120 results about "Distributed generation" patented technology

The invention, which relates to the technical field of distributed power generation, discloses a modularized distributed photovoltaic inverter cluster intelligent regulation and control system comprising an impedance identification module, an impedance control module, a state sensing module, a fault diagnosis and isolation module, a power distribution module and a cluster fault control module. The power grid impedance monitoring module is used for monitoring voltage and current signals of a grid-connected point of the photovoltaic inverter, calculating a power grid equivalent impedance value, an impedance change trend and a harmonic component proportion of the current photovoltaic inverter, and generating power grid impedance information. The impedance identification module and the impedance control module are arranged, adjustment is carried out based on the virtual impedance parameters, the resonance problem caused by power grid impedance fluctuation is effectively suppressed, the situation that grid-connected current distortion affects the electric energy quality is avoided, the photovoltaic inverter cluster stably operates in a power grid impedance change scene, and the power grid impedance change efficiency is improved. And the cluster grid-connected power quality and the adaptability to the power grid environment are improved.

The invention relates to a transportation junction multi-business micro-energy network chain-type interconnection architecture, and the architecture comprises a load layer which comprises micro-energy networks of different business forms; the energy layer comprises an external energy source and a distributed power generation and energy storage system and is used for providing comprehensive energy supply for energy consumption requirements of the micro-energy grids in different commercial forms in the load layer; the energy network layer comprises different types of energy networks, the different types of energy networks carry out coupling conversion on energy of the energy layer so as to meet the energy use requirements of micro energy networks in different business states in the load layer, and coupling interaction and interconnection intercommunication between the different types of energy networks are achieved through different types of energy conversion equipment; and the cloud edge-end energy collaborative management and control system is used for regulating and controlling the energy layer, the energy network layer and the load layer by utilizing a cloud-edge-end three-layer management and control architecture so as to realize the collaboration and dynamic balance of multiple energy flows among different regions of the transportation hub.

The invention discloses a network security monitoring method and system based on the Internet of Things, and relates to the technical field of Internet of Things security. Through dynamic challenge-response physical unclonable authentication, physical parameters and a real-time state are fused to generate a dynamic challenge value, and a physical unclonable function circuit is combined to generate a response value to realize identity verification; adaptive noise lattice-based homomorphic encryption is adopted, a ciphertext is generated based on a high-dimensional lattice-based password, and noise parameters are adjusted through channel quality to guarantee transmission security; multi-modal confrontation federated learning anomaly detection is utilized, flow, energy consumption and physical state characteristics are fused, and parameters are aggregated through a confrontation auto-encoder training model and based on federated learning; through dynamic threshold key negotiation, in combination with identity-based encryption and a block chain smart contract, distributed generation and dynamic adjustment of a key are realized; on the basis of a Merkle-salt value dynamic hash chain and block chain evidence storage, a log is generated in a trusted execution environment, a hash chain is constructed, and chain tail hash is synchronized to block chain evidence storage.

The invention discloses a micro-grid optimal scheduling method, system and device considering flexible loads, and relates to the field of micro-grid optimal scheduling. Establishing a comprehensive objective function and constructing an operation load constraint set by taking micro-grid operation cost minimization and environmental benefit maximization as objectives; based on the operation load constraint set, solving the comprehensive objective function to obtain day-ahead scheduling information and intra-day rolling information; issuing a flexible load regulation and control instruction to the micro-grid through the block chain smart contract, and collecting flexible load real-time operation feedback information; and in combination with a deep reinforcement learning emergency regulation and control strategy and a sensitivity analysis optimization strategy, determining a compensation optimization scheduling scheme according to the flexible load real-time operation feedback information and the flexible load regulation and control instruction. The method can give consideration to both environmental protection and economy, improves the reasonability of load regulation and control, and effectively deals with the uncertainty of the source load.

The invention provides a distributed power supply and energy storage reactive power control method considering interval coordination, and relates to the technical field of energy storage, and the method comprises the steps: dividing a power distribution network into a plurality of power distribution network regions according to the power loss, the power utilization demand mode, the load characteristics, and the power grid adjustment capability; collecting power loss data of branches in each power distribution network region; constructing a target power optimization model according to the power loss data and the power distribution coefficient corresponding to each power distribution network region; performing iterative solution on the target power optimization model by taking the total loss of the minimized current at each intersection as a target and taking branch node voltage constraint, reactive current stability constraint and equipment capacity constraint as constraint conditions to obtain a reactive power control strategy of the distributed power supply and energy storage; and according to the reactive power control strategy, controlling operation equipment in each power distribution network area. According to the scheme, control over the distributed power supply and the energy storage reactive power can be achieved through line monitoring, and then the voltage quality of the transformer area is improved.

This invention provides a distributed generation (DG) optimization configuration method based on a quantum genetic algorithm, aiming to minimize power loss and improve voltage stability in power distribution systems. The method first collects basic data of the power distribution network, including bus numbers, voltage levels, line impedances, bus load demands, and capacity limitations of distributed generation sources. Next, a population containing different DG configuration schemes is initialized using a random number generation algorithm, and the population is iteratively optimized using a quantum genetic algorithm. During the optimization process, quantum selection, crossover, and mutation operations are used to generate a new generation of configuration schemes, and the power loss and voltage level of each scheme are evaluated using a fitness function to gradually approach the optimal solution. After obtaining the optimal configuration scheme, different load conditions (such as load increases or decreases) are simulated to verify and optimize the adaptability of the configuration, ensuring that the system can maintain low power loss and voltage stability under load fluctuations. The final output optimal DG configuration scheme includes bus location, capacity, and optimized power loss and voltage curves, capable of adapting to dynamic load changes. This method can effectively reduce power loss and improve voltage stability in power distribution systems, providing technical support for building efficient and reliable power distribution systems.

The invention provides a photovoltaic inverter DC side anti-reflux device and method, and belongs to the field of distributed power generation. The device is connected in series between a photovoltaic string and an inverter, and comprises a circuit breaking unit, a parallel power adjusting unit, a blocking diode and the like. The control method adopts a hierarchical control strategy of removal and adjustment: a controller collects the countercurrent power of a grid-connected point in real time, and when countercurrent is detected, the countercurrent power is judged; if the countercurrent power exceeds the output power of the single-path photovoltaic string, cutting off is executed, the corresponding number of circuit breaking units are directly controlled to be disconnected, and part of the photovoltaic string is physically cut off; and controlling the residual trace countercurrent power, calculating a PWM duty ratio by using a direct calculation or incremental PID algorithm, and driving a power adjusting unit to carry out hardware chopping consumption or suppression. According to the invention, long-time heating of the power device under large current is avoided, the problem of overlarge power regulation granularity caused by pure cutting is solved, and smooth and rapid countercurrent prevention of the photovoltaic system is realized.

This invention discloses a multi-source collaborative optimization control method for smart microgrids, relating to the field of energy technology. The method includes: connecting to the user side to predict the power supply demand of the target microgrid in a preset time zone; acquiring a hybrid energy supply module containing multiple distributed power sources; collecting historical power supply logs of the distributed power sources and generating relevant time sequences; performing energy curtailment rate analysis based on this to generate indicators and decisions; optimizing energy storage units after determining that the indicators meet the standards; and then performing multi-source collaborative power supply control according to preset demand. This method solves the technical problems of existing new energy power generation uncertainties that are difficult to accurately predict, and unreasonable energy storage module configurations that lead to significant energy losses during power generation, storage, and distribution, resulting in low energy utilization efficiency and unstable power supply quality. By optimizing and integrating new energy power generation, energy storage modules, and energy distribution in the microgrid, it achieves the technical effect of reducing energy losses and ensuring efficient and high-quality power supply to the microgrid.

The invention discloses an area micro-grid distributed power supply-energy storage robust collaborative planning method considering load side resource flexibility, and belongs to the technical field of power system planning. Comprising the steps that energy storage characteristics of load side electric vehicles and heating ventilation air conditioners are considered, and a cluster electric vehicle generalized energy storage aggregation model and a heating ventilation air conditioner generalized energy storage aggregation model are established; considering the influence of source-load uncertainty, and according to the cluster electric vehicle generalized energy storage aggregation model and the heating ventilation air conditioner generalized energy storage aggregation model, establishing a zone area micro-grid robust collaborative planning model considering the load side resource flexibility; and solving the zone area micro-grid robust collaborative planning model considering the load side resource flexibility by adopting a nested column and a constraint generation algorithm. According to the collaborative planning model established by the method, the flexible adjustment potential of load side resources can be fully mined, the energy storage configuration scale is remarkably reduced, and economic and efficient operation of the micro-grid can be ensured.

The present disclosure relates to control of a voltage regulator in an electric power system. In one embodiment, a system to control a voltage regulator includes a communication interface configured to communicate with the voltage regulator. A power flow direction subsystem may determine a direction of a current flow in the electric power system. A tap change monitoring subsystem may monitor tap changes implemented by the voltage regulator to evaluate a voltage change resulting from each of the plurality of tap changes and determine a source stiffness value for a first source and a second source. A voltage regulator control subsystem is configured to determine a regulation direction based on the direction of current flow determined by the power flow direction subsystem and based on the source stiffness value for the first source and the second source, and communicate the regulation direction to the voltage regulator through the communication interface.

The invention provides a power distribution network power supply and distribution system and method based on energy storage balance. The method comprises the steps that real-time operation parameters of all nodes in an active power distribution network are collected; the real-time operation parameters comprise the real-time power generation power of the distributed power supply, the real-time electrical load power of the user side and the real-time charge state of the energy storage device; performing power supply simulation based on the real-time generated power, the real-time electrical load power and the real-time charge state, and determining an initial power supply scheme; the initial power supply scheme comprises initial power supply power of the distributed power supply and initial charging and discharging power of the energy storage device; after power supply is carried out according to the initial power supply scheme, stability evaluation is carried out based on the current charge state of the energy storage device and the voltage constraint condition and the current constraint condition of each node in the active power distribution network, and a final power supply scheme is determined; the final power supply scheme comprises the final power supply power of the distributed power supply and the final charging and discharging power of the energy storage device. According to the invention, efficient and stable operation of the power distribution network is realized.

The invention discloses a market mechanism-based power distribution network distributed clean energy bearing optimization method. The method comprises the following steps of 1, constructing a planning decision model of a power distribution network distributed energy system and a small gas turbine; step 2, constructing a power purchase decision optimization model of the power purchase side power distribution network so as to obtain a decision scheme with the minimum total power purchase cost; and step 3, on the basis of the bidding strategy game model of the distributed power generation unit, constructing a market clearing model of the power transaction center, and obtaining an optimal decision scheme under the model. According to the method, the defect that existing power distribution network planning is difficult to consider clean energy bearing capacity, investment uncertainty and cost optimization is overcome, low-cost power purchase and efficient clean energy consumption are realized, the reliability and flexibility of the system are improved, and the bearing capacity and operation economy of the power distribution network are effectively enhanced.

The application discloses a micro-grid distributed cooperative control method and system based on FCS-MPC and improved finite-time consensus, relates to the technical field of power system control, and comprises the following steps: configuring a hybrid energy storage system of super capacitors and storage batteries in a photovoltaic power generation unit and a fan power generation unit respectively, and constructing a distributed power generation unit; utilizing FCS-MPC to optimize the switching state of a Boost voltage-boosting circuit, a hybrid energy storage bidirectional DC / DC converter and a two-level inverter, and performing voltage dynamic regulation and fluctuation correction of a direct-current bus; constructing a micro-grid; performing secondary frequency recovery control and active power proportional distribution based on a secondary frequency recovery control strategy of the improved finite-time consensus theory; and performing secondary voltage recovery control and reactive power proportional distribution based on a secondary voltage recovery control strategy of the improved finite-time consensus theory. The application improves the operation stability and power quality of the micro-grid under high renewable energy penetration.

The invention discloses a configuration optimization method and device for a flexible interconnection device of a power distribution network, a terminal and a medium, and the method comprises the steps: firstly obtaining the topological structure information of the power distribution network, collecting the data of the power distribution network, and calculating the load moment parameter of each node; the method comprises the following steps: acquiring a load moment parameter, constructing a load moment correlation model of a correlation relationship between the load moment parameter and a power distribution network operation parameter based on the load moment parameter, then constructing a multi-target optimization model based on load moment parameter weighting based on the load moment correlation model, and solving the model to obtain an SOP configuration optimization scheme. According to the scheme, the load moment parameter is introduced, the load moment correlation model and the load moment parameter weighting-based multi-objective optimization model are constructed, and the spatial distribution characteristics of the load in the power distribution network and the influence of the spatial distribution characteristics on the system operation are fully considered, so that in the active power distribution network containing the high-proportion distributed power supply, the power distribution efficiency is improved. The optimization result can be prevented from falling into local optimum, so that the configuration of the flexible interconnection device of the power distribution network can be optimized more accurately.

The invention relates to the technical field of photovoltaic grid-connected control, and discloses a photovoltaic grid-connected box control method and system suitable for active harmonic suppression, and the system comprises a photovoltaic assembly module, a grid-connected inverter and a composite repetitive control module. According to the system, solar energy is converted into direct current through a photovoltaic assembly module, then the direct current is converted into alternating current through a grid-connected inverter to be connected into a power grid, a composite repetitive control module is used for detecting grid-connected current harmonics, generating a total harmonic distortion rate and judging whether a photovoltaic grid-connected box meets grid-connected conditions or not, and if the total harmonic distortion rate is smaller than or equal to 5%, the grid-connected conditions are met; and if the total harmonic distortion rate is greater than 5%, a harmonic suppression measure should be taken in time, so that compared with a traditional control system, the photovoltaic grid-connected box has better harmonic suppression capability, realizes active suppression of the photovoltaic grid-connected box on harmonic current caused by power grid background harmonic waves and nonlinear loads, and has great significance in guaranteeing the electric energy quality in the photovoltaic grid-connected process. And the method has a positive effect on promoting distributed power generation friendly grid connection and the like.

The application discloses a county power grid comprehensive regulation system and method considering distributed power consumption and energy storage benefits, and relates to the technical field of power grid regulation. The system comprises a data collection unit, a control unit and an execution unit. The data collection unit is used for collecting power grid operation data, photovoltaic power generation, wind power generation and energy storage state in real time. The control unit is used for making decisions on energy storage operation strategy, distributed power generation operation strategy and county power grid branch line connection switch connection strategy according to the collected data. The execution unit is used for executing the decisions of the control unit and regulating power grid operation. Through real-time data collection, intelligent control decision and automatic execution, the energy storage operation strategy, the distributed power generation operation strategy and the county power grid branch line connection switch connection strategy are optimized, and the maximization of power grid economic benefits and the optimization of distributed power consumption are realized.

This invention provides a method, apparatus, and electronic device for batch generation of short drama works, belonging to the field of film and television work generation technology. The method includes: a master node acquiring the script of the short drama to be generated; decomposing the script into multiple atomic tasks and determining the dependencies between these tasks; based on the dependencies, distributing atomic tasks without dependencies to multiple slave nodes in a distributed generation system in parallel via a message queue; each slave node executing the received atomic tasks in parallel, writing the intermediate data generated as execution results into a distributed storage system; and the master node reading the execution results of each atomic task from the distributed storage system, merging them according to the dependencies and the time sequence of the script to generate the short drama video. This invention enables high-concurrency batch production of short dramas, significantly improving the efficiency and stability of short drama generation.

The present disclosure provides a kind of based on self-consistent distribution unit area flexible interconnection planning method and planning device, including obtaining uncontrollable data of area, based on the uncontrollable data of area, calculate uncontrollable net load of area, the uncontrollable data includes the uncontrollable distributed power generation of area and the rigid load power of area;Based on the uncontrollable net load of area, calculate the complementary matching degree of area in distribution network;The self-consistent distribution unit of the two areas under the highest complementary matching degree of area is selected to plan, the objective function and constraint condition of self-consistent distribution unit are constructed;The objective function is solved, and the planning result is output.The present disclosure can guarantee the safe and economic operation of distribution network, and as far as possible to absorb new energy generation by the above method.

This invention relates to a distribution network reconfiguration method based on distributed generation and SOP (Standard Operating Procedure) optimization configuration, belonging to the technical field of new energy grid connection and distribution network optimization operation. The method includes: performing site selection and capacity determination on the original distribution network using an improved gray wolf algorithm based on a constructed distributed generation optimization configuration model; updating the distribution network structure to form a new distribution network structure, constructing an SOP optimization configuration model, and optimizing the SOP configuration using an improved sensitivity analysis method; connecting the optimal access location and capacity of the distributed generation obtained from site selection and capacity determination, along with the SOP optimized configuration capacity and location, to the distribution network, constructing a distribution network demand response model; constructing a distribution network reconfiguration model based on the distribution network demand response model, reconfiguring the distribution network, obtaining the distribution network disconnection results, and thus obtaining a new topology. It aims to solve the technical problems of increased voltage fluctuations, increased network losses, and bidirectional power flow caused by a high proportion of distributed generation access to the distribution network.

The present invention relates to a method and device for optimizing the distributed power for a building. According to an embodiment of the present invention, the method for optimizing the distributed power for a building comprises the steps of: collecting energy usage data of a building and confirming an energy usage pattern through data analysis of the collected energy usage data; predicting energy demand by using a trained demand prediction model; and optimizing the combination of distributed power applied to the building by using a genetic algorithm on the basis of the confirmed energy usage pattern and the predicted energy demand.

The present disclosure provides systems and methods for managing electrical power distribution using artificial intelligence models deployed on edge computing devices positioned within power distribution environments. These edge devices may analyze measurement data from various sources throughout the electrical network and generate predictive forecasts to inform power management decisions. The edge computing device may coordinate with distributed generation systems to optimize electrical power management through localized control actions.  The artificial intelligence model may process electrical consumption and generation data to generate forecasts of electrical demand and supply conditions.

The invention relates to an active power distribution network multi-target planning method based on reliability explicit analytic expression, and the method comprises the steps: building a reliability evaluation-oriented matrix calculation model, and building an ADN multi-target collaborative planning model which gives consideration to the power supply reliability, DG absorption capability and economical efficiency; carrying out linear reconstruction and optimization solution on the multi-target collaborative planning model; and outputting a multi-target collaborative planning result, and analyzing resource configuration characteristics and cost structure evolution characteristics of the ADN under multi-target collaborative optimization. According to the method, a matrix analytic calculation system oriented to reliability evaluation is established, an explicit analytic calculation method of the ADN reliability index considering SOP and ESS is provided, the reliability cost obtained through conversion of the reliability index is embedded into an ADN multi-objective optimization model, and coordination and balance among ADN power supply reliability, DG absorption capacity and economical efficiency are achieved through reasonable configuration of the SOP and the ESS.

This disclosure relates to the field of voltage control technology, and proposes a distributed voltage control optimization method and system for three-phase unbalanced distribution networks. It uses the active and reactive power output by single-phase distributed power sources connected to the distribution network and the three-phase distributed power sources as the control objects. By coordinating the power injected into each phase of the distribution network by the distributed power sources, it reduces the deviation of voltage at each node from the voltage reference value and the phase-to-phase voltage deviation, thereby achieving stable control of the voltage of each phase at each node of the distribution network. Two different control modes are designed according to the different degrees of voltage deviation in the three-phase distribution network, taking into account both voltage coordination and the maximum utilization of distributed generation (DG) energy. The distributed controller only communicates with adjacent units, reducing the requirements for the controller's computing power and communication performance.

The invention discloses a power distribution network energy conservation and loss reduction management method, which comprises the steps of collecting power distribution network data, carrying out load prediction and fluctuation sequence simulation, calculating power flow and loss of a power distribution network by utilizing a self-adaptive double-layer forward-backward substitution power flow calculation method, constructing an objective function with optimal economic benefits, determining a static loss reduction scheme, and taking active loss as the objective function. And determining a regulation scheme of the distributed power supply, the adjustable load, the capacitor bank and the on-load voltage regulating transformer and a dynamic reconstruction combination of the power distribution network, and determining a dynamic loss reduction scheme. According to the scheme, the equipment transformation combination scheme is determined through the static loss reduction optimization model, the transmission efficiency of the power grid infrastructure is systematically improved, and the line loss abnormity problem caused by backward equipment performance and insufficient capacity is reduced; in addition, the operation conditions of the distributed power supply, the adjustable load, the reactive compensation equipment and the like and the topology change condition of the power distribution network are determined through the dynamic loss reduction optimization model, and the line loss caused by load fluctuation is reduced.

The application belongs to the technical field of energy storage power stations, and particularly relates to an energy storage power station energy optimization method based on graph calculation, which comprises the following steps: S1, predicting future power generation capacity and load demand of the energy storage power station based on graph calculation: obtaining historical power generation data and load data of distributed power stations in the grid-connected area of the energy storage power station, and external influence data, constructing a space-time graph neural network model, constructing the space-time graph neural network model, and obtaining prediction results of power generation data and load data of each hour period in the future 24 hours; S2, calculating power and load values of each node in the power grid through power flow analysis; and calculating the energy that the energy storage power station needs to provide or consume according to the predicted future power generation capacity and load demand. The application realizes optimization of energy of the energy storage power station, and reduces the cost of the energy storage power station.

This invention relates to the field of power system operation and control technology, and particularly to an equivalent aggregation method and system for the output power of distributed generation clusters. The purpose of this invention is to construct an equivalent aggregation method and system for cluster output power. First, output models of the power of generators, photovoltaics, wind turbines, and energy storage devices in the cluster are constructed. Then, a cluster network power flow technical constraint model is constructed, and node voltage and branch power flow constraints are established based on linear branch power flow equations. Next, an inscribed ellipsoid model of the equivalent domain for cluster output power aggregation is constructed. The parameter values ​​of the inscribed ellipsoid model are solved by constructing and solving a specific optimization problem. Compared with existing methods, the proposed equivalent aggregation method for cluster output power significantly accelerates the calculation speed and greatly improves the accuracy of the solution results, enabling rapid equivalent aggregation of cluster output power and possessing significant value in practical applications.

The invention is suitable for the technical field of electric energy storage, and provides a teaching experiment platform and method for simulating a hybrid energy storage system to participate in power grid frequency modulation, the teaching experiment platform comprises a power grid, the power grid is electrically connected with an energy storage unit through an AC bus, and the output end of the power grid is also electrically connected with a simulation power generation unit. The output end of the simulation power generation unit is electrically connected with the alternating current bus, a first switch is arranged between the simulation power generation unit and the alternating current bus, and the energy storage unit at least comprises a flywheel energy storage unit, a battery energy storage unit and a simulation load unit which are connected in parallel through the alternating current bus; according to the teaching experiment platform and method for simulating the participation of the hybrid energy storage system in the power grid frequency modulation, the distributed power generation units and various types of energy storage devices are configured, and the various energy storage devices can be flexibly combined through the alternating current bus, so that various different types of microgrids are constructed; and diversified scenes are provided for technical research, equipment monitoring and personnel training of the alternating current bus.

The invention belongs to the technical field of power grid regulation and control, and particularly relates to a demand side resource aggregation response regulation and control method for supporting urban power grid low-carbon toughness, which comprises the following steps: generating an urban power grid low-carbon toughness evaluation data set; calculating the charging and discharging efficiency and the cycle life index of the energy storage equipment, and the power conversion rate and the renewable energy source content of the distributed power generation equipment; calculating an urban power grid automatic recovery coefficient; constructing an anti-interference evaluation model, and outputting a corresponding urban power grid anti-interference index; constructing a low-carbon operation evaluation model, and obtaining a low-carbon operation index of the urban power grid; constructing an urban power grid low-carbon toughness evaluation correction model, and correcting different types of urban power grid low-carbon toughness evaluation indexes; and after correction, analyzing the low-carbon toughness of the urban power grid, sending out a corresponding response signal, and performing corresponding regulation and control on demand side resources supporting the low-carbon toughness of the urban power grid. According to the invention, a scientific basis can be provided for efficient configuration of various resources and optimization of a low-carbon and high-toughness operation strategy of a power grid.

A method for distributed generation siting planning considering line fault and grid resilience is proposed, including the following steps: considering the line fault model under the influence of typhoon load, analyzing the influence of typhoon on line meteorological load; combining with the actual load capacity of line, the line fault probability is calculated; the fault scene is selected by using system information entropy, the fault scale and its probability caused by typhoon are determined, and the distributed generation siting model is established based on the calculated line fault probability; the multi-objective particle swarm optimization algorithm is used to solve the distributed generation siting planning model considering line fault rate and grid resilience. The method can get the distributed generation siting position that meets the constraints and maximizes the grid resilience for different typical scenarios.

The present application relates to the field of distributed energy response scheduling, and discloses a demand response scheduling decision method and apparatus based on electricity-carbon coupling, a device, and a system. The method comprises: acquiring information data of a user end, wherein the information data comprises an electricity-carbon coupling locational marginal price signal corresponding to a distribution system operator, the information data is determined on the basis of a locational marginal price model of electricity-carbon coupling at a distribution system end, and the locational marginal price model is determined by the distribution system operator by using a distribution system branch flow algorithm; determining a user-side demand response model, wherein the user-side demand response model is constructed on the basis of the information data and with the objective of minimizing a power factor; and using Markov decision to perform mathematical transformation on the user-side demand response model, and using a deep reinforcement learning method to perform iterative optimization calculation to obtain a scheduling decision scheme, so as to coordinate a user-side load of the user end with distributed generation. The present application aims to implement coordinated adjustment and scheduling of distributed energy and user loads.