260 results about "Soft switch" patented technology

The invention relates to the technical field of power electronics, and discloses a soft switch of a high-frequency switch transformer and a distributed control method and system thereof, and the method comprises the steps: achieving the precise synchronization of nodes through the construction of a ring topology network, combining the monitoring of multiple physical quantities with the collaborative optimization of parameters, dynamically adjusting the parameters of a resonant network and a driving time sequence, and achieving the precise synchronization of the nodes. A zero-voltage switching state is maintained, and electromagnetic interference is suppressed by adopting the composite optimization model; the system comprises a network initialization module, a multi-physical-quantity monitoring module, a space-time synchronization control module, a resonance parameter adjustment module, an electromagnetic optimization decision module, a dynamic adjustment module and a parameter evolution module. The stability of the soft switch is improved through a distributed network and time-space synchronization, and the loss is reduced by adopting a dynamic optimization algorithm; constructing an electromagnetic interference optimization model to enhance compatibility; performing multi-parameter fusion and weight distribution to optimize dynamic response; the reliability is improved through a high-precision protocol and coevolution; and the tensor product framework realizes multi-dimensional intelligent cooperative control.

The invention discloses a new energy automobile wireless power supply soft switching control system based on a segmentation strategy, and particularly relates to the technical field of new energy automobile wireless power supply, and the control system comprises a resonance current zero-cross detection module which detects a resonance current output square wave signal of a resonance network in real time; the segmented control decision module is used for selecting a strong control strategy or a weak control strategy according to a comparison result of the smoothed frequency difference value and a preset threshold value; the segmented control execution module is used for adjusting the inverter driving frequency by adopting a corresponding control algorithm according to the output of the segmented control decision module; according to the new energy automobile wireless power supply soft switching control system based on the segmentation strategy, the segmentation control logic and the model and algorithm of the special module are designed, so that the driving frequency of the new energy automobile is adjusted, and the driving frequency of the new energy automobile is adjusted to be within the preset frequency locking range. And wide-range frequency locking, rapid dynamic correction and high-precision steady-state control are realized.

The invention relates to a flexible scheduling method and device for soft switch resources of a cloud native architecture, equipment and a medium. The method comprises the following steps: performing feature extraction and marking on computing nodes, storage resources and network resources by using a resource classification model to generate a resource tag library representing initial classification of each resource, extracting resource feature data from a resource tag library based on each resource initial classification, generating current supply and demand data in combination with resource use state data collected in real time, calculating a resource allocation priority sequence by using a multi-objective optimization algorithm fusing service response time and cost balance optimization parameters, and generating a preliminary sorting result; and detecting a resource supply and demand imbalance state based on the preliminary sorting result and the resource supply and demand change data flow monitored in real time, if the imbalance state is detected, executing resource allocation adjustment calculation based on the current supply and demand data, and generating a preliminary resource allocation scheme, thereby realizing flexible scheduling and optimal allocation of soft switch resources under the cloud native architecture.

The invention relates to a power distribution network optimal configuration method for a high-proportion distributed new energy access scene, and the method comprises the steps: obtaining the basic data of a power distribution network, and constructing a bearing capability evaluation index system; a robust optimization evaluation model considering the uncertainty of the source load is constructed, and the critical bearing capacity is solved in combination with a bearing capacity evaluation index system; based on the critical bearing capacity, energy storage, SOP intelligent soft switching and DR demand side response are sequentially configured, an updated power distribution network state is obtained, whether convergence conditions are met or not is judged, and if yes, an optimal configuration scheme including current energy storage, SOP and DR configuration and the current critical bearing capacity is output; otherwise, returning to re-optimize. Compared with the prior art, the power distribution network can safely and efficiently consume the high-proportion distributed new energy, and the bearing capacity of the power distribution network is effectively improved.

The invention belongs to the technical field of power distribution, and discloses a direct current transformer soft switch and a control method.The direct current transformer soft switch comprises a medium-voltage direct current bus and low-voltage direct current buses, the medium-voltage direct current bus is electrically connected with a modular multi-level multi-port direct current converter, and the modular multi-level multi-port direct current converter is electrically connected with a plurality of low-voltage direct current converters; the plurality of low-voltage direct-current converters are electrically connected with a low-voltage direct-current bus and are used for realizing bidirectional power transmission from medium-voltage direct current to low-voltage direct current; according to the method, the medium-voltage side inductance value is reduced, the medium-voltage side current ripple is enabled to pass zero, the M3DC operates in an approximate critical conduction mode, a constant valley current control strategy is adopted, the minimum value of the medium-voltage side inductance current is controlled to be constant under different working conditions, and then zero-voltage switching-on of a switching device in a wide operation range and zero-current switching-off of an anti-parallel diode are achieved.

The invention provides a power distribution network post-disaster intelligent recovery method and device based on a RainbowDQN algorithm. The method comprises the steps of obtaining a power distribution network model and a preset N-3 fault combination, and constructing a Markov decision environment model of a power distribution network load recovery task when a line has an N-3 fault; setting a target function and a constraint condition of the Markov decision environment model; training an intelligent agent in the Markov decision environment model by adopting a RainbowDQN algorithm added with a self-adaptive action mask to obtain a trained intelligent agent; and parameter information of the power distribution network with the N-3 line fault is transmitted to the trained intelligent agent, and the intelligent agent outputs a load recovery strategy of the power distribution network with the N-3 line fault. According to the method, the flexible soft switching technology is utilized to quickly isolate an affected area when a fault is caused by a natural disaster, so that the risk of fault diffusion is reduced, the power supply grid is quickly subjected to necessary topological adjustment after the disaster, and efficient distribution of power support after the disaster is realized.

According to the PCIe Switch system and the PCIe switch, a PCIe hardware IP is used as a bottom layer, and a basic PCIe interface function for physical layer and link layer management is provided; and identifying and configuring all connected devices to construct a device address routing mapping table through a Soft Switch IP mounted on the PCIe hardware IP, and determining a specific target of data transmission based on the constructed mapping table so as to route the data to a specific position of the corresponding device. According to the invention, flexible equipment enumeration can be carried out by selecting a pure hardware mode or a software and hardware combined mode according to actual requirements, so that the data can be correctly and efficiently transmitted to the target endpoint from the source equipment, and the complex problems of address resolution and routing management are solved. Compared with the prior art, the method can replace the existing PCIe Switch IP of a manufacturer, provides higher flexibility and expansibility, obtains better balance in the aspect of cost control, and is suitable for various applications needing large-scale PCIe equipment connection, virtualization and high-speed data exchange.

The present invention discloses a method for siting and sizing a flexible soft switch of a distribution network based on mixed second-order cone programming, including: acquiring interconnected flexible distribution system data; establishing and optimizing, based on the interconnected flexible distribution system data and an interconnected flexible distribution system constraint, a flexible soft switch siting and sizing model with a minimal daily comprehensive operation cost as an objective; and acquiring an optimal flexible soft switch siting and sizing solution by using combination of an improved sparrow algorithm and second-order cone programming to solve. The present invention is both reliable and economic.

The invention discloses a method for improving the toughness of a power distribution network containing an energy storage type flexible soft switch in a fault state, and belongs to the field of power systems and automation of the power systems, and the method comprises the steps: extracting time sequence data and fault information of a distributed power supply and a load; according to the method, an integrated optimization model integrating fault isolation, multi-stage dynamic maintenance, network reconstruction and energy storage type flexible soft switch cooperation is constructed, minimization of whole-process power loss and branch and device loss is taken as a target, and multiple constraints including time sequence balance, device operation, maintenance resources and decoupling power flow are taken into consideration. Wherein the energy storage type flexible soft switch realizes cross-period energy time shifting through an embedded energy storage system; and a mixed integer second-order cone programming algorithm is adopted to carry out rolling solution, and island division, a maintenance sequence and a device operation strategy are synchronously optimized in each stage. According to the method, global coordination and space-time energy management of the multi-stage recovery process can be realized, and the power supply recovery capability and toughness of the power distribution network under the extreme fault are remarkably improved.

The invention discloses an energy storage type intelligent soft switch double-layer optimization site selection method based on improved whale algorithm and second-order cone programming cooperation, and belongs to the technical field of power distribution networking and optimization operation, and the method comprises the steps: collecting and preprocessing the basic data of a power distribution network; a double-layer optimization model with the minimum daily operation cost of the system as the target is established, the upper layer takes the installation position of the energy storage type intelligent soft switch as a decision variable, and the lower layer takes the three-port power transmission value as a decision variable and constructs constraints based on the power flow equation after second-order cone relaxation and the energy storage operation limitation; an upper layer site selection problem is solved by adopting an improved whale optimization algorithm introducing a self-adaptive inertia weight, a lower layer operation problem is solved by adopting a second-order cone programming method, and collaborative optimization is realized through double-layer interaction. According to the method, global collaborative optimization of planning and operation is realized, the solving precision and efficiency of the site selection problem are improved, and the system operation cost and the network loss are effectively reduced.

According to the power distribution network flexible networking planning method and system based on closed-loop optimization operation, based on a topological structure of an intelligent soft switch in a power distribution network, the weighted sum of an active power smoothness index and a reactive power supporting capability index is used as a flexible scheduling index; taking the weighted sum of the voltage deviation index and the power balance index as a closed-loop operation optimization index; taking the weighted sum of the flexible scheduling index and the closed-loop operation optimization index as an intelligent soft switch operation optimization target; establishing a target function of a multi-target optimization model based on the investment cost, the comprehensive operation cost and the operation optimization target of the intelligent soft switch in combination with the voltage quality index and the load balancing index of the power distribution network; power distribution network constraint conditions and active power constraints, reactive power constraints and capacity constraints of the intelligent soft switch are used as constraints of the multi-objective optimization model; and solving the multi-objective optimization model to obtain a flexible networking planning scheme of the power distribution network, thereby improving the operation efficiency, economy, safety and flexibility of the power distribution network.

The application discloses a single-stage bidirectional power conversion topology structure capable of realizing wide-range soft switching and a control method thereof. The bridge-in and bridge-between phase shift control of a double half-bridge circuit and a high-frequency switch matrix provides a basis for realizing soft switching of all power tubes. The soft switching of a wide voltage variation range is realized by real-time adjustment of a switching frequency according to the size of a port voltage. The bridge arm current connected with the primary side of a second transformer is the sum of the primary side current of the second transformer and the inductance current connected with the primary side of the second transformer in parallel. By designing the inductance value of the parallel inductance connected with the primary side of the second transformer, the bridge arm current connected with the primary side of the second transformer can be effectively changed, so that the soft switching realization range of the switching tube of the bridge arm connected with the primary side of the second transformer under the wide power transmission range can be expanded.

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

The invention relates to an intelligent energy storage soft switching configuration method considering refined photovoltaic power generation potential evaluation. The method comprises the following steps: constructing a photovoltaic power generation potential evaluation model based on a physical model chain; constructing an intelligent energy storage soft switch model; and configuring the obtained intelligent energy storage soft switch model. An energy storage device is integrated to a direct current port of an SOP, an intelligent energy storage soft switching device model is constructed, a power distribution network has space-time flexible adjustment potential, an intelligent energy storage soft switching configuration method considering photovoltaic power generation potential evaluation is provided, a space power transfer-time energy scheduling two-dimensional cooperation mechanism of an E-SOP is utilized, and the power distribution network is optimized. And the energy production and elimination among the regions are balanced, so that the random fluctuation of the source and load sides of the power distribution network can be better relieved.

The invention discloses a multi-mode electric energy conversion system and a method thereof, and relates to the technical field of power electronic conversion, the system comprises a signal acquisition module, a mode discrimination module, a soft switching control module and a switching execution module, the signal acquisition module acquires an input voltage, an output voltage, a load current and a switching tube temperature signal; the mode judgment module determines a target working mode according to an input voltage interval and a load rate interval, dynamic switching among a full-bridge phase shift mode, a half-bridge mode and an interleaving parallel mode is achieved, the soft switching control module generates a soft switching time sequence signal, a main power switch tube is enabled to achieve zero-voltage switching, and the main power switch tube is enabled to achieve zero-voltage switching. The switching execution module adopts a current ramp control strategy to execute mode switching, the switching time is less than 5ms, the voltage fluctuation is less than 3%, and the global efficiency is greater than 95% and the peak efficiency is greater than 98% under the conditions of wide voltage and wide load.

The invention discloses a locating and sizing method and device for an intelligent soft switch in a power distribution area, terminal equipment and a storage medium, and belongs to the field of power distribution network optimization. The method comprises the following steps: constructing a bilevel planning model, a power distribution network operation constraint and an energy storage equipment constraint according to electrical parameters, distributed energy parameters, energy storage parameters and cost data; by taking the minimum total operation cost of the system as a target, repeatedly executing a locating and sizing optimization operation on the bilevel programming model until a preset number of iterations is reached, and obtaining the installation position and the installation capacity of the intelligent soft switch; the optimization operation comprises solving the current installation position and capacity of an upper-layer intelligent optimization model of the bilevel planning model; if the preset number of iterations is reached, the final installation position and capacity are determined; and if not, inputting into a lower-layer operation scheduling model to construct intelligent soft switch operation constraints, solving the lower-layer model under the three constraints, and updating the total operation cost of the current system. According to the invention, the problem of multi-zone-area multi-intelligent soft switch collaborative optimization in the prior art is solved.

Embodiments relate to a method and apparatus for a soft satellite switching procedure. A method for a user equipment (UE) in communication with a source satellite to switch to a target satellite includes the following operations: receiving a signal from the source satellite; and determining whether to switch to the target satellite based upon a hard switch or a soft switch.

The invention relates to a power distribution network collaborative optimization operation method and device and a medium, and the method comprises the steps: a day-ahead global optimization stage: constructing a day-ahead source-network-load-storage collaborative optimization model, and taking the minimization of the day-ahead total operation cost containing the green certificate transaction cost as an optimization target, day-ahead scheduling is carried out on a distributed power supply, an interconnection switch, an interruptible load, a transferable load and a three-terminal intelligent soft switch containing energy storage in the active power distribution network; and an intra-day rolling optimization stage: constructing an intra-day rolling optimization model, and performing intra-day scheduling on a switchable capacitor and a three-terminal intelligent soft switch containing energy storage in the active power distribution network by taking the minimum intra-day total operation cost containing voltage offset cost as an optimization target. Compared with the prior art, the day-ahead-intra-day two-stage collaborative optimization method is provided based on the dynamic response characteristics of the equipment, the refinement level of a scheduling scheme is remarkably improved through layered progressive optimization, and the consumption rate of new energy is greatly improved.

The embodiment of the invention provides an intelligent power grid voltage stability control method, which comprises the following steps: acquiring real-time data of a multi-source load, constructing a load prediction model based on historical load data and real-time acquired data, and calculating a load prediction deviation rate; analyzing impedance ratio change characteristics of the power distribution network, and identifying dynamic voltage sensitive regions in different operation states according to the impedance ratio change characteristics; dynamically adjusting coupling output parameters of active power and reactive power of the intelligent soft switch based on the load prediction deviation ratio and the dynamic voltage sensitive area; and optimizing the power flow distribution of the power distribution network in real time according to the output parameter change of the intelligent soft switch so as to inhibit the voltage sudden rise and voltage sudden drop at the tail end of the power distribution network. According to the scheme of the embodiment of the invention, cooperative regulation and control can be carried out on active-reactive coupling output of the intelligent soft switch so as to solve the problem of terminal voltage sudden rise / sudden drop caused by bidirectional power flow of the power distribution network.

The invention discloses a flexible interconnected power distribution network fault recovery method and a related device. The method comprises the following steps: constructing a loss model of an energy storage type intelligent soft switch; generating a typical photovoltaic output scene in combination with a principal component analysis method and a K-means clustering algorithm; establishing a target function with minimum weight of recovery load and system loss as a target, and constructing constraint conditions to obtain a fault recovery model of the flexible interconnected power distribution network; and in combination with second-order cone programming and an improved sparrow search algorithm, solving the fault recovery model of the flexible interconnected power distribution network to obtain a power supply scheme which is used for fault recovery of the flexible interconnected power distribution network. The method has a good power supply recovery effect, the influence of the DG permeability on power distribution network fault recovery is considered, and reliable technical support is provided for power distribution network planning and operation.

The application relates to the technical field of power distribution networks of power systems, and discloses a fault post-recovery control method for a power distribution network containing flexible soft switches, which comprises the following steps: after a fault occurs, the original main station converter is exited, the active power, the reactive power and the rated capacity of the remaining converters are collected to calculate the dynamic capacity margin, the electrical distance from each converter node to the load center of the system is calculated, the comprehensive score is obtained based on the capacity margin and the electrical distance weighting, the converter with the highest comprehensive score and the capacity margin greater than the preset threshold is selected as the new main station, and the control mode of the new main station is switched; the main station selection mechanism based on the comprehensive evaluation of the dynamic capacity margin and the electrical distance is used to quickly establish a stable voltage frequency reference for the power failure area, the load shedding penalty sub-target and the load hierarchical and phased recovery strategy are used to preferentially guarantee uninterrupted power supply for the first important load under the condition that the transfer supply capacity is limited, and the influence of power failure on sensitive users is effectively reduced.

The invention discloses a gallium nitride soft switching high-voltage Buck voltage converter, belongs to the technical field of switching power supplies, and solves the problems of large device switching loss, high thermal stress, large voltage peak and high-frequency oscillation caused by a switching capacitor link in a traditional high-voltage Buck switched capacitor voltage converter by introducing an auxiliary soft switching link. The efficiency and the reliability of the system are improved; furthermore, by introducing a double-phase interleaving parallel structure, the current output capability of the power supply is improved, and the application in a higher power scene can be realized; meanwhile, by adopting the gallium nitride transistor, compared with the traditional scheme, the switching frequency is improved, the size of a passive element is reduced, the integration level of a PCB is improved, the parasitic parameters of the system are reduced, the dead time and the duty ratio loss are reduced, and the system efficiency and the power density are further improved.

The invention provides a wireless electric energy transmission system and a control method, relates to the technical field of wireless electric energy transmission, and is used for realizing soft switching irrelevant to the load weight and the coupling coefficient so as to improve the system efficiency and reduce the thermal runaway risk. The wireless power transmission system comprises an inverter, a magnetic coupling structure, a rectifier and a controller, the input end of the inverter is electrically connected with the direct-current power supply end, and the output end of the inverter is electrically connected with the input end of the magnetic coupling structure; the input end of the rectifier is electrically connected with the output end of the magnetic coupling structure; the output end of the rectifier is connected with a load; the control end of the controller is electrically connected with the control end of the inverter; and the controller is configured to collect the voltage of the input end of the magnetic coupling structure in real time, compare the voltage with a preset upper threshold voltage and a preset lower threshold voltage, and output a driving signal according to a comparison result to control the on and off of the inverter, so that the inverter realizes zero-voltage switching in a full-power range.

The present invention discloses a coordinated optimization scheduling method, device, medium and equipment in the technical field of smart grid, aiming to solve the problems of slow response speed, limited regulation ability and insufficient intelligence in the prior art. It includes obtaining an optimization scheduling model based on dynamic networking and price incentive constructed in advance; solving the optimization scheduling model based on dynamic networking and price incentive according to the safe operation parameters of the target distribution network, the safe operation parameters of the microgrid and the price incentive strategy of the microgrid to generate an optimal scheduling scheme. By the organic combination of intelligent soft switches, dynamic networking and price incentive mechanisms, the present invention provides an efficient, intelligent and reliable coordinated optimization scheduling method for distribution network - microgrid, overcomes the deficiencies of the prior art in terms of response speed, regulation ability and intelligence level, and has remarkable technical innovation and practical application value.

The invention discloses a bidirectional DC-AC converter control method considering a soft switching condition and current optimization. According to the invention, the switching loss of the converter is reduced by optimizing the phase shift angle and the switching condition of the converter, and the energy transmission efficiency is optimized by minimizing the effective value of the current, so that the performance of the whole sodium battery energy storage system is improved. Specifically, based on the relation between the excitation inductance Lm and the current effective value Iprms, the phase shift angle of the converter is accurately controlled, the current transmission efficiency is optimized, and it is ensured that the zero-voltage switching condition of a primary side bridge arm and a secondary side bridge arm can be achieved in the working process, so that the loss of the converter is remarkably reduced, and the energy conversion efficiency is improved.

The invention discloses a flexible power distribution system planning method and system based on a long-short time energy storage type soft switch. The method comprises the following steps: establishing a source-network-load-storage cooperative operation framework of a flexible power distribution system; constructing a long-short time energy storage type soft switch model, wherein the long-short time energy storage type soft switch model is formed by integrating an energy type energy storage unit and a power type energy storage unit to a direct current side of a soft switch; an integrated planning model of the flexible power distribution system is established, wherein the integrated planning model comprises configuration and operation constraints of source side, network side, load side and storage side equipment based on a collaborative operation framework, and an optimization objective function with the purpose of minimizing the total cost of the whole life cycle of the system; and solving the integrated planning model, and determining an optimal configuration capacity and an operation strategy of each device in the system. Through the introduction of the long and short time energy storage type soft switch, although the early equipment investment is increased, the total cost of the scheme is reduced in the whole planning period due to the operation benefit brought by the long and short time energy storage type soft switch.

The present invention provides a database security control method, apparatus, electronic device, and storage medium, including: sending database operation and maintenance instructions through a database operation and maintenance tool, and after the database soft switch performs security control on the database operation and maintenance instructions, forwarding them to the database; the database soft switch uses a similarity cycle analysis algorithm to simulate the database, enabling the database to perform session keep-alive communication with the database operation and maintenance tool; calling the operating system kernel, and using a multi-threaded mechanism and a fast read-write data cache queue to perform network traffic collection and analysis. In view of the problem that various database tools need to be customized and developed for database operation and maintenance control, the present invention realizes the centralized control of database operation and maintenance through the database soft switch, without the need to transform the database tools. At the same time, it solves the problem of maintaining the keep-alive of the database tools during the waiting period for the approval of the vault triggered by the instructions, and calls the operating system kernel, uses multi-threading and a fast read-write data cache queue to improve the traffic processing ability, ensuring the operation and maintenance efficiency.

The invention discloses a power distribution system adaptive operation method considering differentiated demands based on joint learning. The method comprises the following steps: 1, establishing a reconfigurable soft switch model; 2, constructing a combined learning agent based on a soft actor-commentator network and a dual deep Q network; 3, performing off-line learning on the reconfigurable soft switch in the established joint learning agent to realize rapid and accurate decision of the reconfigurable soft switch in a time-varying environment; and 4, proposing an adaptive control strategy under the support of the reconfigurable soft switch, including three control modes of loss reduction control, voltage optimization and demand response, and designing an adaptive switching mechanism capable of flexibly switching among multiple modes. Differential regulation and control requirements of the power distribution system are considered, and the flexibility and adaptability of the system are improved by using the reconfigurable soft switch, so that adaptive operation of the power distribution system is realized.

The invention discloses a reactive power optimization control method suitable for a series resonance dual active bridge, relates to the technical field of power electronic converter control, and solves the problem that an effective compensation scheme is not provided for an incomplete soft switching problem caused by dead time in the prior art. And the requirement of all-working-condition efficient operation in engineering application is difficult to meet. Based on triple phase shift control, the optimal phase shift angle combination is accurately solved through the power factor Lagrange function and the KKT condition, the reactive power of the primary side or the secondary side can be counteracted in a targeted manner, and the energy circulation of the resonant cavity is effectively inhibited; meanwhile, soft switching boundary analysis and critical phase compensation are combined, so that zero-voltage switching of all main switching tubes in a full-voltage gain and full-load range can be ensured, and switching loss is reduced; and a mode switching mechanism is designed in control logic to adapt to dynamic working condition response requirements, so that the energy transmission efficiency and working condition adaptability of the series resonance dual-active bridge converter are greatly improved.

The invention relates to the technical field of power systems, and particularly discloses a medium-low voltage collaborative optimal control method for an active power distribution network based on double-layer reinforcement learning. Historical data of distributed photovoltaic output, key node voltage, power flow reverse transmission rate of a transformer in a transformer area, tap state of a medium-low voltage transformer, port power of a medium-voltage intelligent soft switch and network loss are collected through a measuring device; training a two-stage neural network based on historical data; taking the two-stage neural network as a reinforcement learning off-line training environment, and constructing a double-layer Markov game model; and deploying the trained agent parameters to medium and low voltage control terminals to realize medium and low voltage multi-target cooperative control containing multiple types of adjusting devices. The method has the advantages that the double-layer reinforcement learning algorithm integrated with the attention mechanism is proposed to solve the multi-time scale equipment regulation and control problem, the sum of lower-layer agent rewards serves as a part of an upper-layer agent, and active power distribution network medium-low voltage collaborative optimal control is achieved.