Abstract: A power grid reactive voltage control method and control system based on two-stage deep reinforcement learning, comprising steps of: building interactive training environment based on Markov decision process, according to a regional power grid simulation model and a reactive voltage optimization model; training a reactive voltage control model offline by using a SAC algorithm, in the interactive training environment based on Markov decision process; deploying the reactive voltage control model to a regional power grid online system; and acquiring operating state information of the regional power grid, updating the reactive voltage control model, and generating an optimal reactive voltage control policy. As compared with the existing power grid optimizing method based on reinforcement learning, the online control training according to the present disclosure has costs and safety hazards greatly reduced, and is more suitable for deployment in an actual power system.

Abstract: A method for estimating a state of a combined heat and power system is provided. The method include: establishing an objective function; establishing constraints under a steady-state operating stage; converting the objective function and the constraints by utilizing a Lagrangian multiplier to obtain a Lagrange function; obtaining a steady-state estimation result of the combined heat and power system based on the Lagrange function; calculating an energy transmission delay produced by each pipe; establishing a dynamic constraint of each pipe based on the steady-state estimation result and the energy transmission delay; converting the objective function, the constraints, and the dynamic constraint by utilizing the Lagrangian multiplier to update the Lagrange function; obtaining a dynamic-state estimation result of the combined heat and power system during a dynamic-state operating stage of the combined heat and power system based on the updated Lagrange function.

Abstract: The present disclosure provides a stability criterion for time-delay of cyber-physical power systems under distributed control, which relates to a field of cyber-physical power systems technologies.

Abstract: The present disclosure relates to a method, an apparatus and a storage medium for controlling a combined heat and power system, belonging to the field of power system technologies. The method discloses: establishing a decision model, the decision model including an objective function aiming to minimize a total cost of the first generators and the second generators, and constraints with respect to the first generators, the second generators and the heating exchange stations; solving the decision model to acquire operation states of the first generators, operation states of the second generators, and operations states of the heating exchange stations; and controlling the combined heat and power system, based on the operation states of the first generators, the operation states of the second generators, and the operations states of the heating exchange stations.

Abstract: The present disclosure provides a stable region determining method for distributed cyber-physical power systems with multiple time delays, including: first establishing a state space expression of the cyber-physical power systems under distributed control with multiple time delays; converting the state space expression to frequency domain through Laplace transform to obtain a characteristic equation for multiple time delays of the cyber-physical power systems under distributed control, and establishing a marginally stable characteristic equation with unified time delay to obtain a marginally stable characteristic equation for multiple time delays of the cyber-physical power systems under distributed control with unified time delay; in each time delay direction, solving a stable boundary for time delay of the cyber-physical power systems under distributed control; connecting the stable boundaries for time delays in all time delay directions, and generating a stable domain for time delays of the cyber-physical

Abstract: A planning method for a power distribution automation system based on a reliability constraint is provided. The method includes: defining installation states of components and principles of a fault isolation, a load transfer and a fault recovery after a branch fault occurs; establishing a reliability evaluation optimization model for a power distribution network based on a mixed integer linear programming, the reliability evaluation optimization model comprising a target function and constraint conditions; solving the reliability evaluation optimization model to obtain an optimum planning scheme; and planning the power distribution automation system based on the optimum planning scheme.

Abstract: A data-driven wind farm frequency control method based on dynamic mode decomposition. The method enables a low-dimension nonlinear dynamic feature of a wind power system to perform global capturing in a high-dimension space through a state transition matrix given by a Koopman operator theory, thus fewer data samples are necessary while control requirements are satisfied with respect to a model fitting accuracy. Meanwhile, a pure linear feature of a control model also provides a favorable foundation for fast on-line dynamic response, thereby satisfying response accuracy and speed requirements simultaneously in an actual control step.

Abstract: A method of assessing dynamic flexibility for a virtual power plant, which belongs to the technical field of operating and controlling a power system. The method equals a virtual power plant to an equivalent energy storage device and an equivalent generator and decouples a network constraint condition between the two types of devices through a Robust optimization method. Subsequently, by using a two-stage Robust optimization algorithm, parameters of the equivalent energy storage device and the equivalent generator are calculated and finally accurate depiction is realized on adjusting ability of a distributed resource, so as to provide a scientific decision basis for the virtual power plant to participate in grid control, such that it has a great value in an actual application.

Abstract: The present disclosure provides a scheduling method for a power system based on flexible HVDC (high-voltage direct current) and a pumped storage power station, which belongs to a field of power system control technologies. The method is applicable in a power system having a flexible HVDC system and a pumped storage power station. By establishing a scheduling model for the power system, which contains an objective function and multiple constraints, and solving the scheduling model, a capability of the pumped storage power station is used to adjust the unstable output of the renewable energy power generator and stabilize fluctuant of the renewable energy power generation, such that a power incoming into a load center presents a stable ladder pattern and an optimal scheduling scheme can be obtained.

Abstract: The present disclosure provides a method for optimizing transformation of automation equipment in a power distribution network based on reliability, including determining installation states of respective components in the power distribution network and operation criterions for fault isolation, load transfer and fault recovery after a fault occurred in a feeder segment; determining a target function which is a target function for minimizing a total transformation cost of the power distribution network; determining constraint conditions including reliability constraints; establishing an optimization model for evaluating the reliability of the power distribution network based on the reliability constraints in accordance with the target function and the constraints; and solving the established optimization model for evaluating the reliability of the power distribution network based on the reliability constraints to obtain optimal solutions as optimization results of the automation transformation state of the cir

Abstract: The disclosure provides a method for calculating a parameter changing domain of loads under a case that guarantees a constant locational marginal price in an electricity market, which relates to the electricity market field of the power system. With the method in the disclosure, the clearing model on the locational marginal price in the general form is established, and the safe changing domain of the locational marginal price with respect to the loads may be derived and calculated based on the first-order KKT condition expansion of the clearing model on the locational marginal price in the general form. The method may quickly calculate the parameter changing domain of different nodal loads under the condition of a clear base state in the current power market. When the increment of the nodal loads is subordinate to the changing domain, the locational marginal price may remain unchanged.

Abstract: The disclosure provides power distribution network reliability index calculation method based on mixed integer linear programming. The method includes: establishing a model for optimizing reliability indexes of a power distribution network based on a mixed integer linear programming model, wherein the model comprises an objective function and constraint conditions, the objective function is for minimizing a system average interruption duration index (SAIDI); solving the model based on the objective function and the constraint conditions to obtain reliability indexes of the power distribution network; and controlling operation of the power distribution network based on the reliability indexes.

Abstract: The present disclosure provides a dispatching method and a dispatching device for an integrated transmission and distribution network. The integrated transmission and distribution network include a transmission network and at least one distribution network. The method includes: establishing a dispatch model of the integrated transmission and distribution network; solving the dispatch model to obtain dynamic dispatch parameters for the integrated transmission and distribution network, in which the dynamic dispatch parameters comprise a boundary transferred power from the transmission network to each of the at least one distribution network, and power outputs of all generators in the transmission network and each of the at least one distribution network; and dispatching the integrated transmission and distribution network based on the boundary transferred power and the power outputs of all the generators in the transmission network and each of the at least one distribution network.

Abstract: The present disclosure proposes a decomposition-coordination voltage control method for wind power to be transmitted to a nearby area via flexible DC. The method includes: initializing parameters; sending the parameters to wind power farms; for each of the wind power farms, establishing a voltage control optimization sub-model; solving the voltage control optimization sub-model to obtain a first optimal result; for the control center, establishing a voltage control optimization main model; solving the voltage control optimization main model to obtain a second optimal result; calculating a determination index based on the first optimal result and the second optimal result; and determining whether the determination index is convergent to an admissible value, if no, updating the parameters and returning to establishing the voltage control optimization sub-model.

Abstract: A state estimation method for a heat supply network in a steady state based on a bilateral equivalent model is provided. The method includes: establishing the bilateral equivalent model based on a mass flow rate in each supply branch of the heating network, a mass flow rate in each return branch of the heating network, a mass flow rate in each connecting branch of the heating network, a pressure and a temperature of each node in the heating network, wherein each heat source is configured as a connecting branch and each heat load is configured as a connecting branch; and repeatedly performing a state estimation on the heating network based on the bilateral equivalent model, until a coverage state estimation result is acquired.

Abstract: A reactive power-voltage control method for integrated transmission and distribution networks is provided. The reactive power-voltage control method includes: establishing a reactive power-voltage control model for a power system consisting of a transmission network and a plurality of distribution networks; performing a second order cone relaxation on a non-convex constraint of the plurality of distribution network constraints to obtain the convex-relaxed reactive power-voltage control model; solving the convex-relaxed reactive power-voltage control model to acquire control variables of the transmission network and control variables of each distribution network; and controlling the transmission network based on the control variables of the transmission network and controlling each distribution network based on the control variables of the distribution network, so as to realize coordinated control of the power system.

Abstract: A power grid reactive voltage control method and control system based on two-stage deep reinforcement learning, comprising steps of: building interactive training environment based on Markov decision process, according to a regional power grid simulation model and a reactive voltage optimization model; training a reactive voltage control model offline by using a SAC algorithm, in the interactive training environment based on Markov decision process; deploying the reactive voltage control model to a regional power grid online system; and acquiring operating state information of the regional power grid, updating the reactive voltage control model, and generating an optimal reactive voltage control policy. As compared with the existing power grid optimizing method based on reinforcement learning, the online control training according to the present disclosure has costs and safety hazards greatly reduced, and is more suitable for deployment in an actual power system.

Abstract: A power grid reactive voltage control model training method. The method comprises: establishing a power grid simulation model; establishing a reactive voltage optimization model, according to a power grid reactive voltage control target; building interactive training environment based on Adversarial Markov Decision Process, in combination with the power grid simulation model and the reactive voltage optimization model; training the power grid reactive voltage control model through a joint adversarial training algorithm; and transferring the trained power grid reactive voltage control model to an online system. The power grid reactive voltage control model trained by using the method according to the present disclosure has transferability as compared with the traditional method, and may be directly used for online power grid reactive voltage control.

Abstract: Provided are method and device for adjusting a power flow based on operation constraints. The method includes: establishing a power flow adjusting model comprising an objective function and constraints; acquiring active power and reactive power of each node by using a two-stage optimization of active and reactive powers. In this method, the power flow adjusting model is divided into the active power optimization sub-model and the reactive power optimization sub-model. The active power optimization sub-model, where the linearized power flow constraint and the tie line section active power constraint are considered, may be regarded as quadratic programming. The reactive power flow optimization sub-model is solved on the basis of the active sub-model, and the AC power flow constraint, the grid voltage range constraint, and the pilot bus voltage setting value constraint are considered.

Abstract: The present disclosure provides a method for planning a distribution network with reliability constraints based on a feeder corridor, including determining installation states of respective elements in the distribution network; determining an objective function, the objective function being an objective function of minimizing a total investment cost of the distribution network; obtaining fault-isolation-and-load-transfer time and fault recovery time in a case where the feeder segment of each feeder line that is contained in each feeder corridor fails; determining constraint conditions including reliability constraints; building a distribution network planning model according to the objective function and the constraints; and solving the distribution network planning model built to obtain optimal solutions as planning states and reliability indexes to plan the distribution network.