111 results about "Energy scheduling" patented technology

The application discloses a power-hydrogen-doped gas network combined scheduling method and relates to the field of energy scheduling. The application proposes a power and hydrogen-doped gas network combined scheduling framework based on graph neural network embedding optimization. Firstly, the hydrogen doping ratio in the pipe network is accurately modeled based on the graph neural network, and then the graph neural network inference process is equivalently embedded in the optimization problem, so that the energy scheduling decision can accurately and efficiently consider the hydrogen doping ratio. The application can improve the decision quality of the combined scheduling operation of the power grid-hydrogen-doped gas pipe network system, thereby improving the safety and economy of the operation, and can be deployed and migrated in batches at low cost.

The application discloses an off-grid renewable energy hydrogen storage and target compound synthesis system, method and electronic device, relates to the technical field of renewable energy, and comprises a renewable energy power generation unit, a water electrolysis hydrogen production unit, a fuel cell unit, a hydrogen storage unit, a target compound synthesis unit and a comprehensive energy scheduling unit which are connected with each other. When the corresponding relationship between power generation power and time is less than or equal to the rated power, the fuel cell unit is controlled to be in a starting state, the water electrolysis hydrogen production unit is controlled to produce hydrogen by being turned on, and the target compound synthesis unit is controlled to synthesize target compounds. When the stability of the comprehensive energy scheduling unit does not satisfy a preset stability condition, the fuel cell unit is controlled to be in the starting state, and the corresponding device in the comprehensive energy scheduling unit which does not satisfy the preset stability condition is in a closed state.

This invention discloses a machine learning-based method for optimizing a low-carbon energy supply chain, comprising the following steps: collecting multi-source operational data and normalizing it to form a standardized operational dataset; predicting key operational quantities for future scheduling cycles in chronological order to form a system state description; defining the state set and action set in an improved Resource Management Platform (RMDP) to obtain a complete RMDP decision framework; statistically analyzing historical state transition characteristics to construct an uncertain transition probability set for the improved RMDP; under the improved RMDP decision framework, selecting corresponding actions according to a two-layer robust value update rule to form a robust scheduling strategy; adjusting the robust scheduling strategy to obtain a convergent robust low-carbon energy supply chain scheduling strategy; and during actual operation, invoking the robust scheduling strategy according to the scheduling cycle to generate energy scheduling schemes and carbon asset allocation schemes. This invention achieves low-carbon energy supply chain optimization.

This invention provides a data center scheduling method, system, and medium considering flexible resources, relating to the field of energy scheduling optimization technology. The method includes: establishing a comprehensive energy system equipment model including the energy flow and / or energy storage status of each device; establishing a computing task model and a thermal inertia model for the data center; establishing a scheduling optimization model based on the equipment model, computing task model, and thermal inertia model; the optimization objectives of the scheduling optimization model include minimizing the total operating cost of the comprehensive energy system and maximizing the data center service quality index; establishing constraints for the scheduling optimization model based on energy balance constraints, energy equipment operation constraints, computing task execution constraints, and upper and lower limits of server utilization constraints, and then solving the scheduling optimization model to obtain a scheduling scheme for energy equipment operation and computing task execution. This invention can optimize energy and computing task scheduling by combining the flexible resources of the data center while ensuring reliable operation.

This invention belongs to the field of energy simulation technology and relates to an energy flow network simulation system and method for steel enterprises. It includes: a system configuration module for configuring parameters based on user-inputted information and forming a structured configuration data package; a front-end operation module for configuring a visual interactive interface based on the configuration data package; generating a Gantt chart based on pre-set production and maintenance plans; and drawing a dynamic energy flow diagram based on user-defined equipment and energy nodes; and a back-end service module for calculating energy prediction results based on the Gantt chart, dynamic energy flow diagram, and configuration data package using a pre-set production and consumption model, and performing scheduling optimization when energy prediction results are unbalanced to obtain an energy scheduling balance result. This invention achieves collaborative simulation of production and energy, more intuitively displays the energy balance process, provides a more comprehensive simulation platform for the steel industry, and facilitates systematic management by enterprises.

The application discloses a photovoltaic energy storage charging and discharging intelligent micro-grid system suitable for a smart rail station and a control method thereof, relates to the technical field of urban rail transit power supply and distributed energy utilization, and adopts a top pantograph and a vehicle-side interface shared high-voltage direct-current bus topology, an energy scheduling strategy based on a train operation plan and a battery state driving, and a hierarchical load power distribution and emergency power supply logic, so that multi-mode coordinated operation among photovoltaic power generation, energy storage, a smart rail vehicle and a power grid is realized, while ensuring that a train departs according to a diagram and the safety of power supply of key equipment, unified monitoring and accounting of station energy carbon data are completed.

The application relates to the technical field of energy storage scheduling, and provides an energy scheduling system and method of an energy storage system, which quantifies a probability distribution of state data through a fusion module, constructs a risk system based on the probability distribution, and generates a decision feasible region to provide a constraint basis for a scheduling strategy; a scheduling module constructs a target function by using an uncertainty boundary of the decision feasible region and a weighted expected value of the risk system, solves the target function through a deep deterministic policy algorithm, and outputs an initial scheduling strategy; a pre-play module realizes pre-play of an execution track of the initial scheduling strategy within a time window, compares the execution track with a safety boundary, and ensures actual feasibility and safety of the scheduling instruction; and a feedback module analyzes a time sequence deviation between an actual response track and the execution track, dynamically adjusts the target function and the safety boundary based on statistical characteristics of the time sequence deviation, enables the scheduling system to dynamically adapt to changes in actual operation conditions, and eliminates operation risks caused by track deviation.

This invention provides an energy management system for a modular robot, comprising a local management unit within each modular unit and a global scheduling unit located on the main control side of the modular robot. The local management unit, centered on a microcontroller, includes an energy bus dynamic reconfiguration module, a lithium-ion battery pack management and monitoring module, a lithium-ion battery pack current capacity estimation module, and a modular unit energy consumption prediction module. It estimates and outputs to the main control controller the current capacity of each modular unit and the future energy consumption requirements for each trajectory in the task sequence. The global scheduling unit, centered on the main control controller, includes a modular robot energy scheduling module. Based on data provided by each microcontroller, it performs global energy planning for the operation of the modular robot and sends energy scheduling commands to each microcontroller. This invention is applicable to solving the problem of localized failures caused by uneven energy consumption in independent power supply systems, and improving the remaining power balance rate.

The application discloses an energy scheduling and communication redundancy control method of a hybrid networking energy management system. The energy scheduling process introduces power dead zone control, effectively suppresses frequent action of energy storage converter caused by short-time light change due to cloud layer passing, significantly reduces the loss of energy storage battery and converter, prolongs the service life of equipment, and guarantees the smooth and stable power of a point of common coupling. In addition, by constructing a three-level priority communication redundancy architecture, fault isolation and automatic switching of a communication link are realized, system paralysis caused by single communication network failure is completely avoided, and the availability of the whole energy management system is greatly improved. By setting a communication recovery stability delay judgment, frequent switching of a communication mode caused by link instantaneous jitter is avoided, and stable operation of the control system is ensured. The whole control method improves the intelligent level and stability of energy scheduling, and enhances the reliability and robustness of the communication system.

This invention discloses a two-layer collaborative optimization method for port operations and energy considering the uncertainty of ship arrivals. It includes: constructing a two-layer collaborative optimization model for port operation scheduling and port energy scheduling, and collecting basic data. Based on the basic data, a multi-objective evolutionary optimization algorithm is used to collaboratively solve the two-layer collaborative optimization model. During the solution process, the uncertainty of ship arrival time is introduced into the operation scheduling decision, and the ship's time in port and the overall port operating cost are optimized simultaneously, generating Pareto optimal solution sets corresponding to different optimization objective trade-offs. A target scheme is selected from the Pareto optimal solution set, and ship berth allocation, operation equipment scheduling, and port energy system operation control are executed according to the target scheme, realizing the collaborative optimization scheduling of the port operation system and energy system. This invention can reduce the overall port operating cost, increase the renewable energy absorption rate, and enhance the robustness of the scheduling scheme in the face of ship arrival uncertainties.

The application discloses a power control method, device and program product, and belongs to the technical field of computers. The method comprises the following steps: in the case that power supply information of a micro-grid does not satisfy a preset condition, determining a first target power according to the power supply information, the first target power being a target power required to be output by an energy storage module, the target power being reactive power or active power; and in the case that the first target power is less than or equal to a second target power, adjusting the target power output by the energy storage module according to the first target power, the second target power being a maximum target power that can be output by the energy storage module. When the load fluctuates and the energy storage module can independently consume the fluctuation caused by the load, only the output power of the energy storage module is adjusted, so that the power generation efficiency of a diesel generator module and the power supply quality can be ensured, and the power supply efficiency is improved. Moreover, the energy storage module can quickly respond to the control of the micro-grid and output stable power, and the energy scheduling speed of the micro-grid can be improved.

This invention discloses a method and apparatus for adjusting intraday household energy dispatching plans based on load correction. The steps are as follows: The day-ahead equipment operation sequence scheduling plan is input into a user-intervention-based load correction mechanism to obtain a user-modified equipment operation sequence scheduling plan; the day-ahead photovoltaic usage plan, day-ahead energy storage charging and discharging plan, day-ahead user electricity purchase plan, and the user-modified equipment operation sequence scheduling plan are input into an intraday rolling optimization model, and intraday photovoltaic usage plan, intraday energy storage charging and discharging plan, and intraday user electricity purchase plan are obtained after rolling optimization. The load correction mechanism parses user instructions and updates equipment operation plans and corrects power curves; the intraday rolling optimization model uses a multi-objective particle swarm optimization algorithm to solve the rolling optimization logic. This invention effectively solves the problem of mismatch between dispatching plans and actual operating conditions, significantly improving the practicality, rationality, and stability of household energy dispatching.

The application discloses a kind of park integrated energy system double-layer optimization scheduling method and system, method includes: constructing park integrated energy system operation framework, modeling each equipment in operation framework;Establish the vehicle-to-grid interaction model considering the temporal and spatial distribution characteristics and charging and discharging behavior of electric vehicles, and the ice storage air conditioning load model;Set considering the PIES double-layer optimization scheduling strategy of vehicle-to-grid interaction and ice storage air conditioning coordination, define upper layer as PIES energy scheduling layer, lower layer as flexible load response layer;Solve electric vehicle optimization model and ice storage air conditioning optimization model, solve system operation cost optimization model, according to the solution result, each equipment in park integrated energy system is optimized and dispatched;The application has the advantages that: EV and IAC are deeply integrated, and collaborative scheduling is carried out, and double-layer optimization scheduling strategy is used, so that economic and low-carbon operation of system level is realized under the premise of guaranteeing user energy cost and comfort.

The application belongs to the technical field of unmanned aerial vehicle task offloading, mobile edge computing and micro-grid energy management, and discloses a kind of fusion modeling method of unmanned aerial vehicle task offloading optimization and micro-grid scheduling, which is suitable for micro-grid environment containing new energy and hybrid energy storage.For the problems of independent task and energy scheduling, insufficient cross-time scale cooperation, weak uncertainty response capability and other problems in the prior art, the application constructs a "computing-energy-communication" trinity cooperation system and a "cloud-edge-end" hierarchical architecture, adopts double-time scale scheduling, introduces opportunity constraints to handle uncertainty, divides task priority and supports multiple types of unmanned aerial vehicles and charging methods, and solves the joint optimization model through Actor-Critic network and MPC cooperation.The application realizes the deep coupling of efficient task execution and economic and stable operation of micro-grid, significantly improves the task completion rate and renewable energy consumption rate, and is suitable for power grid inspection, disaster emergency response and other scenes.

This application relates to the field of digital twin technology, and discloses a method, system, and storage medium for park energy management based on digital twins. The method includes: digitally mirroring and reconstructing the park's physical energy system to obtain a three-dimensional digital twin; performing fuzzy semantic modeling and fuzzy decision processing on multi-dimensional energy state information based on the digital twin to obtain intelligent energy scheduling decision data for the park; inputting the scheduling decision data into a differential evolution algorithm for optimization to obtain the optimal energy management strategy; and constructing a prediction engine based on the optimal strategy for time series learning to obtain a digital twin-driven park energy management scheme. This application solves the problem of difficult virtual-real synchronization of park energy systems by constructing a digital twin, further solves the problem of the inability of fuzzy controller parameters to adaptively optimize by using a differential evolution algorithm, and addresses the problem of insufficient time series data processing capability of traditional prediction methods by using a long short-term memory neural network.

The application provides a kind of intelligent battery replacement control method and system based on auxiliary power supply of electric vehicle, belongs to the cross technical field of new energy vehicle and new type power system, its method includes: when electric vehicle enters battery replacement station and establishes high voltage electrical connection, determine to enter battery replacement state, and the high voltage bus of electric vehicle in battery replacement state, the battery pack to be replaced, station energy system and grid interface are constructed as multi-port real-time energy scheduling network;In the duration of battery replacement state, the power distribution equation is solved in real time to determine the real-time power instruction of each energy port, and the power output or input of each energy port is coordinated and controlled according to the real-time power instruction;When battery replacement mechanical operation is completed and the high voltage system of electric vehicle is confirmed to be stable, exit battery replacement state.Solve the problem of large power impact and low energy utilization rate in the prior art, realize the response of second-level power grid, reduce the power impact, improve the energy utilization rate of battery replacement process, and at the same time guarantee the battery replacement safety and battery life.

This invention discloses an AI-based intelligent energy dispatching and management system based on prediction, scheduling, and diagnosis. The system includes a photovoltaic power generation unit, a hybrid energy storage unit, a thermal energy storage unit, a hydrogen energy storage and conversion unit, an AI intelligent monitoring unit, an AI intelligent management unit, a power grid and load unit, and a cloud platform. The system employs a long short-term memory network to achieve accurate ultra-short-term photovoltaic power prediction, constructs a dynamic optimization scheduling strategy with multiple time scales and energy flows based on deep reinforcement learning, and utilizes a one-dimensional convolutional neural network for real-time fault diagnosis and health management of key equipment. Through the synergy of electricity, heat, and hydrogen energy storage and AI intelligent scheduling, the system significantly improves the self-consumption rate of photovoltaic power generation and system energy efficiency. It possesses intelligent features such as self-sensing of state, self-optimization of scheduling, and self-diagnosis of faults, providing an efficient, reliable, and economical solution for high-proportion renewable energy consumption.

The application discloses a kind of off-grid type multi-energy complementary energy system's self-adapting energy scheduling system and method, and it is related to energy system technical field.The application includes: heating unit;Energy storage unit, energy storage unit is used to store the energy provided by heating unit;Conversion unit, conversion unit is used to convert the energy provided by heating unit and is transported to energy storage unit;Intelligent control system, intelligent control system is used to control heating unit, energy storage unit and conversion unit.The application utilizes solar energy, air energy and the collaborative work of energy storage system, ensures the stability of cold and heat source supply, adapts to different environment and climate conditions;Container type structure, easy to transport and install, can be widely used in remote areas, single-family house, villa and other scenes;System improves the stability of cold and heat supply at the same time, realizes efficient energy storage and intelligent optimization control, provides a kind of feasible solution for low-carbon energy-saving building and new energy utilization.

Embodiments of the present application disclose a kind of heavy energy consumption industrial comprehensive energy scheduling control method and device, equipment and storage medium, first training is obtained the digital twin model of target energy flow system covering multiple energy media, then using deep correlation-self-correcting recursive network algorithm obtains candidate scheduling scheme set, and further using adaptive energy flow multi-objective evolutionary optimization algorithm is scheduled scheme iteration, obtains optimal target scheduling scheme and executes, so that production-energy integration modeling, multi-objective adaptive optimization and whole-process simulation can be realized, which can effectively improve the efficiency of regulation and control response, and realize the full coverage of optimization target.

This invention discloses a charging pile energy scheduling method based on cloud-edge collaboration, comprising the following steps: Step 1: Collecting station-side energy operation data within the target charging station and generating a unified time-based state sequence; Step 2: Establishing edge connections between different energy nodes and calculating edge weights to generate an intra-station energy relationship graph; Step 3: Uploading the intra-station energy relationship graph to a cloud scheduling platform and generating a regional-level cloud energy scheduling graph; Step 4: Inputting the regional-level cloud energy scheduling graph into an improved Graphormer model to generate cloud-based regional scheduling results; Step 5: Splitting the cloud-based regional scheduling results according to the charging station number and distributing station-level scheduling benchmarks to the corresponding edge gateways; Step 6: Obtaining real-time power allocation results within the station based on the station-level scheduling benchmarks and the unified time-based state sequence. This invention achieves intelligent scheduling of charging energy through an improved Graphormer model.

A micro-grid energy scheduling method and system based on reinforcement learning, the method comprising: constructing an energy scheduling objective function and a micro-grid operation cost objective function; defining the state space of a power grid operator agent and a plurality of micro-grid agents respectively, performing action selection and updating the corresponding state space; based on the updated state space of the micro-grid agent, combining the micro-grid operation cost objective function value to determine an instant reward function, and updating the agent; based on the updated state space of the power grid operator agent, calculating the energy scheduling objective function value to determine an outer global reward function, and updating the agent; calculating the comprehensive benefit function of the updated agent, and when a predetermined convergence condition is met, outputting a trained strategy network to determine the optimal action of each agent. The present application constructs a hierarchical multi-agent reinforcement learning energy scheduling mechanism, which realizes the collaborative optimal control of multi-dimensional power grid operation cost while taking into account the stability of the power grid operation.

The application relates to an energy data processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining original energy data based on space division multiplexing transmission energy data; sequentially performing denoising processing and data quality evaluation processing on the original energy data to obtain denoised energy data and a quality evaluation result of the denoised energy data; performing denoising processing on the denoised energy data again according to the quality evaluation result to obtain target energy data; and inputting the target energy data into a trained energy scheduling processing model to obtain target scheduling information of the target energy data. The method can improve the energy data processing efficiency, utilize the target scheduling information to improve the scheduling effect of energy equipment, and realize intelligent management of the energy equipment.

This invention discloses a multi-domain energy recovery self-circulating power supply system. It employs a dynamic adaptive switching threshold, performing inter-group switching based on the energy cycle balance of at least two electrically independent energy storage units. It prioritizes shallow discharge and frequent switching within the sufficient power range and can switch to an extended hybrid operation structure depending on the operating conditions, with a 20% discharge protection baseline. An external energy absorption and conversion module and an internal energy recovery module first send energy and signals to an intelligent energy management chip, then the energy scheduling and seamless switching module uniformly distributes the energy, forming an uninterrupted internal charge closed-loop cycle. This system uniformly recovers internal waste heat, waste electricity, vibration energy, residual electromagnetic energy, and external solar energy, ambient thermal energy, and ambient radio frequency energy. The system adopts a time-sharing independent drive control strategy, achieving short-term power superposition transitions only during instantaneous operating conditions. Combined with hybrid physical isolation and millisecond-level safety protection, it achieves high safety, long endurance, high energy efficiency, and adaptive power supply under all operating conditions. This invention can be widely applied to vehicles, robots, drones, and field and industrial power supply equipment. The pure electric operation structure can operate autonomously without an external power grid or fossil fuels, possessing excellent practicality and safety.

The application discloses an LED complementary power supply intelligent lighting system and an energy scheduling method, relates to the technical field of lighting, and comprises a complementary power supply module integrating photovoltaic, wind energy and a power grid backup power supply unit to form a multi-source complementary architecture; an energy storage module adopts a lithium iron phosphate battery pack and a bidirectional DC-DC converter; a lighting control module contains a constant current driving circuit, a stepless dimming unit and an LED lighting array; an environment sensing module is provided with multiple sensors to collect data such as light, personnel and traffic; an energy scheduling module analyzes data to formulate a dynamic energy distribution strategy and coordinates the work of each module; a communication module adopts a dual-mode communication technology to realize remote data interaction; and a safety protection module integrates multiple protection circuits to ensure safe operation of the system. The application solves the problems of low energy utilization efficiency and poor adaptability of traditional lighting, improves the utilization rate of clean energy through multi-source complementation, and improves safety and convenience through multiple protection and remote operation and maintenance.

This application relates to the technical field of power optimization and dispatching, and in particular to a flexible control method, system, and power router for a power router. The method includes: when the power router is in operation, real-time acquisition of operating status data; calculation based on the operating status data using a preset flexible dispatching algorithm to obtain a dispatching decision result; adjustment of the power allocation and exchange boundaries between the power router's energy ports based on the dispatching decision result to obtain a flexible operating range; determination of the current operating mode based on the flexible operating range; and control of the power router to execute energy management actions corresponding to the current operating mode based on the current operating mode and operating status data. By constructing a flexible operating range, the system's adaptability and operational stability under varying operating conditions are improved, achieving rapid response in the time dimension and multi-port coordination in the spatial dimension for energy dispatching, comprehensively enhancing the operating efficiency and control accuracy of the power router.

The application provides a new energy-thermal power-energy storage comprehensive energy scheduling method, and belongs to the technical field of comprehensive energy system scheduling, which can at least partially solve the problems of strong fluctuation of new energy generation, insufficient coordination of thermal power and energy storage, and difficulty in giving consideration to economy, low carbon and power supply reliability in multi-objective scheduling. The method comprises the following steps: constructing a collaborative coupling model to obtain the time sequence operation characteristics of each unit in the scheduling period; establishing a multi-objective collaborative optimization scheduling model; setting a constraint condition system; solving the multi-objective collaborative optimization scheduling model to obtain a collaborative scheduling scheme of new energy, thermal power and energy storage; and dynamically updating and adjusting the scheduling scheme according to the actual operation state. Through the above method, the coordinated operation of new energy, thermal power and energy storage is realized, the new energy consumption capacity is improved, the system operation cost and carbon emission are reduced, and the safety and stability of the power system operation are enhanced.

This invention provides a method and system for integrated production and energy scheduling at a bulk cargo terminal. The method includes: establishing a mixed integer programming model based on production scheduling variables and energy load variables, wherein the mixed integer programming model has the objective function of minimizing total operating cost; decomposing the mixed integer programming model into a main production scheduling problem and an energy optimization subproblem using the Benders decomposition algorithm; defining production constraints for the main production scheduling problem and energy constraints for the energy optimization subproblem; initializing iteration parameters; iteratively solving the main production scheduling problem and the energy optimization subproblem; generating feasible cuts or optimal cuts based on the solution results of the energy optimization subproblem in each iteration and feeding them back to the main production scheduling problem; stopping iteration and outputting the optimal solution when a preset convergence condition is met. This invention solves the problem of difficulty in solving large-scale integrated scheduling models and can output an optimized scheduling scheme that balances efficient production and low-carbon energy saving within a reasonable time.

The present application relates to the technical fields of energy scheduling optimization, and specifically includes a building electricity-heat-cold multi-energy collaborative scheduling method based on particle swarm optimization, comprising: uploading electricity-heat-cold multi-energy collaborative scheduling precision requirements, setting an adaptive correction scheduling layer and a multi-energy complementary scheduling model, initializing particle swarm position parameters and particle swarm speed parameters; connecting the particle swarm optimization model architecture with the adaptive correction scheduling layer to determine the optimal scheduling parameter combination for collaborative scheduling processing. The present application solves the technical problem of lagging behind in adjusting scheduling parameters when photovoltaic, energy storage and other distributed energy outputs cannot be accurately matched with cold and heat load demands, instantaneous load impact or equipment operation anomalies are encountered, realizes the construction of a multi-energy flow coordination loop and an adaptive correction scheduling layer, integrates electricity, heat and cold multi-energy data, verifies and corrects through energy use task feedback, and simultaneously realizes multi-energy complementation through primary and secondary linkage scheduling combined with node classification marking, thereby improving multi-energy collaborative efficiency.