976 results about "Power load" patented technology

The invention relates to an electrical load prediction and optimization regulation and control method and system for high-energy-consumption equipment, and solves the problems of inaccurate load prediction, single regulation and control means and difficulty in dynamic adaptation of the high-energy-consumption equipment, and the method comprises the steps: collecting multi-source data of the high-energy-consumption equipment in real time, constructing a dynamic equipment collaborative causal graph after preprocessing, and extracting key constraints; inputting the data and the constraints into the dynamic digital sample model to obtain a system state simulation result; based on the result, a multi-objective optimization regulation and control strategy is generated and executed by using a meta-learning + reinforcement learning decision framework; and collecting actual data comparison deviation, starting hierarchical federated learning when a threshold value is exceeded, grouping and aggregating similar experiences according to a causal graph topology, and dynamically calibrating model parameters and a decision framework. The method has the following effects that accurate load prediction and multi-target cooperative regulation and control of the high-energy-consumption equipment are achieved, working condition changes are dynamically adapted, the cost is reduced, and continuous production and the service life of the equipment are guaranteed.

The invention discloses a power grid photovoltaic output and load sequence modeling method, system and device and a storage medium, and the method comprises the steps: comprehensively utilizing the multi-scale feature extraction capability of a time-frequency decomposition technology, the time sequence dependence modeling capability of a long and short-term memory network, and the global hyper-parameter optimization capability of a Bayesian optimization algorithm; and carrying out collaborative modeling and prediction on the photovoltaic output and the power load under a unified framework. By introducing a source load time-delay correlation analysis and probability interval construction mechanism, point prediction results and uncertainty intervals of photovoltaic, load and net load can be output at the same time, and a set of source load integrated prediction system with high prediction precision, strong robustness and reliable interval characterization capability is constructed. The method can improve the precision and reliability of photovoltaic power and load prediction, also can reduce the risk in power system scheduling, optimizes the energy storage configuration strategy, and especially has wide popularization potential and application prospects in the scenes of new energy grid-connected operation, intelligent micro-grid and virtual power plant management and the like.

The invention discloses a server energy-saving system and method based on a lag compensation type dynamic thermal impedance model, and relates to the field of server energy saving.By collecting operation data of a server hardware bottom layer in real time, a multi-dimensional thermal-computing force coupling time sequence atlas is constructed, and based on the multi-dimensional thermal-computing force coupling time sequence atlas, a dynamic thermal impedance model is established. Calculating a heat conduction time constant of hardware in a current environment; establishing a lag compensation type dynamic thermal impedance model based on the heat conduction time constant; constructing a thermodynamic phase space according to operation data; analyzing a noise reduction evolution trajectory in combination with the lag compensation type dynamic thermal impedance model; the method comprises the steps of generating a weighted thermal resonance state vector, activating an adaptive gain MPC predictive damping scheduling strategy based on the weighted thermal resonance state vector, constructing and solving a dynamic weighted multi-objective optimization function, generating an optimal damping scheduling instruction, and thoroughly solving the fan asthma phenomenon that the fan PWM duty ratio fluctuates substantially in a sine mode under the constant computing power load.

The invention discloses a command and control system resource trend prediction method based on fusion of long and short time sequence characteristics. The method comprises the following steps: acquiring a public power load or similar time sequence monitoring data set, and preprocessing the data in the data set; a deep learning network model based on a TCN-Transformer hybrid model is constructed, a TCN model and a Transformer model are adopted for parallel computing to achieve feature extraction, the TCN model extracts short-term information, the Transformer model extracts long-term features, then fusion features are obtained through a cross attention mechanism and multi-layer perceptron (MLP) weighting, and finally prediction output is generated through full connection layer mapping. Taking data in the training set as input, training the constructed TCN-Transform hybrid model, and continuously optimizing the model until convergence meets a set requirement; and performing prediction by using the trained network model. According to the method, the TCN-Transform hybrid model is constructed, so that local fine-grained features are reserved, the global time trend is effectively captured, and the accuracy of command decision making is improved.

The invention relates to a mixed scale optimization regulation and control method and device for rural energy and a storage medium, and belongs to the technical field of new energy. According to the method, layered optimization is carried out by establishing a monthly time scale optimization scheduling model, a day-ahead time scale optimization scheduling model and an intra-day time scale optimization scheduling model which are connected with one another, and long-term economic planning and medium-short-term operation scheduling are organically combined, so that multi-target collaboration and multi-energy complementation are realized; specifically, through monthly optimization, an optimal purchase and inventory strategy can be formulated according to seasonal price fluctuation of biomass, the fuel cost is remarkably reduced from the source, and the overall economical efficiency of the system is improved; through a day-ahead gas storage plan and intra-day real-time scheduling, the fluctuation and intermittency of wind energy and solar energy power generation can be effectively stabilized by utilizing the stability and controllability of biomass power generation, and the power load demand can be stably met under various working conditions, so that the stability and reliability of power supply are enhanced, and the energy consumption is reduced. And on-site efficient consumption of rural renewable energy sources is promoted.

The invention discloses an interpretable load prediction method based on knowledge distillation and a time self-attention additive neural network, and the method comprises the steps: collecting the historical load and meteorological data of a power grid as the input characteristics of a model, carrying out the detection of a data quartile abnormal value, dividing the data quartile abnormal value into a training set, a test set and a verification set, and carrying out the detection of the data quartile abnormal value; standardization and abnormal value filling are carried out through Z-shaped orthogonalization and linear filling, and finally, a tensor form meeting the model input requirement is converted through a sliding window; designing a knowledge distillation'teacher-student 'framework based on multiple scales and multiple cycles; constructing a time self-attention additive neural network TSA-NAM as a student model; calculating a shape function representing the contribution degree and the characteristic value in the sub-network to obtain the interpretability of the characteristic dimension; exporting the attention weight of the time self-attention module to obtain the interpretability of the time dimension; performing simulation verification; according to the method, high reliability and high precision are guaranteed, and meanwhile, multi-dimensional interpretability is brought to power load prediction.

The invention discloses a power load prediction method, and the method comprises the steps: firstly solving an extreme event data sparsity problem through a generative adversarial network, and constructing an event time sequence library through a time sequence anomaly detection algorithm; then analyzing the causal relationship between the event and the load by applying a causal discovery algorithm, and converting prediction output into probability distribution by adopting a Bayesian neural network to quantify uncertainty; constructing a prediction model triggered by an event, and generating a multi-time scale probability prediction interval; and finally, generating a multi-scene prediction result through Monte Carlo simulation, quantifying the system recovery capability in combination with a toughness index, and integrating the system recovery capability to a decision support system to generate a risk response scheme. According to the method, the accuracy and robustness of load prediction under the extreme climate are remarkably improved, full-chain risk insight from early warning to recovery is realized, and prospective decision support is provided for safe operation of a power system.

The invention discloses a short-term power load prediction method and system based on a CNN-Transform hybrid model, and the method comprises the steps: carrying out the data collection of historical load data and meteorological data of a power system, carrying out the data preprocessing of the collected data, and carrying out the coding of a periodic time feature, and obtaining periodic time coding information; local space-time features of the load data and the meteorological data are extracted by using a convolutional neural network, and hierarchical expression of the features is realized through a multi-layer convolutional structure during extraction; the local spatiotemporal features and the periodic time coding information are fused to obtain fusion features containing a load sequence, the long-period dependency relationship of the load sequence is modeled through a Transform network, global modeling of the fusion features is achieved through a multi-head self-attention mechanism, and a CNN-Transform hybrid model is obtained; a CNN-Transform hybrid model is used for prediction, and a load prediction result is output; according to the invention, the precision of load prediction and the generalization ability of the model are significantly improved.

The invention relates to the technical field of radiator monitoring, and particularly discloses a radiator heat dissipation performance dynamic test system, which is characterized in that a heat source simulation body is arranged on a heat transfer interface of a radiator, and a high-fidelity dynamic electric power load is applied to the heat source simulation body to simulate an actual working condition; radiating a microwave detection signal to a space where the heat source simulator is located and receiving a multi-path scattering response signal; the three-dimensional dielectric constant dynamic distribution of the heat source simulation body is reconstructed by solving the inverse scattering problem fused with the space-time constraint; according to the material dielectric constant-temperature relation mapping, three-dimensional temperature field dynamic distribution is generated; and finally, intelligently identifying and extracting a migration track and a temperature change curve of the highest temperature point in the space from the continuous time sequence temperature field data, and taking the migration track and the temperature change curve as a direct evaluation basis for the dynamic heat dissipation performance of the radiator. According to the method, lossless, full-field, real-time visualization and quantitative analysis of the migration process of the dynamic hot spots in the hidden heat source are realized, and the authenticity of the dynamic heat test is improved.

The invention discloses a regional power grid new energy consumption method and system based on computing power-power space-time coordination. The method comprises the following steps: acquiring real-time operation state data of a regional power grid and to-be-processed computing power task data of a data center cluster; dividing the computing power task into flexible loads based on the time sensitivity of the task, and determining the energy consumption conversion relation of the flexible loads; on the basis of the real-time operation state and the energy consumption conversion relation, the cross-regional migration amount of the flexible load and the output state of the generator set serve as decision variables, and a cooperative scheduling instruction containing a computing power task cross-regional migration path and generator set power adjustment is generated; and in response to the instruction, the flexible load in the load center area is migrated to the data center for execution in a cross-area manner through the communication network, and the output of the generator set in the corresponding area is synchronously adjusted. The method is used for solving the problems that in the prior art, due to the fact that a physical power transmission channel is limited, new energy power abandoning is serious, and power loads and new energy resources are mismatched in space distribution.

The invention discloses an intelligent scheduling control system for computing power and power load of a data center, and the system obtains key data of computing power and power in real time through a data collection module, thereby helping the system to master the operation state in time. The load evaluation module calculates a comprehensive load value based on the data, comprehensively considers calculation power and electric power dimensions, accurately reflects an actual load, clarifies calculation power demand and electric power supply balance, and avoids misjudgment of single-dimension evaluation; the comprehensive load value is compared with a preset threshold range through a scheduling strategy generation module, a strategy is generated in combination with service priority and computing power resource distribution, actual requirements are met, and the problems that in a traditional mode, consideration on the service priority is insufficient, and flexible scheduling cannot be achieved according to resource distribution are solved; computing power and power distribution are adjusted in real time through the scheduling control module according to a strategy, load changes and service requirements can be quickly responded, efficient operation of the data center is ensured, the resource utilization efficiency is improved, the operation cost is reduced, and the defect that traditional scheduling is difficult to adjust in real time is overcome.

The invention discloses a power load prediction method based on a dynamic expert pool and a load balancing mechanism MoE, and belongs to the field of power load prediction, and the method comprises the following steps: collecting multi-dimensional input data needed by power load prediction, detecting and repairing an abnormal value in the input data, and obtaining a power load prediction result; constructing a time-feature matrix by using the repair data; projecting the time feature matrix into three subspaces of Q, K and V, calculating attention weights among feature dimensions, and obtaining enhanced features through attention weighting; the enhanced features are input into a routing layer of the MoE model, selection probability distribution of experts is calculated, the MoE model adopts a dynamic expert pool and introduces a load balancing mechanism, and a Top-2 expert selection strategy is randomly distributed in the reasoning stage; and when the MoE model is migrated to a new scene, updating the attention weight of the MoE model by adopting a meta-learning strategy. According to the method, complex factors influencing the power load can be comprehensively captured, and the power load prediction precision and the cross-scene adaptive capacity are remarkably improved.

The invention discloses a power load prediction and energy storage optimization control method and system, belongs to the technical field of power system energy storage optimization control, and aims to solve the problems that the reaction is slow, the charging and discharging mode is not optimized enough and the risk of countercurrent cannot be pre-judged in advance due to the fact that reverse power transmission to a power grid is prevented through detection of an anti-countercurrent electric meter in an existing anti-countercurrent method. Based on historical load data, environmental data and time features, a time sequence deep learning model fused with an attention mechanism is utilized to output a future multi-time-scale user net load prediction result in a rolling manner, and whether a grid-connected point power prediction value is smaller than a dynamic countercurrent threshold value or not is judged so as to identify a countercurrent risk. And if the risk exists, establishing a countercurrent avoidance optimization model, otherwise, establishing a conventional scheduling optimization model, performing rolling solution by adopting an efficient solution algorithm to obtain an optimal charging and discharging power instruction sequence, performing electric energy quality evaluation and correction, and then issuing the optimal charging and discharging power instruction sequence to the energy storage converter for execution, thereby realizing pre-judgment of the countercurrent risk in advance and optimization of energy storage charging and discharging behaviors.

The embodiment of the invention discloses a malignant load identification method, device and equipment, a medium and a program product, and relates to the technical field of power load monitoring. The method comprises the following steps: performing modal decomposition on an original power utilization sequential sequence to obtain a plurality of intrinsic mode components, and reconstructing intrinsic mode components which do not belong to noise components to obtain a target power utilization sequential sequence; performing feature extraction on the target power consumption time sequence to obtain target power consumption features, and inputting the target power consumption features into a pre-trained malignant load identification model for identification to obtain an identification result; the malignant load identification model is obtained by updating model parameters of a weak learner based on a natural gradient descent method and performing training optimization. The lightweight malignant load learning model obtained through training in the scheme can be deployed and operated on the intelligent electric meter, high-quality input features are obtained through multi-mode decomposition and reconstruction, the accuracy of malignant load recognition is improved, and accurate recognition of the malignant load based on the lightweight model is achieved.

The invention provides a load prediction and intelligent real-time control system based on hybrid algorithm fusion. Relates to the field of energy storage systems and energy scheduling, and comprises a data acquisition and processing module used for acquiring and preprocessing multi-source heterogeneous data of the energy storage system in multiple scenes to generate a structured time sequence feature set; the multi-source heterogeneous data comprises historical load data, time variables, environmental data, economic data and scene exclusive data; the power load prediction module outputs a load prediction result by integrating two different types of prediction models, and the two prediction models comprise a first prediction model based on historical sequence similarity and a second prediction model based on time decomposition; and the intelligent real-time control module is used for dynamically generating an energy storage system charging and discharging instruction and an energy scheduling strategy through a rolling optimization strategy based on a load prediction result and a preset target function, so that multi-target energy management is realized. According to the invention, the load response capability and prediction control precision of the energy storage system in multiple scenes are improved.

The invention discloses a power load event detection algorithm based on an adaptive window model, and belongs to the field of power detection, and the algorithm comprises the steps: collecting power load total power time sequence data, carrying out the preprocessing, carrying out the rough detection of the preprocessed data, positioning all suspected event points, constructing a composite feature vector, and screening the suspected event points. And eliminating misinformation and repeated event points, and outputting a final power load event detection result. According to the method, the missing detection rate and the false detection rate are greatly reduced, the high recall rate is achieved through the dynamic threshold value and the improved CUSUM algorithm in the coarse detection stage, the load event detection accuracy is improved through composite feature vector and mahalanobis distance screening in the fine detection stage, the false detection rate is reduced, and the method can adapt to different types of loads and different sampling frequency data.

The invention discloses a power load time sequence anomaly detection method and system based on a Mama and LSTM hybrid network, and belongs to the technical field of power system data analysis and artificial intelligence, and the method comprises the steps: inputting the preprocessed power load and related factor time sequence data into a Mama-LSTM hybrid encoder; performing time sequence data reconstruction and anomaly probability prediction in parallel by using depth features output by an encoder, and performing model training by jointly optimizing reconstruction error loss and anomaly detection loss; calculating a comprehensive abnormal score based on the trained model, and judging an abnormal point by adopting a dynamic threshold value; and outputting an anomaly detection result and providing an analysis report containing an unsupervised evaluation index and multi-dimensional visualization. Through deep series fusion of Mama and LSTM, long-term dependence and complex modes in a power load sequence are effectively captured, and the accuracy, robustness and interpretability of anomaly detection are significantly improved in combination with a joint training strategy and an unsupervised evaluation system of the system.

The invention discloses an aliasing power load identification and power decomposition method, system, device and medium, and the method comprises the steps: collecting electrical data containing aliasing signals, carrying out the multi-modal feature extraction, and obtaining a device fingerprint comprising a steady-state power feature, a frequency domain harmonic feature and a statistical behavior feature; constructing an equipment behavior graph based on the fingerprint features, wherein nodes in the graph represent equipment, and edges represent power behavior correlation between the equipment; performing feature aggregation and joint reasoning on the equipment graph by using a graph attention neural network, and outputting an identification result of the target equipment and a single-equipment power estimation value; the classification precision and the power fitting capability are optimized at the same time through a joint loss function guide model; and finally, high-precision identification and power decomposition in a multi-device aliasing state are realized. The method has good anti-interference capability and edge deployment performance, and is suitable for the scenes of distributed power utilization monitoring, non-intrusive load identification, intelligent energy-saving control and the like.

The invention belongs to the technical field of power load monitoring and artificial intelligence crossing, and particularly relates to a user side load non-intrusive identification method and system, and the method comprises the steps: constructing a load feature library of typical electric equipment, and storing a steady-state feature set and a transient feature set of each piece of equipment; extracting user power consumption behavior characteristics, and combining the load characteristic library to synthesize a user power consumption gateway load time sequence data sample through a data generation model; extracting a multi-scale steady state characteristic quantity and a transient state characteristic quantity from the sample, and performing characteristic fusion to form a fusion characteristic vector; inputting the fusion feature vector into a trained load identification model, and outputting the operation state and type of each electric device at the user side; the four core obstacle problems of feature confusion, data scarcity, difficulty in concurrent identification and model stiffness are solved, and the accuracy, robustness and practicability of load identification are remarkably improved.

The invention discloses a power load prediction method and device based on quadratic mode decomposition and double-model parallelism, and a medium, and the method comprises the steps: carrying out the fine decomposition of an original load sequence through a quadratic mode decomposition method, carrying out the denoising and reconstruction through combining with a wavelet threshold method, and finally obtaining a series of stable mode components; in a prediction stage, a parallel prediction architecture of the Informer and the BiLSTM is constructed, all modal components are synchronously input, global long-term dependence is captured by using a multi-head probability sparse self-attention mechanism of the Informer, and local short-term dynamic is captured by using the BiLSTM; and carrying out splicing and nonlinear fusion on the heterogeneous features extracted by the two to obtain a final prediction value. Compared with the prior art, cooperative capture and accurate prediction of the multi-scale features of the non-stationary power load sequence are realized through secondary decomposition from coarse to fine and a targeted double-model parallel architecture.

The invention discloses a computing power load space-time migration regulation and control method and a related device. The method comprises the following steps: acquiring power regulation information required by a power grid frequency modulation service; according to the power regulation information required by the power grid frequency modulation service, constructing a space-time migration characteristic model of a data center computing power load, and calculating the computing power load based on the space-time migration characteristic model of the data center computing power load; constructing an optimization problem by taking the minimum economic cost as an optimization target according to the computing power load capacity, constructing constraint conditions, solving the optimization problem under the constraint conditions to obtain an optimal regulation and control scheme, and carrying out computing power load space-time migration regulation and control according to the optimal regulation and control scheme. According to the method and the related device, the space-time multi-dimensional adjustment potential of the computing power load can be mined for multi-service requirements, the space-time migration regulation and control of the computing power load are improved, and safe and economical operation of a power grid is ensured.

The invention belongs to the field of non-intrusive power load monitoring, and discloses a non-intrusive power load identification method, which comprises the following steps of: constructing a load identification framework utilizing frequency domain characteristics, and aims to solve the problem that transient characteristics cannot be effectively applied in non-linear load identification in non-intrusive load monitoring. A current feature extraction technology based on fast Fourier transform and Hilbert-Huang transform and a classification method based on an extreme learning machine as a main body are used for training and testing a public data set to verify that the method is used for extracting transient load features and identifying nonlinear loads.

The invention discloses a heat supply unit deep peak regulation and heat supply optimization operation method based on multi-mode collaboration, and particularly relates to the technical field of thermal power generation and heat supply, and the method comprises the steps of S1, system modeling and parameter identification, S2, thermoelectric load prediction, S3, multi-objective optimization solution, S4, operation decision and feedback, and S5, data agent mapping acceleration. According to the method, the thermoelectric load is accurately predicted through mechanism and data dual-drive modeling, and based on the target of maximizing the economic benefits of the whole plant, the optimal cooperation scheme of multiple operation modes such as heat supply, power supply and deep peak regulation is dynamically solved by utilizing the multi-target optimization algorithm on the premise of ensuring the safety of the unit, so that the power supply efficiency is improved. Finally, production is guided through an online decision-making and closed-loop feedback system, and safe, economical and flexible operation of the unit under the working condition of deep peak regulation is achieved.

The invention discloses an electric power and computing power coordinated regulation and control method and system, and relates to the field of load regulation and control, and the method comprises the steps: obtaining the electric power data of a power generation side and the electric power data of a computing power center, inputting the electric power data into a preset multi-target coordinated optimization algorithm, and obtaining the power generation and consumption data of a target time period meeting the requirements of the minimum power consumption cost and the maximum green power consumption, load distribution parameters are generated in combination with load demand data of the computing power center, and power generation and utilization loads of a computing task, computing power equipment, refrigeration equipment, a power generation side and the like of the computing power center are accurately controlled in a target time period. Through collaborative optimization of the power generation side and the computing power center, the green power intermittency and the computing power load fluctuation are effectively balanced, the green power consumption rate is improved, the power consumption cost of the computing power center is reduced, and the power supply and computing power operation stability is guaranteed.

The invention discloses a communication power supply load measurement and calculation and air switch control method and system based on service priority, and relates to the technical field of communication power supply intelligent management. Comprising the following steps: initializing and acquiring a load service priority list and a time threshold; monitoring an AC input state, switching to a standby power supply mode when the AC input state fails, and recording a power-off moment; a hybrid algorithm of ampere-hour integration and dynamic voltage calibration is adopted to measure the residual capacity of the storage battery in real time and with high precision, and residual power supply time is dynamically predicted; when the waiting time exceeds a first threshold value and the remaining power supply time is smaller than a second safety threshold value, a turn-off instruction is generated; and dynamically generating a turn-off sequence from low to high according to the service priority list, and iteratively executing turn-off and state re-evaluation until the endurance safety requirement of the core service is met. According to the invention, the problems of low control precision, incapability of distinguishing service priorities and low resource utilization rate in the prior art are solved, and accurate, intelligent and service-aware power management is realized.

The invention relates to the technical field of power supply, and discloses a humanoid robot modular distributed power supply system which comprises a power supply battery pack, a power management distribution board and a plurality of power utilization modules. The power utilization module at least comprises a control computing power unit, a sensing system, an upper limb joint module, a lower limb joint module and other joint modules; the power management distribution board is electrically connected with the power supply battery pack and each power utilization module. The power management distribution board comprises an MCU control unit, a DCDC power supply unit, a soft start unit, a high-power output unit and a voltage and current detection unit. Through a modular distributed power-on strategy and in combination with soft start pre-charging, voltage and current real-time detection and a regenerative braking absorption unit, voltage and current peaks generated at the moment of power-on of the capacitive high-power load are remarkably suppressed, the risk that a power device is damaged due to overvoltage and overcurrent impact is fundamentally avoided, and the reliability of the power device is improved. And the system reliability and the service life are greatly improved.

The invention discloses a power control method of an electric power system for polyester staple fiber production, and relates to the technical field of industrial power load cooperative control, and the method comprises the steps: collecting real-time process parameters and power grid state parameters of each energy consumption section, and calculating the expected basic power demand of each section through a section power consumption prediction model; and in combination with a power fluctuation range predicted by the power grid load fluctuation analysis model, a multi-target dynamic power distribution optimization equation is constructed for solving, so that a target set power value of each workshop section and a total regulation power instruction of the system are obtained. And the section level is adjusted to the variable frequency driver and the heating controller based on the instruction, and the energy storage unit or the standby unit is controlled to act. The method achieves the real-time precise prediction of the power demand of each workshop section, enables the total load of the system to actively cooperate with the fluctuation requirement of the power grid through dynamic optimization distribution, effectively guarantees the stability of the production technology, and improves the energy utilization efficiency and the response capability of the power grid.

The invention relates to the technical field of power systems, and discloses a regional electrical load prediction method based on periodic features and related equipment, and the method comprises the steps: constructing a multivariate feature data set; performing architecture adjustment on a preset basic prediction model based on the periodic characteristics of the electrical load of each region; training the adjusted prediction model according to the multivariate feature set to obtain an electrical load prediction model corresponding to each region; and when an electrical load prediction request for the target area is received, predicting the electrical load of the target area based on the electrical load prediction request and an electrical load prediction model. According to the invention, the problem of low accuracy of a current electrical load prediction scheme can be solved.

The invention discloses a split-phase anti-countercurrent control method and system for a three-phase inverter. The method comprises the following steps: acquiring output power, load power and grid-connected power of each phase of the three-phase inverter in real time; for each phase, calculating the difference between the load power and the output power, if the difference is less than or equal to 0, judging that the phase has countercurrent, and performing corresponding split-phase control; and if the difference is greater than 0, judging that the phase has a countercurrent trend, and carrying out corresponding split-phase control.

The invention relates to the technical field of block chains, and discloses a power load prediction system based on artificial intelligence, and the system comprises a data collection module which is used for collecting historical load data, real-time meteorological data, calendar information, and power grid event data; the data storage module is used for performing partition storage on the historical load data, the real-time meteorological data, the calendar information and the power grid event data in the parallel chain to obtain a partition storage result; the feature fusion module is used for performing federal feature extraction on the partition storage result in the parallel chain to obtain federal features and fusing all the federal features; the load prediction module is used for outputting a predicted power load corresponding to the space-time fusion feature through a hybrid expert model; and the load calibration module is used for generating an attribution auxiliary index of the predicted power load and calibrating the predicted power load into the final power load by using the attribution auxiliary index. According to the invention, a new-generation prediction framework considering data security, feature fusion and interpretability can be provided.