801 results about "Energy scheduling" patented technology

The invention provides an energy digitization platform resource scheduling method based on cloud edge cooperative computing, which comprises the following steps: acquiring real-time supply and demand data, an energy price signal and network topology information from a distributed energy management system, and preprocessing to obtain a structured dynamic supply and demand scene data set meeting a unified format requirement; aiming at a dynamic supply and demand scene data set, respectively detecting the fluctuation frequency and amplitude of an energy price on different time scales by adopting a time sequence analysis method, detecting the change condition of a network topology structure in real time by adopting a network analysis technology, and extracting key parameters reflecting scene dynamic characteristics from the change condition; and extracting a scheduling demand of cross-regional energy flow from the adjusted edge node permission configuration, and optimizing a cross-regional energy flow path in combination with real-time inter-regional supply and demand difference data and network state evaluation to obtain a globally optimized cross-regional energy scheduling scheme.

The invention relates to the technical field of micro-grid energy optimization, in particular to a distributed federal reinforcement learning-based hydrogen-containing micro-grid energy scheduling method, which comprises the steps of constructing a multi-region hydrogen-containing micro-grid system model, designing a state space, an action space and a reward function of an intelligent agent, constructing an Actor-Critic network and an experience pool, and completing environment initialization. The intelligent agent inputs the operation state of the equipment into the Actor network, updates the state of the equipment according to the output action, verifies the constraint and outputs a reward value; tuples are extracted from the experience pool to update local network parameters, and the exploration rate is updated regularly; when a federation interaction period is reached, exchanging Critic network parameters and updating federation parameters; and when the training round arrives, outputting an equipment operation plan, deploying the model to the local hydrogen-containing micro-grid in the island mode, and outputting an equipment output value. According to the scheme, strategy sharing and learning collaboration are realized through neighborhood collaboration and local communication among the regional intelligent agents, so that dependence on a central node is avoided.

The invention relates to the field of new energy technology and power electronics, and discloses a photovoltaic diesel generator energy storage hybrid off-grid and grid-connected household energy storage system, which comprises a data acquisition and state monitoring module for acquiring photovoltaic, diesel generator, energy storage, load and commercial power states in real time and generating system state parameters; the central control and decision module generates a control strategy containing an operation mode and an energy scheduling instruction; the energy flow and conversion execution module executes energy conversion and flow; the seamless switching control module realizes non-impact switching between modes; the self-adaptive safety protection module dynamically adjusts protection parameters; and the emergency response and recovery module executes black start and active recovery in an emergency state. According to the invention, through the unified central control and decision-making module, photovoltaic, diesel generator, energy storage and commercial power scheduling logics are integrated to form a collaborative energy management core, and the system can carry out global optimization on energy flow in grid-connected and off-grid modes according to a preset priority principle.

The invention relates to the technical field of computer systems based on specific calculation models, and discloses a control method and system for an intelligent calculation center comprehensive energy supply device, and the method comprises the steps: collecting the operation data of energy supply equipment and an environment sensor in real time through an SCADA system, and carrying out the preprocessing; based on the collected data and simulation data generated by a simulation environment, performing offline mixed training on the reinforcement learning model to generate an energy scheduling strategy; inputting a real-time state into the trained reinforcement learning model to generate a preliminary scheduling instruction, performing security verification and interpretability analysis by using a large language model, and optimizing a strategy; and fusing the preliminary scheduling instruction with the suggestion of the large language model, generating a final scheduling command through the energy router control unit, and issuing the final scheduling command to the energy supply equipment for execution. The problems that in the prior art, black box decision making and simulation are not accurate, and experience is difficult to solidify are solved, and the purposes of decision making transparency, simulation high fidelity and experience structuring are achieved.

The invention discloses a power grid dispatching method based on emergencies and a graph structure. The method comprises the following steps: establishing a baseline load prediction model by collecting historical electrical load data; recognizing emergencies influencing the power utilization demand in real time; and in combination with real-time power consumption behavior data, constructing a time-varying power consumption disturbance factor, and dynamically correcting load prediction. Geographic distribution and historical power generation data of new energy power stations such as wind power and photovoltaic power stations are acquired, a power generation graph structure model is constructed, the power generation amount is independently predicted by adopting a long-short-term memory network, and a prediction result is corrected in combination with a graph structure. And based on the corrected load and power generation prediction, considering the capacity and the energy state of the energy storage system, optimizing multi-time-sequence-scale energy scheduling, and formulating an energy storage charging and discharging and generator set operation scheme. According to the method, the dynamic influence of emergencies and the spatial relevance of new energy are fused, the load prediction precision and the new energy power generation prediction accuracy are remarkably improved, more reasonable power grid dispatching is achieved, and the safety and stability of a power grid are enhanced.

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 a fused salt heat storage and Carnot cell combined coal-fired unit peak-load regulation operation method, device and equipment, a medium and a product, and relates to the field of unit peak-load regulation operation. Acquiring information data; based on a power regulation demand prediction model, performing peak regulation demand prediction according to the information data to obtain a prediction result; the power regulation demand prediction model is obtained by adopting a multi-objective optimization model and performing time sequence analysis on a long-short-term memory network model; determining an energy scheduling strategy based on the prediction result; the energy scheduling strategy comprises a heat storage power coordination instruction and a heat release power coordination instruction; and according to the energy scheduling strategy, operation adjustment is conducted on the coal-fired unit, the fused salt heat storage subsystem and the Carnot battery subsystem based on the control system. The invention aims to improve the peak regulation performance of the coal-fired unit.

According to the electrical ship optimal scheduling strategy optimization method and related equipment provided by the embodiment of the invention, an electrical ship comprises a photovoltaic module, a plurality of generator sets and a battery energy storage system, and the method comprises the steps of obtaining a photovoltaic power function of the photovoltaic module based on operating environment parameters of the electrical ship in a sailing process; based on the generator set parameter of each generator set, the system state parameter of the battery energy storage system and the charging cost and the charging parameter of the electric ship at the port, obtaining an operation cost function; based on the sailing state parameters of the electric ship, the system operation parameters of the battery energy storage system and the photovoltaic power function, sailing scheduling constraints and energy scheduling constraints are obtained; based on the uncertainty of the photovoltaic power function and the charging cost, generating an uncertainty operation cost optimization model according to the operation cost function, the navigation scheduling constraint and the energy scheduling constraint; and the uncertainty operation cost optimization model is solved, an optimization decision is obtained, and the overall economy of the whole voyage of the electric ship is remarkably improved.

The invention discloses an intelligent operation and maintenance method and system for an energy management platform, and relates to the technical field of intelligent operation and maintenance, and the method comprises the steps: analyzing data through employing an NLP technology, generating a multi-objective optimization function, constructing a user behavior portrait, adjusting the weight parameters of the multi-objective function through employing a reinforcement learning algorithm in combination with an Actor strategy network, and carrying out the operation and maintenance of a user. An energy scheduling scheme is obtained by using an improved bald eagle search algorithm and a prey escape energy mechanism, a digital twinborn model of mapping of a physical space and a virtual space is constructed, and the energy scheduling scheme is optimized and implemented by combining the digital twinborn model with a soft constraint mechanism. Through fusion of NLP technology semantic analysis and a reinforcement learning algorithm, a multi-target scheduling strategy is dynamically optimized, and an improved bald eagle search algorithm and a digital twin model are combined to realize simulation verification and closed-loop feedback, so that the intelligence and optimization level of energy system operation is improved, and the stability, economy and low-carbon operation capability of the system are also improved.

The invention provides a smart city construction energy intelligent management scheduling regulation and control system, and relates to the field of energy intelligent management, comprising the following steps: the system detects energy physical parameters in real time through an event chain generation module, maps data into event nodes by using an event feature extraction chip, and sends the event nodes to a cloud server; an event chain topology is constructed through a causal association engine, and a nonlinear priority is generated; the responsibility collaboration module creates a scheduling instruction and a responsibility node based on the priority, calculates a responsibility weight through a reverse causal tracing algorithm, triggers cross-system permission degradation when the weight exceeds a threshold, and migrates the operation permission to an associated system; the paradox enhancement module injects controllable disturbance when the event chain conflicts or the responsibility nodes continuously exceed the limit, the disturbance effect is evaluated through the paradox index, the event chain topology is fed back and updated, and dynamic optimization and hidden risk prevention and control of energy dispatching are achieved.

The invention discloses an energy scheduling method, system and device for a low-earth-orbit satellite and a medium. The method comprises the steps that the energy storage level is calculated according to the current generation power of the low-earth-orbit satellite, the current remaining electric quantity of an energy storage unit and the health degree of a battery; generating a future illumination time sequence according to the orbit parameters of the low-orbit satellite and the satellite attitude control data; according to the current operation state data of each device loaded on the low earth orbit satellite and a preset task list, generating corresponding task prediction energy consumption data arranged in a descending order according to the importance level through a historical energy consumption model; according to the energy storage level, the future illumination time sequence and the task prediction energy consumption data, calculating the dominant power supply amount, matching the energy consumption demand in the task prediction energy consumption data, and carrying out the preferential power supply of the equipment of the task item with the high importance level. And carrying out power supply adjustment on the other equipment by adopting at least one strategy of delaying to the illumination period, reducing the operation power and shortening the operation duration so as to realize efficient scheduling on the energy of the low-orbit satellite.

The invention relates to the technical field of power grid collaborative optimization, in particular to a state grid provincial multi-level scheduling operation solving method based on collaborative standby, which comprises the following steps: establishing a multi-level scheduling model considering collaborative standby constraint according to each level objective function participating in trans-provincial energy scheduling and standby scheduling; based on an augmented Lagrangian relaxation method, decomposing the multi-level scheduling model into sub-problems of a national scheduling level, a network scheduling level and a provincial scheduling level; and performing cooperative solution on each sub-problem by using a target cascade method to obtain a global optimal scheduling scheme. According to the state-grid-province multi-level scheduling operation solving method provided by the invention, a reference can be provided for exploring a state-grid-province multi-level cooperative scheduling mode by constructing a state-grid-province multi-level scheduling model considering a cooperative standby mechanism; besides, solving is carried out by adopting a target cascading method, actual and internal mechanisms of the power grid under each level are considered, and the power system optimization scheduling solving efficiency under whole-grid cooperation is also improved.

The invention discloses an intelligent data center energy scheduling optimization method based on machine learning. The method comprises the following steps: acquiring data to form a multivariable time sequence; the improved PatchTST model calls a multi-level memory interaction structure to establish short-term memory and long-term memory, and an attention constraint energy consumption memory module is introduced to output prediction features; inputting the prediction features into a decoding layer of the improved PatchTST model; constructing an energy scheduling multi-objective optimization problem, and generating an equipment control instruction set by adopting an NSGA-III algorithm; collecting an actual execution result to form feedback data; performing deviation evaluation and strategy updating on feedback data through an energy self-feedback correction process; and judging whether the energy consumption prediction error and the energy scheduling deviation meet a preset termination condition or not. The method is suitable for intelligent energy scheduling and operation efficiency optimization in multi-energy coupling scenes such as an intelligent data center.

The invention discloses a super-large plane array type space computing power center, and belongs to the field of space technologies and space infrastructures. The space computing power center is deployed in a morning and evening orbit and comprises a plurality of computing power satellites which are physically docked in orbit through a docking mechanism. Each computing power satellite comprises a satellite platform, and a computing power load, a condensation type energy system and a space pump drive fluid loop system which are arranged on the satellite platform, and a docking mechanism for inter-satellite in-orbit physical docking is also assembled on the satellite platform. A plurality of computing power satellites form a planar array type rigid whole body through the docking mechanism, and energy scheduling among the light condensation type energy systems is realized based on the docking mechanism. According to the space computing power center, through multi-satellite physical docking and energy collaborative scheduling, the energy utilization efficiency and the power supply reliability of the system are improved.

The invention discloses a dynamic signal synchronization control method and system for an energy scheduling network, and relates to the technical field of dynamic signal control, and the method comprises the steps: carrying out the analysis and disassembly of the energy scheduling network, and determining signal transmission delay data and signal transmission error data; configuring a first energy distribution vector; configuring a second energy distribution vector; fusing the first energy distribution vector and the second energy distribution vector, and configuring a regulation and control strategy matrix of an energy stable distribution level and a signal synchronization correction parameter; and performing multi-node cooperative control, and feeding back a regulation and control effect to the coordinated optimization network to iteratively optimize the attention weight. According to the invention, the technical problems of poor network coordination and weak anti-interference capability caused by low signal synchronization precision and unstable distribution of the energy scheduling network in the prior art are solved, and the technical effects of realizing dynamic synchronization and stable distribution of the signals in the energy scheduling network and improving the coordination and anti-interference capability of the network are achieved.

The invention belongs to the technical field of load prediction, and discloses an off-grid micro-grid system load prediction method and system based on a neural network. The method comprises the following steps: constructing an equipment fault diagnosis model, an energy scheduling model and a load prediction model by using a neural network algorithm; carrying out data acquisition and preprocessing to obtain preprocessed real-time area monitoring data; performing equipment fault diagnosis by using the equipment fault diagnosis model; if the real-time equipment fault diagnosis result is that a fault exists, entering an energy scheduling step, otherwise, entering a load prediction step; performing energy scheduling by using the energy scheduling model, executing the obtained real-time energy scheduling scheme, and returning to the data acquisition step; and performing load prediction by using the load prediction model. According to the method, the problems of data island, insufficient model generalization ability, limited fault diagnosis precision and efficiency, insufficient energy scheduling strategy optimization and poor load prediction precision and robustness in the prior art are solved.

The invention provides an energy storage equipment management method and system based on the Internet of Things, and relates to the technical field of energy storage management, and the method comprises the steps: determining an energy scheduling target node and a node interaction strategy through a block chain network according to the real-time operation data of energy storage equipment collected by an Internet of Things platform, and generating a decentralized scheduling instruction; docking a target node edge calculation unit according to the instruction, and outputting network configuration parameters; global state monitoring is carried out through an end-edge-cloud collaborative architecture, and data of charging and discharging abnormity of a physical layer and communication abnormity of a service layer are acquired; generating an exception handling strategy based on an adaptive deep reinforcement learning model, recalculating an energy scheduling target node, forming a closed-loop control instruction, and feeding back the closed-loop control instruction to the block chain network; according to the invention, processing delay easily caused by dependence on a master-slave block chain structure in a shared energy storage scene is avoided; the adaptability to the dynamic environment is enhanced, the sudden electricity price change or equipment abnormity is handled through automatic adjustment, and the effect of decision making in the complex power grid environment is improved.

The invention discloses a heating furnace group control system and method based on the Internet of Things, and relates to the technical field of industrial Internet of Things heating furnace control. The adaptive edge calculation module fuses algorithm processing data and reduces response delay; the dynamic thermal efficiency optimization module predicts and improves thermal efficiency; the digital twinborn decision support module realizes fault prediction; the collaborative energy scheduling module optimizes multi-furnace operation; the block chain security management module guarantees data security; and the cognitive interaction interface module realizes multi-modal interaction, and the system also comprises extension modules such as a multi-scale combustion optimization module and the like, so that accurate control and intelligent management are realized. According to the invention, accurate acquisition and real-time processing of multi-dimensional data of the heating furnace group are realized, the heat efficiency is improved, and energy consumption and emission are reduced; the system has the capabilities of fault prediction, cooperative scheduling and data security guarantee; and the man-machine interaction experience is improved, the production efficiency is improved, and intelligent upgrading of industrial heating is promoted.

The invention belongs to the technical field of power system optimization scheduling, and discloses an intelligent port logistics energy scheduling method based on multi-modal digital twinning, and the method specifically comprises the following steps: obtaining collected multi-modal perception data of a port operation scene; processing the multi-modal perception data through an evolutionary reinforcement learning-based target detection algorithm, and obtaining optimized target detection information in combination with a spatial semantic attention mechanism; performing multi-modal fusion on the target detection information and the multi-modal perception data to generate a port global situation semantic vector; constructing a multi-granularity digital twin model based on the semantic vector, and performing simulation prediction; generating a cooperative scheduling strategy of the logistics and energy system according to the simulation result; according to the method, the problems of insufficient multi-modal perception fusion, lack of logistics energy collaborative optimization and insufficient simulation modeling precision in the prior art are effectively solved by combining a target detection algorithm based on evolutionary reinforcement learning with a spatial semantic attention mechanism.

The invention discloses an energy digital management method and system, and the method comprises the steps: receiving a multi-source heterogeneous energy data collection signal, and generating an initial energy characteristic spectrum based on a space-time correlation feature extraction algorithm; performing graph neural network coding on the initial energy feature graph, constructing an energy knowledge graph vector set, and decomposing a high-dimensional vector in the knowledge graph vector set into a plurality of subspace vectors; performing real-time scheduling decision on the subspace vectors by using an energy flow optimization model driven by reinforcement learning to generate an energy distribution strategy set; a digital twinborn verification algorithm is applied to the energy distribution strategy set, physical-digital space consistency verification is carried out, and a trusted energy scheduling scheme is generated; and performing block chain evidence storage and intelligent contract execution on the credible energy scheduling scheme to generate a non-tampering energy transaction record. By utilizing the embodiment of the invention, the scheduling precision and the response speed of the energy system can be improved, and full-link credible management from decision-making to execution is realized.

The invention discloses a time prediction method and system based on double-domain feature fusion. The method and system adapt to long and short term time series prediction requirements of multiple scenes such as weather forecast, energy scheduling, traffic flow and financial exchange rate. The method comprises the steps that a multi-field data set is obtained and preprocessed, and instance normalization is carried out; performing double-domain multi-scale characteristic decomposition by adopting down-sampling and discrete wavelet transform to obtain continuous trend and high-frequency mutation details; a local unit is obtained through patch cutting and embedding, local time sequence association is mined through depth separable convolution, cross-patch global interaction is achieved in combination with a multi-layer perceptron, and local-to-global progressive fusion is completed; and constructing bidirectional attention flow enhanced cross-domain and cross-scale collaboration, and combining with standardized data training to obtain a prediction model. According to the invention, the method can improve the depiction capability of non-stable and non-linear complex time sequence data containing abrupt change and multi-period superposition, gives consideration to the adaptability of long and short term prediction, remarkably improves the accuracy of multi-field time sequence prediction, and promotes the application of the prediction technology in multiple scenes.

The invention discloses a zero-carbon park-oriented multi-energy transformer power mutual aid system, and relates to the technical field of transformer equipment, and the system comprises the following steps: S1, carrying out response demand analysis based on a time dimension; s2, constructing a response adaptation degree model; s3, constructing a scheduling sorting function, and generating an energy scheduling priority sequence; s4, constructing an actual adjustment output function, and outputting actual output power; s5, executing system-level power balance detection, and judging whether the power supply requirement of the park is met or not; and S6, performing short-time gain or peak clipping processing on the single energy through the local adjustment function. According to the method, a full-process mutual aid mechanism from load behavior modeling, energy adaptation evaluation, dynamic optimal sequence regulation and control to disturbance correction is constructed by adopting a multi-step coupling control mode. Through linkage adjustment of the optimal sequence regulation and control module and the disturbance correction module, millisecond-level response and redundant resource rapid compensation are realized, and the system operation stability and the energy utilization efficiency are remarkably improved.

The invention discloses a power distribution network coordination control method considering a distributed power supply and a related device, and belongs to a new energy power distribution network regulation and control technology, the method comprises the following steps: establishing a power distribution network state space equation comprising distributed power supply output and control event identification, and reflecting a power grid operation state in real time; generating a dynamic security constraint based on the state vector and the topological structure of the power distribution network by using a pre-trained constraint prediction model; the power distribution network is partitioned, the state vector of each partition is extracted, a partition control strategy is generated according to the partition state and the dynamic security constraint, and local optimal control over an inverter and an energy storage system is achieved; according to the method, all partition control strategies are fused in a global feasible region, a global control strategy is generated, coordination and consistency of partition control are achieved, distributed power supply and load changes can be dynamically responded, the safety, stability and energy scheduling efficiency of a power distribution network are improved, and the method is suitable for a large-scale distributed energy access scene.

The invention relates to the technical field of sewage treatment process control, in particular to a sewage treatment process control system and device based on a multi-scale time sequence diagram neural network, and the system comprises an energy consumption digital twin modeling module which constructs a whole-process equipment energy consumption and process state twin mapping model; the energy consumption trend prediction module captures three-level energy consumption association by using a multi-scale time sequence diagram neural network based on the model data to obtain a prediction result; the multi-objective optimization module constructs an optimization function containing total energy consumption and the like according to the total energy consumption and the like to obtain a balance strategy; the process self-adaptive regulation and control module adjusts process parameters and data updating network according to the inlet water quality and the optimization target; and the energy scheduling optimization module constructs a model containing peak and valley electricity price perception and outputs a scheduling result. By designing a multi-objective optimization framework and combining water quality adaptive adjustment process parameters and a peak-valley electricity price sensing mechanism, global energy consumption collaborative optimization of the sewage treatment plant can be realized, the energy utilization efficiency can be improved, the operation cost can be reduced, carbon emission can be reduced, and efficient green treatment can be realized.

The invention belongs to the technical field of power grid energy scheduling, and particularly relates to an eVTOL energy station scheduling method based on a micro-grid, which comprises the steps of data acquisition and preprocessing, prediction module setting, scheduling target setting, optimal scheduling strategy generation and real-time adjustment. For distributed power supply output, an ARIMA and LSTM double-layer architecture is adopted to capture short-term sudden fluctuation and medium and long term trend, task randomness is optimized and adapted for eVTOL charging load through individual behavior prediction and group aggregation, and prediction deviation is dynamically corrected in combination with real-time data. According to the method, the output prediction error of the distributed power supply is reduced, the eVTOL charging load prediction error is controlled within 15%, the effect of providing an accurate prospective basis for a subsequent scheduling strategy is achieved, and the micro-grid stability problem and eVTOL task delay caused by supply and demand mismatching are reduced from the source.

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 multi-energy microgrid dynamic balance control and energy scheduling method and system. The multi-energy micro-grid dynamic balance control and energy scheduling method comprises the following steps: establishing a dynamic electric and thermal load prediction model of a rotary hearth furnace; a multi-energy micro-grid framework containing biomass power generation, photovoltaic power generation, gas turbine combined cooling heating and power generation, flue gas waste heat power generation and energy storage is constructed; establishing a system dynamic balance model and a multi-objective optimization framework considering production process constraints; designing a hierarchical dynamic balance joint control strategy; and scheduling by adopting a multi-time scale optimization algorithm. Through multi-energy complementation, waste heat gradient utilization and intelligent optimization scheduling, economical, reliable, low-carbon and efficient operation of energy supply of the rotary hearth furnace is achieved, comprehensive energy consumption and carbon emission are remarkably reduced, and an effective solution is provided for green low-carbon transformation of a high-energy-consumption industrial process.

The invention discloses a park load prediction and energy scheduling method and system based on AI reasoning. The method comprises the steps that minute-level power load data, second-level equipment state data, minute-level meteorological data and user behavior data in a park are collected through intelligent terminal layer equipment; in the edge reasoning layer, according to minute-level power load data, second-level equipment state data, minute-level meteorological data and user behavior data, a lightweight GNN-LSTM hybrid model is adopted to carry out ultra-short-term load prediction, and an isolated forest algorithm is adopted to calculate and detect a load sudden change point in real time; fusing edge side data, historical data, meteorological prediction data and electricity price signal data at a cloud decision-making layer, performing multi-time scale feature extraction and multi-modal data fusion by adopting a TFT-GNN fusion model, generating a short-term load prediction curve, and generating an optimized energy scheduling strategy based on a reinforcement learning algorithm, thereby achieving the optimal energy scheduling. And multi-source data fusion, high-precision power load prediction and real-time dynamic collaborative energy scheduling are carried out on the park.

The invention relates to the technical field of virtual power plants, and discloses a virtual power plant load prediction and optimization control method, which comprises the following steps: obtaining historical operation load data of a virtual power plant for characteristic decomposition to obtain a trend component, a seasonal component and a residual component, inputting the trend component, the seasonal component and the residual component into a load prediction model based on LSTM (Long Short Term Memory), and obtaining a load prediction value in a future set time period; calculating theoretical output of renewable energy sources to determine supply and demand conditions of energy supply and load prediction values; controlling energy storage charging or discharging and controlling the fossil fuel generator set to be started or stopped by combining the peak and valley conditions of the load prediction value; actual operation data of the virtual power plant are collected in real time, deviation meeting the predicted value is compared, and the energy storage charging and discharging strategy and the fossil fuel generator set output strategy are adjusted. According to the method, by accurately capturing load characteristics and cooperatively optimizing a multi-energy scheduling and dynamic adjustment mechanism, the operation stability and economy of the virtual power plant are improved, the energy waste is reduced, and the adaptability to a power system is enhanced.

The invention relates to the technical field of offshore wind turbine generators, in particular to a method and system for providing emergency power supply for a wind power generation system through an ocean energy power generation system, electronic equipment, a storage medium and a monitoring system. The invention discloses an emergency power supply method, a wind power generation system is provided with an energy storage backup power supply module and an electric energy access and switching control module, and communication connection is configured between an ocean energy power generation system and a main control system of the wind power generation system. When the high-voltage side of the wind power generation system is powered off or the power grid is interrupted, the main control system judges whether the energy storage backup power supply needs to supplement electric energy; if yes, the ocean energy power generation system is started to charge the system; if not, the energy storage module supplies power to the control system; when the energy storage module fails, the ocean energy system is controlled to directly supply power to the control system; and energy scheduling, state monitoring and remote control are realized through communication connection, so that the power supply reliability and the operation safety of the system under extreme working conditions are improved.