, and discloses a heavy truck charging load scheduling-oriented distributed energy intelligent matching method, which comprises the following steps of: establishing a charging service computing power mapping table at a scheduling node; maintaining a shadow counter in a local memory, extracting a pre-estimated computing power consumption value according to an event type and accumulating the pre-estimated computing power consumption value to the shadow counter, and executing linear numerical deduction on the shadow counter according to a reference logic subtraction rate so as to simulate a scheduling data throughput evolution process; adjusting a linear deduction rate parameter according to the deviation between the state feedback data and the numerical value of the shadow counter; and distributing the charging matching task to a charging station edge computing node of which the shadow counter value does not exceed a preset logic saturation threshold value. According to the invention, through an open-loop estimation and closed-loop calibration mechanism of a local logic state, an instantaneous congestion risk caused by physical feedback lag is eliminated; and logic state consistency and self-adaptive distribution of the whole network computing power resources are realized.

The invention discloses a space-time price-based computing power and electric power space-time collaborative flexible scheduling method and device, and relates to the technical field of electric power systems, and the method comprises the steps: obtaining the architecture and operation characteristics of a data center, pre-establishing an energy consumption model and a load scheduling model of the data center, and pre-establishing a computing power-electric power collaborative regulation double-layer optimization model, the calculation power-electric power coordinated regulation double-layer optimization model is based on an energy consumption model and a load scheduling model of the data center, takes the initiative of the data center as an independent operator and the influence of the load of the data center on the electricity price of the system into consideration, and is constructed by taking the data center as a decision-making main body; a lower-layer power grid direct current optimal power flow problem is converted into a KKT condition to serve as a constraint to be substituted into an upper-layer problem, a strong dual theorem and a Big-M method are utilized to linearize and solve the double-layer optimization model of computing power-power coordinated regulation, and a computing power-power space-time coordinated flexible scheduling result is obtained.

The invention provides a large language model application workload scheduling method, system and device, and relates to the technical field of model load scheduling, and the method comprises the steps: modeling a composite large language model application into a directed acyclic graph comprising a conventional stage, an LLM stage and a dynamic stage; modeling execution correlation among stages in the directed acyclic graph through a Bayesian network, dynamically predicting duration distribution of uncompleted stages, and calibrating a duration estimated value of an LLM stage in combination with a real-time batch processing size of an LLM executor; the uncertainty reduction amount of each ready stage is quantitatively scheduled based on information entropy; an epsilon-greedy strategy is adopted, and a JCT priority queue and an uncertainty reduction priority queue are combined to allocate scheduling resources; and assigning the task to a corresponding executor for execution, and repeating the above process until all operations are completed. The technical problem that the scheduling technology in the prior art is difficult to effectively deal with the execution time uncertainty and the structure uncertainty of the composite LLM application is solved.

The invention discloses a multi-port flexible interconnection control method, system, equipment and medium, and the method comprises the steps: obtaining first historical load information and real-time load information of a first flexible interconnection device, obtaining a plurality of clustering results based on the first historical load information, based on each clustering result and the real-time load information, judging whether the first flexible interconnection device breaks down or not; if a fault occurs, respectively acquiring second historical load information of each second flexible interconnection device, determining a plurality of standby devices based on each second historical load information, calculating a target distance between the first flexible interconnection device and each standby device, and determining the standby device with the minimum target distance as a target port flexible interconnection device; and connecting the load of the first flexible interconnection device and the distributed power supply to the target port flexible interconnection device, so that the target port flexible interconnection device performs load scheduling. Therefore, resource waste can be reduced while stable operation of the power grid is guaranteed.

The invention relates to a fault network card isolation method and device applied to a GPU cluster, electronic equipment, a storage medium and a computer program product, and the method comprises the steps: determining whether a fault network card exists on any GPU node in the GPU cluster or not according to the state information of each network card in the GPU node; when it is determined that fault network cards exist on the GPU node and the number of the fault network cards is smaller than or equal to a preset threshold value, an NCCL topological file of the GPU node is updated, and the NCCL topological file of the GPU node is used for indicating the topological relation between available GPU devices and available network cards included in the GPU node; and according to the NCCL topology file of the GPU node, isolating a fault network card in the GPU node when carrying out load scheduling on the GPU node. According to the embodiment of the invention, the fault isolation granularity can be effectively refined to a single network card in the GPU cluster.

The invention provides a load optimization scheduling method and system based on a transformer area energy storage device, and belongs to the technical field of load scheduling, and the method specifically comprises the steps: determining the residual energy storage capacity of a standby energy storage device and a standby association relationship between the standby energy storage device and different power distribution transformer areas, in combination with the residual energy storage capacity of the transformer area energy storage devices of the power distribution transformer area with the standby association relationship, when it is determined that the standby adjustment coefficients of the standby energy storage devices meet the requirements, the standby adjustment coefficients of the different standby energy storage devices with the standby adjustment coefficients meeting the requirements and the coincidence condition of the power transmission lines of the power distribution transformer area are determined; the working modes of different standby energy storage devices are determined, and the stability of the load of the power distribution area is improved.

The invention discloses a micro-grid energy scheduling optimization method based on artificial intelligence load prediction, and the method comprises the following steps: collecting original data of a micro-grid, and carrying out the preprocessing of the original data, and obtaining the preprocessing data; constructing a causal directed acyclic graph by adopting a causal discovery method based on the preprocessed data to obtain a prediction feature set; constructing an improved causal convolutional network based on the prediction feature set; inputting the preprocessed data and the prediction feature set into an improved causal convolutional network for training, and generating a load prediction result; constructing a micro-grid energy scheduling model; inputting the load prediction result into the micro-grid energy scheduling model for solving, and generating an energy storage unit power distribution strategy, a renewable energy source output distribution strategy and a controllable load scheduling strategy; and updating the preprocessed data and the prediction feature set, generating a new load prediction result, inputting the new load prediction result into the micro-grid energy scheduling model for solving, obtaining an updated scheduling scheme, and executing the updated scheduling scheme.

The invention provides a micro-grid management method and system based on source grid load storage, and relates to the technical field of micro-grids, and the method comprises the steps: S1, obtaining renewable energy power generation data in a micro-grid, the state of charge (SOC) of an energy storage device, a load demand, and power grid operation state information; and S2, performing real-time prediction on the load demand by using an intelligent algorithm and generating a load scheduling plan. According to the micro-grid management method and system based on source grid load storage, load prediction is carried out by introducing an intelligent algorithm, power scheduling between renewable energy sources and an energy storage device is optimized by a dynamic coordination mechanism, and resources are allocated by a multi-objective optimization algorithm, so that efficient management of the micro-grid is successfully realized. By acquiring various data in the micro-grid in real time and combining with a dynamic adjustment scheduling strategy, the method can effectively deal with the uncertainty of load fluctuation and renewable energy output, optimize the operation efficiency of the power grid, and ensure the stability and economy of the system.

The invention provides a multi-element load joint prediction method and system based on sequence decomposition and feature screening, and the method comprises the steps: collecting multi-element load data and related influence factor data of an integrated energy system, and carrying out the preprocessing, and obtaining the processed multi-element load data and related influence factor data; performing sequence decomposition on the processed multivariate load data, and fusing decomposed component sequences to obtain a multivariate fusion sequence; performing feature screening on the processed related influence factor data to obtain an influence factor feature set; and inputting the multivariate fusion sequence and the influence factor feature set into an improved multi-task learning model for joint training and prediction, and outputting a joint prediction result of the multivariate load. According to the multi-element load joint prediction method based on multi-source data decomposition and multi-task coupling learning, the model precision, generalization ability and operation efficiency can be effectively improved, and the multi-element load joint prediction method is suitable for cooling, heating and power load scheduling and energy optimization management of a comprehensive energy system.

The invention provides a flexible distributed energy network multi-agent collaborative optimization method based on MARL, and the method comprises the steps: building a distributed energy network multi-agent interaction framework which comprises a local energy transaction model for distinguishing an intelligent soft switching path, a network cost model based on a power transmission distribution factor, and a power distribution network operator and user income model; a physical system operation constraint model is established and covers intelligent soft switch operation characteristics, network topology radial constraint, energy storage charging and discharging dynamic states, controllable distributed power supply and photovoltaic output limitation, translational load scheduling and DistFlow power flow constraint. And finally, constructing a collaborative optimization mechanism based on a multi-agent near-end strategy optimization algorithm, modeling the system into a partially observable Markov decision process, adopting a centralized training distributed execution framework, and guaranteeing transaction security and data privacy through block chain evidence storage, RSA encryption and an intelligent contract. The system economy and the operation flexibility are improved.

The invention discloses a load optimization scheduling method and system based on a thermodynamic and electrical coupling model, relates to the technical field of load scheduling, and solves the technical problem that the existing load adjustment method neglects the coupling relationship between thermodynamic characteristics and electrical parameters of devices, resulting in poor adjustment effect. The method comprises the steps of obtaining operation data of load equipment; processing the operation data to obtain initial data; extracting and fusing multi-dimensional data features of the initial data to obtain a model input vector; constructing a thermodynamic and electrical parameter coupling model; the optimal scheduling strategy is generated based on the coupling model and the optimization algorithm, and the technical problem is solved.

The invention discloses a source network load storage oriented multi-resource hierarchical regulation and control method and system, and relates to the technical field of source network load storage hierarchical regulation and control. The multi-resource hierarchical regulation and control method oriented to the source network load storage comprises the following steps of source-network transmission matching analysis, network-load scheduling analysis and load-storage collaborative analysis. According to the invention, in the source network transmission stage, transmission matching analysis is carried out according to source network double-side data to determine whether transmission matching optimization regulation is carried out, then in the power distribution stage, load scheduling analysis is carried out to determine whether load scheduling optimization regulation is carried out, and finally in the load-storage linkage stage, load scheduling optimization regulation is carried out. Load-storage collaborative analysis is carried out according to the load-storage bilateral data to judge whether load-storage collaborative optimization regulation is carried out or not, so that timely and efficient source-network-load-storage multi-resource layered regulation is realized; the problem that in the prior art, when renewable energy sources are accessed, corresponding multi-resource layered regulation and control are not timely, and consequently, the'source-network-load-storage 'cooperation stability is not high is solved.

The invention discloses a layered optimization method considering fused magnesium high-energy-consumption load regulation and thermal power depth peak regulation, and relates to the technical field of power system optimization, and the method comprises the steps: bringing a fused magnesium high-energy-consumption load into a power system regulation system based on the production characteristics of a fused magnesium furnace, and constructing a fused magnesium load scheduling model in which the load participates in power grid scheduling; a thermal power depth peak regulation model is established in combination with the operation characteristics of the thermal power generating unit after flexible transformation; according to a game theory, constructing a grading decision model comprising an upper layer leader and a lower layer follower; the upper-layer leader aims at minimizing the wind curtailment amount, and the lower-layer follower aims at minimizing the operation cost of the system; and by solving the grading decision model, determining the peak regulation participation condition of the thermal power generating unit and the system operation cost, and obtaining an optimal scheduling result. According to the method, the high-energy-consumption fused magnesium load is brought into power grid optimization scheduling, and the wind power absorption capacity and the peak regulation performance are effectively improved.

The invention discloses an intelligent power grid dispatching system and method based on digital twinning and deep learning, and relates to the technical field of intelligent power grid dispatching, the intelligent power grid dispatching method based on digital twinning and deep learning specifically comprises the following steps: step 1, multi-source heterogeneous data and a dynamic parameter updating mechanism are fused, and a dynamic parameter updating mechanism is established; the method comprises the following steps of: 1, constructing a power grid digital twinborn body synchronously mapped with a physical power grid, 2, aggregating multi-region power grid data by adopting a federated learning framework, establishing an equipment degradation model and perfecting a priority data channel mechanism, and 3, determining a real-time power grid state and an equipment risk coefficient based on the power grid digital twinborn body, and designing a deep reinforcement learning dynamic decision framework. According to the method, the real-time power grid state and the equipment risk coefficient are determined based on the power grid digital twinborn body, a deep reinforcement learning dynamic decision framework is designed, and multi-target collaborative load scheduling optimization can be achieved.

The invention relates to a power equipment load scheduling optimization method and device. The method comprises the following steps: carrying out load operation data acquisition through monitoring units deployed in power equipment to obtain a distributed load operation data set, and obtaining strategy game relationship network data between the equipment based on the distributed load operation data set; obtaining initial load adjustment intention intensity data of each power device according to the policy game relationship network data between the devices; sending the initial load adjustment intention intensity data and the global collaborative scheduling optimization target to a distributed negotiation chain to obtain final load adjustment strategy data after negotiation consensus; and obtaining an optimized distributed load scheduling model according to the final load adjustment strategy data after negotiation of the consensus, distributing the optimized distributed load scheduling model to each power device, and executing decentralized power device load scheduling optimization. By adopting the method, the load scheduling of the power equipment can be optimized.

The invention discloses a distributed photovoltaic user power behavior control scheduling method and system, and the method comprises the steps: deploying an edge controller at a photovoltaic user local device, and collecting power data in real time; a sliding window autoregression model is adopted to carry out short-term load prediction, and an edge controller realizes energy storage state adjustment and load matching balance by constructing an edge node objective function; carrying out constrained quadratic programming solution on the edge node target function, taking a solution result as a node local scheduling strategy, and regularly uploading a current state and a control result to the cloud; the cloud optimization layer collects all edge node state data, constructs a global system state set, and establishes a multi-target joint scheduling model on the cloud optimization layer; and solving and optimizing the multi-target joint scheduling model to generate a global scheduling strategy, and issuing the global scheduling strategy to each edge node. According to the invention, energy prediction and real-time load scheduling are independently executed on the edge side controller on the basis of local data, and the response speed is improved.

The invention discloses an artificial intelligence Emsp super charging prediction and management system, and relates to the technical field of Emsp super charging, the charging demand and the power grid load change are predicted by obtaining the charging station equipment state, the user behavior, the power grid load and the environment data, and an optimized charging task distribution plan is calculated; the charging power switching rate is smoothly adjusted by the load scheduling module, and the instantaneous load change rate is reduced; the synchronous control module is used for realizing synchronization of frequency and phase of the charging equipment and the power grid; a coordination index is monitored in real time by means of an evaluation and dynamic regulation and control module, power distribution is dynamically adjusted under the incoordination condition, and the power of a high-load station is dispersed; real-time data and historical data are integrated through the control and storage module, an artificial intelligence model and a scheduling strategy are optimized, the risk that a power grid is unstable due to instantaneous load surge and harmonic interference is effectively reduced, the operation efficiency and safety of a charging network are improved, and meanwhile the charging experience of a user is improved.

The invention relates to a micro-grid optimization scheduling method with electric vehicle and multi-source uncertainty. The micro-grid optimization scheduling method comprises the following steps: S1, constructing a multi-target optimization scheduling model of a micro-grid system layer; s2, performing robust modeling on multi-source uncertainty in the multi-target optimization scheduling model of the micro-grid system layer based on a multi-target confidence gap decision theory, and establishing a robust optimization model of the micro-grid system layer; s3, constructing an optimal scheduling model of an electric vehicle user layer based on a foreground theory, and taking electric vehicle user comprehensive foreground value maximization as a target function; and S4, constructing a double-layer segment model of day-ahead scheduling, carrying out cooperative solution on an upper layer and a lower layer by adopting a double-layer optimization algorithm, and outputting a day-ahead scheduling plan of each unit in the micro-grid and the electric vehicle. According to the method, the comprehensive operation cost, the load fluctuation level, the electric vehicle owner utility and the source load uncertainty of the micro-grid are integrated, and the internal load stability and the energy utilization rate of the micro-grid are improved by excavating the scheduling potential of the source load side.

The invention belongs to the technical field of charging pile load scheduling, and provides a power distribution network measurement data fusion driven ultrafast charging load flexible regulation and control method and system, and the method comprises the steps: firstly processing multi-source data through a multi-source measurement data fusion module by employing a self-adaptive weighted fusion and Kalman filtering algorithm, and forming a high-fidelity data pedestal; the load is predicted through a charging load accurate prediction module in combination with wavelet transform, an LSTM-GNN model and a variational mode decomposition algorithm; then, a dynamic regulation and control strategy generation module generates a regulation and control strategy through marginal cost pricing and deep reinforcement learning according to prediction; the source-load collaborative optimization module integrates related systems and optimizes scheduling by means of a particle swarm optimization algorithm; the real-time monitoring and feedback module monitors and corrects the strategy in real time; and the security protection module ensures data and system security. During use, the above module processes are operated in sequence, and flexible regulation and control of the ultrafast charging load are realized.

The invention provides a flexible load aggregation scheduling method and device for a power distribution system, and belongs to the technical field of load aggregation. The method comprises the steps of collecting operation data of a flexible load, performing feature extraction on the operation data, and forming a plurality of feature vectors according to each extracted feature; obtaining Euclidean norms of the feature vectors, evaluating the information richness of the feature vectors by using the Euclidean norms, and reserving the feature vectors of which the information richness meets a preset requirement; fusing all the reserved feature vectors to form a comprehensive feature vector; and forming a load scheduling scheme of the flexible load based on the comprehensive feature vector. According to the method, the Euclidean norms of the feature vectors are obtained to evaluate the information richness and keep the feature vectors meeting the requirements, so that the information richness of the feature vectors is improved, the accuracy of subsequent data analysis is improved, and a flexible load scheduling scheme formed based on the comprehensive feature vectors is optimized.

This invention provides a load balancing method and system for cryptographic devices based on shared locks. When receiving a request from a business system, the method determines the request source based on request parameters and calls the corresponding resource occupancy ratio and group identifier. Based on the group identifier, it searches the corresponding shared lock pool. Based on the number of locks in the shared lock pool, it calculates the maximum number of idle locks that the corresponding business system can use. It then searches the shared lock pool for idle locks and finds the corresponding Socket connection object through the association relationship of the successfully found locks. Finally, it uses this Socket connection object to call the cryptographic device for cryptographic operations. This method can solve the scheduling problem of multiple cryptographic devices and ensure balanced scheduling across multiple cryptographic machines.

The invention discloses a software scheduling system and method for load balancing of communication links of a circuit controller, and relates to the technical field of communication links, the system comprises a link load monitoring unit, a link load scheduling module, an early warning terminal and a database, and by testing each communication link corresponding to the circuit controller under each layer, the load balancing of the communication links is realized. The load type of each communication link is obtained through analysis based on the tested data, and software scheduling under the specific load type corresponding to each communication link is executed, so that the omnibearing load balancing analysis of the communication link of the circuit controller is realized, the stability and efficiency of the communication link of the circuit controller are comprehensively guaranteed, and the reliability and reliability of the circuit controller are improved. The risk of unbalanced load of the communication link of the circuit controller is reduced, the phenomena of link overload and link idle waste of the communication link are avoided, and the application efficiency of the communication link of the circuit controller is improved.

The invention discloses a new energy charging pile operation data analysis processing method, and relates to the technical field of new energy charging pile data analysis, and the method comprises the following steps: S1, collecting multi-source operation data such as charging power, current and voltage of a charging pile, and storing the multi-source operation data according to a timestamp; s2, preprocessing data, removing abnormal values, complementing missing values and standardizing; s3, extracting instantaneous operation, time dimension and equipment state core features; s4, user charging behaviors are clustered and analyzed to generate a classification label library; s5, analyzing an operation load situation and identifying a load fluctuation factor; s6, evaluating the health state of the equipment, grading and performing early warning; s7, generating optimization strategies such as load scheduling; and S8, collecting new data to iteratively optimize model parameters and algorithm logic. According to the method, multi-source data fusion and accurate analysis are realized, the fault identification accuracy and the load balance degree are improved, and a landing optimization strategy is generated; different scenes are adapted through iterative optimization, and scientific support is provided for fine management of the charging pile.

The application provides a network load balancing algorithm based on a Xinyuan platform and a Xinyuan terminal, and relates to the technical field of Xinyuan, which comprises the following steps: collecting real-time traffic data from multiple ports; performing normalization, outlier elimination and protocol field standardization preprocessing on the collected data; performing multi-dimensional protocol fingerprint feature extraction on the traffic of each port based on a protocol analysis algorithm; modeling the historical and real-time traffic of each port using a time series neural network, and outputting traffic prediction values and abnormal traffic probability evaluation in a future short period; dynamically generating a multi-port distribution weight factor based on the protocol characteristics and traffic change trend of each port; inputting the prediction results and real-time load state into a reinforcement learning scheduling agent; and immediately performing feedforward load distribution adjustment when abnormal traffic trend is detected. The method can improve the data processing efficiency, realize the intelligence of load scheduling, ensure the resource allocation priority of the ports of the Xinyuan terminal, and guarantee service continuity.

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

The invention relates to the field of generator load coordination control, particularly discloses a load coordination control method and system for a full-hydrogen-cooled generator, and aims to solve the problems that the running boundary is fixed and the real-time health condition of the generator cannot be matched in the prior art. According to the method, multi-dimensional operation state parameters of the all-hydrogen-cooled generator are collected in real time, and a comprehensive health state index is obtained based on weighted fusion evaluation; dynamically constructing a dynamic safe operation domain formed by active power and reactive power boundaries according to the index; after receiving an external power grid dispatching instruction, checking whether a target power point is in the dynamic safe operation domain; if the instruction exceeds the safe operation domain, the instruction is automatically corrected to the nearest safe point in the domain, and a final load control instruction is generated and executed. According to the method, the safety operation domain matched with the real-time health condition of the generator is dynamically constructed, and the scheduling instruction is automatically checked and corrected, so that the safety and the accuracy of load scheduling are ensured, and the operation efficiency and the stability of the generator are improved.

The invention provides a hybrid cloud architecture-based power business load balancing scheduling method and system, and the method comprises the steps: classifying power business operation data collected in real time based on the importance of power businesses, and obtaining a target power business category; determining a current load state of the target power business category by combining resource state information of the private cloud resource pool and the public cloud resource pool based on the target power business category and the corresponding power business operation data; and determining a load scheduling strategy based on the current load state for the target power business category. According to the method, the problems that in an existing method, the resource capacity of a local physical server cluster is fixed, sudden peak loads are difficult to deal with, and service response delay and data processing interruption are likely to be caused are effectively solved, and meanwhile stable and efficient operation of a power system is guaranteed.

The invention discloses a chip low-power-consumption intelligent control method and system based on a proportion threshold value, and relates to the technical field of chip power consumption control. A proportion threshold reference model of each module of the chip is established, a proportion threshold sensing unit is designed to collect chip operation data in real time and identify proportion stress points influencing chip power consumption, and on this basis, chip power supply, clock and load scheduling are dynamically optimized through an intelligent control unit, so that the chip always works in an optimal proportion threshold interval. According to the method, the overall power consumption of the chip can be greatly reduced, the energy efficiency ratio is improved, the core task performance is guaranteed, the chip operation stability is improved, and the method is suitable for power consumption optimization of hardware such as various AI chips, processors and SoC.