750 results about "Distribution power system" patented technology

The invention provides an intelligent power distribution load prediction and adaptive scheduling method, and aims to improve the response capability and operation efficiency of a power distribution system to load fluctuation. According to the method, historical load data, real-time meteorological information and user power consumption behavior data of a target power distribution area are collected, a multi-dimensional input data set is established, a short-term load prediction model is constructed based on the data set, and prediction of future load levels of multiple feeder lines and key nodes is achieved. According to a prediction result, potential voltage deviation, load imbalance and equipment overload risks are identified, and a dynamic scheduling control strategy is generated by adopting a rolling horizon optimization method in combination with a power grid topological structure and operation constraints; the strategy comprises control measures such as transformer tap position adjustment and capacitor bank switching; through issuing a scheduling strategy to an equipment control unit, active adjustment is completed before load change, voltage stabilization, load balancing and energy optimization are realized, and intelligent and adaptive operation guarantee is provided for a power distribution system.

The invention discloses an intelligent power distribution layered self-healing fault isolation and power supply recovery method, which is suitable for realizing rapid fault isolation and power supply recovery of a non-fault area when a power distribution system has a fault. According to the method, a hierarchical control framework is adopted, and intelligent switch equipment on the lower layer is responsible for collecting the current and voltage states of a line in real time and immediately completing local identification and fault section removal after a preset fault signal is detected; the fault information is then uploaded to a power distribution automation master station on the upper layer, the master station analyzes a recoverable power supply area in combination with the current network topology and generates a network reconstruction scheme, and a non-fault area is switched to a standby power supply path by controlling an interconnection switch; the system supports the backtracking analysis of historical data such as waveform distortion and partial discharge signals before a fault, identifies a potential abnormal trend, optimizes an operation strategy, and achieves a self-adaptive early warning function. The method has the advantages of being rapid in response, clear in structure and high in autonomy, and the reliability and continuity of the power distribution system can be remarkably improved.

The invention relates to the technical field of tunnel power supply and distribution, in particular to a tunnel modular prefabricated cabin power supply and distribution intelligent substation self-adaptive regulation and control system based on edge calculation. Comprising an edge calculation and AI decision-making unit which is used for realizing rapid acquisition, processing and instant decision-making of tunnel power supply and distribution multi-dimensional data, generating a power supply and distribution adaptive regulation and control strategy by deploying calculation resources and a machine learning algorithm at edge nodes close to a data source, and converting the strategy into an executable regulation and control instruction; a cloud platform collaborative management unit; and an intelligent sensing and internet-of-things unit. According to the invention, hierarchical decision control of the tunnel power supply and distribution system is realized by constructing a hybrid architecture of edge computing and cloud platform collaboration and a priority judgment mechanism; according to the invention, multi-modal data are integrated through the multi-protocol communication link module and the full-scene data fusion analysis module, and data association analysis is realized through Kalman filtering, D-S evidence theory and other algorithms.

The invention discloses a direct-current arc fault diagnosis method and device with adaptive capacity. The method comprises the following steps: 1) collecting a current alternating-current component when a current direct-current system normally works; 2) extracting time-frequency domain characteristics of a current AC component, wherein the time-frequency domain characteristics comprise a current peak-to-peak value, a standard deviation and an amplitude reconstruction harmonic power sum; 3) performing multi-time-frequency-domain feature fusion based on mahalanobis distance to obtain arc detection features; 4) calculating an arc fault judgment threshold value based on a box plot method; 5) collecting a current AC component in real time to calculate a Mahalanobis distance, comparing the Mahalanobis distance with an arc fault determination threshold, and recording an arc event; the method has the advantages that the system adaptability is high, the detection rate is high, the false alarm rate is low, and the method can be widely applied to high-voltage and low-voltage direct-current power distribution systems such as airplanes, vehicles and ships.

The invention provides a network security multi-mode intelligent detection system and method, relates to the technical field of network security management, and is applied to a power distribution system which comprises a communication device and a power distribution device. The network security multi-modal intelligent detection system comprises a multi-modal data acquisition module used for acquiring network flow data, equipment characteristic data and behavior data of a power distribution system; the detection engine module is used for analyzing and detecting the network flow data, the equipment characteristic data and the behavior data to obtain a detection result; and the decision and response module is used for performing risk assessment according to the detection result based on a preset risk assessment model to obtain a risk grading result and a response strategy. According to the invention, comprehensive monitoring and deep analysis of the network security condition of the power distribution system are realized. By integrating multi-modal data, the limitation of a traditional single data detection mode is effectively overcome, and the accuracy and timeliness of threat detection are improved.

The invention discloses a reconfiguration-based operation optimization method for a power distribution system containing a reconfigurable soft switch. The method comprises the following steps of: 1, constructing a self-energy-storage type reconfigurable intelligent soft switch topology based on asymmetric voltage source converter capacity and feeder line selection; 2, modeling is carried out on the self-energy-storage recombined intelligent soft switch; and 3, modeling the reconfiguration-based flexible power distribution system containing the reconfigurable soft switch, and obtaining an optimal operation strategy of the power distribution system by solving the optimization operation model. According to the invention, the multi-element controllable equipment of the power distribution system can be reasonably utilized to improve the utilization rate of the traditional multi-terminal intelligent soft switch to the capacity of the voltage source converter, and the maximum transmission power of the traditional multi-terminal intelligent soft switch can be improved, so that the operation loss of the power distribution system can be reduced, and the new energy consumption can be improved.

The invention discloses an E-SOP-based interconnected power distribution area voltage optimization regulation and control method, and the method comprises the steps: carrying out the analysis of an E-SOP-containing power distribution area interconnection system structure, and constructing an E-SOP mathematical model; establishing a voltage-power sensitivity calculation model, and determining the optimal access position of the E-SOP; an E-SOP interconnected power distribution area planning model with the lowest comprehensive cost as the target is constructed, and the optimal capacity configuration of the E-SOP is determined; establishing a multi-objective function E-SOP interconnection power distribution area operation optimization model and solving the model; and determining the optimal position, capacity and operation scheme of the E-SOP according to the solving result. According to the method, a three-terminal SOP (E-SOP) containing an energy storage system is applied to an interconnection system of a power distribution area, the flexibility and rapidity of a power distribution network can be improved from the multi-dimensional aspects of space, energy and power of a power distribution system, and voltage optimization of the power distribution area is achieved.

The utility model belongs to the technical field of medium-voltage power distribution systems, and discloses an isolating switch device and a switch cabinet, the isolating switch device comprises an insulating rod, a conductive block, a conductive sheet and an operating mechanism, the conductive block is sleeved on the insulating rod, the conductive sheet is fixedly connected with the conductive block, and the operating mechanism drives the conductive sheet and the conductive block to rotate through the insulating rod. Therefore, the conducting strip is selectively connected or disconnected with the circuit breaker connector bar, and the conducting block is electrically connected with the voltage transformer in the rotating process. An isolating switch device is additionally arranged between a circuit breaker and a voltage transformer in a switch cabinet, an operating mechanism is utilized to drive a conducting strip and a conducting block to rotate through an insulating rod, the conducting block and the voltage transformer keep electrical connection in the rotating process, the position of the conducting strip is changed in the rotating process, and then the conducting strip is selectively connected with or disconnected from a circuit breaker connector bar. The structure is simplified, the number of elements is reduced, flexible operation can be achieved, and the stability and reliability of the disconnecting switch device can be guaranteed.

The invention provides a high-voltage power supply and distribution system for an electric vertical take-off and landing aircraft, and belongs to the technical field of power supply and distribution regulation control systems, and the system comprises a main bus bar module which is used for the current collection and distribution of an energy storage battery and a ground DC bus high-voltage power supply, and is provided with a fuse for overload cut-off; the output bus bar module comprises six mutually-independent motor load output channels and two mutually-independent high-voltage output channels, and each motor load output channel supplies power to the two symmetrically-arranged motors at the same time and is used for distributing 12 motor loads and 2 high-voltage output loads; the power-on buffer module is used for power-on buffer of 12 paths of motor loads and restraining power-on impact current; the self-locking control module has a motor load output control self-locking function, and can keep normal output of motor load current under the condition that the monitoring unit fails; and the monitoring unit module is used for monitoring the input voltage, the output voltage and the load current, and performing power-on buffer control and high-voltage contactor self-locking control on the motor load.

The invention belongs to the technical field of on-satellite intelligent information processing power supply and distribution, and discloses a power supply and distribution system of an on-satellite real-time information processing system. The system is composed of a short circuit protection circuit (10), a surge suppression circuit (20), a satellite real-time processing system switching circuit (30) based on a magnetic latching relay, an EMI filter (40), a DC-DC power supply module (50), a relay-based power supply and distribution switching circuit (60), a DC-DC power supply module (70) and a DC-DC power supply module (80). According to the invention, the power supply problem of any dynamic redundancy unit in the satellite real-time information processing system is solved, and the sneak path problem caused by misoperation in the use process is avoided.

The invention provides a fault processing device and method compatible with arc suppression coil operation, and relates to the technical field of power supply equipment, the device comprises an arc suppression coil module and an intelligent grounding module, and the arc suppression coil module and the intelligent grounding module are connected in parallel; the arc suppression coil module comprises a first front circuit breaker, a first grounding transformer, an arc suppression coil and a first current limiting resistor, the wire inlet end of the first front circuit breaker is connected with a bus of the power distribution system, the output line of the first front circuit breaker is connected with the wire inlet end of the first grounding transformer, and the neutral point of the first grounding transformer is connected with one end of the arc suppression coil. The other end of the arc suppression coil is connected with a current-limiting resistor I, and the other end of the current-limiting resistor I is grounded; the intelligent grounding module comprises a front circuit breaker II, a fault phase selection sub-module and a fault line selection sub-module, a bus of the power distribution system is connected with a wire inlet end of the front circuit breaker II, the fault phase selection sub-module is connected with the front circuit breaker II in series and then is grounded, and the fault line selection sub-module is connected with the fault phase selection sub-module in parallel.

The invention discloses a power distribution network power supply recovery method and system considering multi-type distributed power supply cooperation, and the method comprises the steps: enabling a fault section to be successfully isolated, and carrying out the non-voltage switching-on of a network-following type DG in an intertripping power-losing region; constructing a source-load balance island based on the network construction type DG, and preferentially recovering an important load; when there is no contact, the upstream switch of the fault point carries out non-voltage reclosing to process an instantaneous fault, and island grid connection is planned; when connection exists, an optimal connection switch is optimized according to the capacity of a connection line and the capacity of a power-losing load, closing is carried out after an unrecoverable section is cut off, and staged power restoration is achieved by circularly cutting off the unrecoverable load, grid connection of the grid-following type DG and updating the recoverable capacity by considering the capacity of the adjacent grid-following type DG. And when an island adjacent section is recovered, the connected switches are subjected to synchronization grid connection. According to the invention, through a multi-type DG cooperative control strategy, the maximum capacity safety recovery of a non-fault section load is realized, the active support capability of the DG is fully exerted, and the reliability of the power distribution system is remarkably improved.

The invention belongs to the technical field of wireless communication networks, and particularly discloses a LoRa communication system for power distribution network line fault detection and a use method of the LoRa communication system for power distribution network line fault detection. For each node, continuously monitoring changes in voltage, current and temperature monitoring ranges of a line with high voltage acquisition precision and a specific current signal sampling rate, removing noise influence by combining an environmental interference filtering technology, and generating an original monitoring data set according to a preset data acquisition frequency; the data preprocessing module is used for carrying out standardization processing on the collected signals according to the original monitoring data set; the invention aims to solve the problem of logic association caused by mutual fusion of low monitoring precision, high abnormal false alarm rate, unstable data transmission and slow fault isolation response in a traditional power distribution system in the prior art.

The invention discloses a power distribution system control strategy optimization method and system. The method comprises the steps of obtaining a graph structure of a power distribution network of a power distribution system; wherein the graph structure comprises nodes and edges; constructing an action space and a reward function of the power distribution network according to the power characteristics of the power distribution network; according to the action space and the reward function, training the GNN and reinforcement learning network by adopting the graph structure to obtain the trained GNN and reinforcement learning network; and optimizing a control strategy of the power distribution system according to the trained GNN and the reinforcement learning network. According to the method, the GNN and reinforcement learning network method can be combined, more intelligent decision and strategy optimization can be obtained through the graph structure of the power distribution network, the source network load storage distributed optimal coordination and management in the power distribution system can be realized, the coordination and accuracy of the control strategy can be improved, the overall strategy optimization effect can be improved, and the method is suitable for the complex power system optimization problem.

The sulfur hexafluoride insulation ring main unit comprises a ring main unit power distribution platform, a ring main unit information base, a ring main unit working condition unit, a power distribution interference unit, a ring network distribution unit, a power regulation and control unit and a power distribution management unit. According to the method, power distribution stability performance analysis is carried out from two points of working characteristics and working parameters of the target ring main unit, and analysis is carried out in combination with the sulfur hexafluoride gas interference degree of the target ring main unit, so that the working stability and continuity of the target ring main unit are improved; ring network distribution working performance risk analysis is carried out on the working condition information of the target ring main unit in an information feedback mode, so that the safety and reliability of the power distribution performance of the target ring main unit are improved, and electric power adjustment demand evaluation analysis is carried out on the electric energy management data. Therefore, the load distribution scheme of the target ring main unit is adjusted according to the information feedback condition, and the reasonable distribution of power resources and the operation efficiency of a power grid are improved.

The invention discloses a high-precision transformer fault detection method and system, relates to the technical field of transformer detection, is used for solving the problems of insensitive fault characterization and delayed diagnosis under a light load condition, and judges whether to enter a load judgment mechanism or not by acquiring input side access voltage information and counting low-load accumulated duration. When entering a load discrimination mechanism, detecting the start-stop behavior of a load branch and the temperature rise trend of a winding, calculating a light load index, identifying a light load state, carrying out region division on an iron core, collecting magnetic flux density data, and calculating iron loss balance characteristics aiming at iron loss deviation which is easy to occur under a light load condition; the insulation degradation coefficient is calculated by fusing the oil temperature peak value and the dielectric loss factor, and the abnormal index is generated with the iron loss balance characteristic, so that the early warning of the early hidden fault of the transformer can be realized in a light load scene in which the traditional temperature rise and current indexes are insensitive, and the operation reliability and maintenance efficiency of the transformer in a power distribution system are improved.

The invention discloses a fault detection method and device for a power distribution system, and a terminal equipment storage medium, and the method comprises the steps: dividing a target power distribution system into a plurality of power distribution regions, and laying current sensors between the power distribution regions, so as to enable each current sensor to obtain a current vector and a current value at each moment; constructing a current identification matrix of the target power distribution system according to the current vectors of the current sensors; wherein each element in the current identification matrix represents the current flow direction of each power distribution area; for each current sensor, calculating a current phase vector at each moment according to a current value and a current vector at each moment and the current identification matrix; and determining a fault current sensor and a fault power distribution area according to the current phase vector at each moment, the preset difference threshold value of each current sensor and the current identification matrix. According to the invention, the fault detection efficiency and the fault detection accuracy can be improved.

The invention discloses a short-circuit current limiting and short-circuit recovery transient voltage control device and method for an aviation three-stage power generation system, and the device comprises a three-stage power generator, a power generator controller, a current sensor, a voltage and current collection module, and an asymmetric half-bridge excitation control circuit. Collecting the output current iL and voltage UL of the generator through a digital processor of the generator controller; when short circuit occurs, the given voltage USet of the voltage regulating loop is linearly reduced in a piecewise mode according to the relation between the iL and a preset threshold value, so that the generator works in a constant power interval; and when the short circuit is recovered, closing the upper / lower power tubes of the asymmetric half-bridge excitation control circuit according to the relationship between UL and a preset threshold value in a grading manner, and triggering a negative-pressure follow-current mode of a main excitation winding of the generator controller to quickly extinguish the field. The method can adapt to different generators without adjusting hardware circuit parameters, has no motor ablation risk during short circuit, has transient voltage less than 350V after short circuit recovery, has no power supply interruption in the whole process, has response delay less than 1ms, and greatly improves the safety and robustness of an aviation power supply and distribution system.

The invention provides a high and low voltage power distribution cabinet remote operation and maintenance management and control system based on cloud computing, relates to the field of remote operation and maintenance management, and improves the accuracy and operation and maintenance efficiency of power distribution cabinet fault early warning. The method comprises the following steps: firstly, acquiring sensing data through an edge intelligent sensing module, performing multi-dimensional correlation analysis based on a static safety threshold, identifying an abnormal trend with spatial-temporal correlation, and generating a preliminary early warning; then, a cloud platform prediction decision module drives the digital twin model to carry out dynamic simulation, and a predictive maintenance strategy and a dynamic safety threshold are generated in combination with a prediction algorithm of a historical performance decline curve; and finally, the adaptive control execution module optimizes subsequent analysis by using a dynamic threshold value, and triggers a differential control action from monitoring adjustment to emergency isolation according to a strategy type. According to the invention, by constructing the closed-loop intelligent operation and maintenance architecture of cloud-side cooperation, the operation and maintenance mode transformation from passive response to active prediction is realized, and the reliability and safety of the operation of the power distribution system are significantly improved.

The invention belongs to the technical field of ship power distribution, and particularly discloses a double-bus redundant direct-current power distribution system for a ship. Comprising a first direct-current busbar left, a first direct-current busbar right, a second direct-current busbar left, a second direct-current busbar right, a first circuit breaker, a second circuit breaker, a lithium battery pack, a first propulsion inverter cabinet, a first daily inverter cabinet, a second propulsion inverter cabinet, a second daily inverter cabinet, a direct-current voltage stabilizer and a system charging socket box. According to the invention, through setting the first direct-current busbar left, the first direct-current busbar right, the second direct-current busbar left, the second direct-current busbar right and the switching relation thereof, and adopting an operation mode that one group of busbars works and the other group of busbars is standby, flexible and balanced distribution of a power supply and a load is realized, and all loops can work without power failure; once any busbar or branch has a fault, the standby busbar is immediately started so as to start the standby loop, so that no power loss and no power reduction of the whole ship are ensured, and all equipment and components of the whole system are subjected to redundancy design so as to ensure that the power distribution system always supplies power normally.

The invention discloses a distribution line inter-phase permanent fault identification method and system based on SOP detection, and relates to the technical field of active injection protection. Based on an active detection idea, when an inter-phase short-circuit fault occurs in a distribution line containing SOP, a fault current limiting control measure is firstly started; limiting the output current of the fault side converter to be zero so as to enable the fault to extinguish arc; secondly, injecting pilot frequency positive sequence detection signals to obtain response characteristics by adopting a constant current injection strategy; solving the permanent fault equivalent model, and carrying out permanent fault identification by utilizing voltage structure similarity based on a model identification idea; and finally, fault isolation and power supply recovery are carried out based on a fault property identification result. Additional injection equipment is not needed, the fault property can be effectively judged, the fault section can be quickly determined under the permanent fault, and the power supply reliability of a power distribution system can be improved.

The invention discloses an unattended power distribution room intensive power distribution system and method based on machine learning, and the method comprises the steps: collecting the operation data of an unattended power distribution room, executing the preprocessing, and generating a standardized input data set; constructing a topology, working condition and equipment feature association relationship to form a three-dimensional coupling feature structure; inputting a hierarchical graph time sequence decision network, and fusing topology and time sequence characteristics to output candidate control actions; constructing a dynamic feasible region according to the joint features, and screening a safety action set meeting constraints; inputting into a topological reversible neural differential control module, predicting transient response and optimizing an execution action; and issuing a control instruction, collecting feedback, and triggering model increment update to realize closed-loop optimization. According to the invention, by introducing a hierarchical graph time sequence decision network and a topological reversible neural differential control mechanism, intelligent intensive scheduling and self-learning closed-loop optimization control of the unattended power distribution room are realized.

The utility model provides a fuse state monitoring circuit and a power distribution system, the fuse state monitoring circuit comprises a fuse connected between a power supply and a load, and the other end of the load is grounded; two ends of the fuse are respectively connected with a first resistor and a second resistor, and the other end of the first resistor and the other end of the second resistor are connected in series with a third resistor to be grounded after being connected; the fuse protection circuit further comprises a voltage sampling circuit which is connected with the voltage sampling end of the third resistor through a sampling channel, and the state of the fuse is monitored according to the sampling voltage of the voltage sampling circuit to the third resistor. According to the invention, state monitoring and voltage monitoring of the fuse are realized by differentiating voltages at two ends of the fuse and connecting the resistors in series, voltage detection of a circuit can be realized, state monitoring of the fuse can also be realized, and the fuse monitoring circuit has the advantages of simple structure and low cost.

The invention discloses a stability evaluation method, system and device of a power system and a medium, and the method comprises the steps: obtaining the load parameters of each node in a power distribution network, and determining the voltage amplitude, first active power and first reactive power of a transformer substation bus based on the load parameters; based on the voltage amplitude, the first active power and the first reactive power, inputting a preset power distribution system model to obtain a first sensitivity matrix, a second sensitivity matrix and a plurality of sensitivity vectors, and based on the first sensitivity matrix, the second sensitivity matrix and each sensitivity vector, obtaining a plurality of sensitivity vectors; the power distribution system model is obtained by coupling a power supply system model and a power distribution network model at a substation bus; and evaluating the stability of the power system based on the power flow distribution. According to the invention, the accuracy and comprehensiveness of stability evaluation of the power system can be improved.

The invention relates to the field of power system monitoring and management, and particularly discloses an intelligent power monitoring and management system, which evaluates the operation performance of a power supply and distribution system in various power supply modes by acquiring operation information of the power supply and distribution system in a mains supply mode, an uninterruptible power supply mode and an emergency generator power supply mode in a data center. Potential fault hidden dangers of various power supply modes of the power supply and distribution system can be found in time, and maintenance measures are taken in advance; the action duration, the voltage transient amplitude, the frequency transient amplitude and the switching success rate of switching between the power supply modes of the power supply and distribution system of the data center are collected, the performance of switching between the power supply modes of the power supply and distribution system is evaluated, then it is ensured that the power supply and distribution system can be rapidly and stably switched under different power supply conditions, and the continuity of power supply is guaranteed; the performance health condition of the power supply and distribution system is comprehensively evaluated by combining the independent operation and coordinated operation performance of the power supply and distribution system, so that the reliable operation of the power supply and distribution system is ensured.

The invention relates to the technical field of low-voltage power supply and distribution systems, and discloses a dual-power-supply quick switching circuit for a low-voltage power supply system, which comprises a main power supply, a standby power supply, a circuit breaker QF1, a circuit breaker QF2, a relay KA1, a relay KA2, an alternating current contactor KM1, an alternating current contactor KM2 and a load, the main power supply is connected with the circuit breaker QF1, one path of the QF1 is connected with the KM1, and the KM1 is connected with the load; the other path is connected with the KA1 from the QF1, the KA1 is connected with the KM2, the KM2 is connected with a coil of the KM1 and then connected with the zero line N, and the 1B phase line and the 1C phase line of the main power supply are further connected with the two ends of the coil of the KA1; the standby power supply is connected with the circuit breaker QF2, one path of the QF2 is connected with the KM2, the KM2 is connected with the load, the other path of the QF2 is connected with the KA2 from the QF2, the KA2 is connected with the KM1, the KM1 is connected with a coil of the KM2 and then connected with the null line N, and the 2A phase line and the 2B phase line of the standby power supply are further connected with the two ends of the coil of the KA2. When the main power supply is abnormal, the standby power supply can be quickly switched to avoid shutdown of the lower-level equipment, the standby power supply can be automatically switched after the lower-level short circuit fault is isolated, and the power supply reliability of the low-voltage power supply and distribution system is greatly improved.

The invention relates to the technical field of power distribution system protection, in particular to a high-safety energy storage system and a fault detection method thereof, the system comprises a measurement and control center, an insulation monitoring device, a bidirectional DC-DC converter and an integrated DC power distribution unit, the insulation monitoring device is connected with a DC power distribution bus, and the ground insulation state of the bus is monitored in real time; the input end of the bidirectional DC-DC converter is connected with the storage battery pack, and the output end is connected with the DC power distribution bus through the integrated DC power distribution unit to construct an electric energy distribution path. The integrated direct current power distribution unit comprises a circuit breaker, two voltage detection modules and two current detection modules, the first voltage detection module is connected with the direct current power distribution bus and the measurement and control center, the second voltage detection module is connected with the circuit breaker and the measurement and control center, and the circuit breaker is connected with the direct current power distribution bus. And the two current detection modules are connected in series between the output end of the bidirectional DC-DC converter and the circuit breaker to form a current detection loop. According to the invention, through multi-level real-time monitoring and centralized control, the safety and fault response capability of the system are significantly improved.

The invention discloses a voltage regulation and peak demand control method based on deep learning, and relates to the technical field of power distribution networks, and the method comprises the steps: S1, building a power distribution system model, a photovoltaic inverter model and an energy storage model, and expressing the coordination control of a photovoltaic inverter and energy storage as an optimal power flow problem; s2, establishing a deep reinforcement learning framework; and S3, solving a multi-objective optimization problem in voltage regulation and peak load management by using a soft behavior-criticality algorithm, and designing two different reward functions for daytime and nighttime. According to the voltage regulation and peak demand control method based on deep learning, by coordinating control strategies of a photovoltaic inverter and a battery energy storage system, the problems of voltage overrun and peak load caused by photovoltaic power generation fluctuation and load change in a power distribution network are effectively solved, and the algorithm is improved through a two-stage deep reinforcement learning control framework. The dynamic coordination control of the photovoltaic inverter and the battery energy storage system is realized.

The invention discloses a power distribution network operation parameter optimization identification method based on optimal power flow calculation, and relates to the technical field of power distribution systems, and the method comprises the steps: collecting historical operation parameters of each node of a power distribution network, screening to obtain a data collection priority of an optimal power flow output index, and reasonably distributing node sampling frequencies according to the data collection priority; measuring and collecting operation parameters of the power distribution network according to the distributed sampling frequency, carrying out pre-detection on the collected data, and meanwhile, carrying out adaptive anomaly judgment and sampling frequency dynamic adjustment and carrying out multi-scale decomposition and sensitivity analysis on node residual errors, so as to realize optimal power flow calculation time window adjustment driven by dynamic parameters; and the load model parameters are verified to ensure the accuracy and reliability of the parameter identification result. Through combination of historical data, real-time measurement and residual sensitivity information, transient disturbance, medium-term fluctuation and long-term trend can be considered in the operation parameter identification of the power distribution network, and the online precision of a load model and line parameters is improved.

The invention relates to the technical field of ship power systems, in particular to a double-power-station power distribution load balancing control method. Through cooperation of the steps of double-power-station load balancing judgment, load switching priority classification, power distribution network reconstruction objective function and parameter setting, minimum switching action frequency and corresponding load switching calculation, load power supply switching operation and the like, load power supply switching can be accurately controlled according to the real-time operation condition of a ship power grid. Load balancing control of double power stations is realized; function calculation is carried out through software, a result is output, personal judgment and decision of operators are not depended on in the double-power-station power distribution load balancing control operation process, and a switch needing switching control can be accurately calculated through a preset target function and parameters; according to the method, the difference condition of different loads is considered, in the process of controlling the change-over switch, the influence range of power failure can be effectively reduced, the possibility of short-time power loss of important loads can be reduced to the maximum extent, and the performance of a ship power distribution system is improved.