Abstract: A source-network-load-storage coordination dispatching method in a background of a coupling of renewable energy sources, including: taking an expectation of a minimum grid operating cost in a dispatching cycle as an objective function; generating an approximate value function of an output of a set for generating electricity from renewable energy sources and a user load, and constructing a source-network-load-storage coordination dispatching model with combination of the objective function; obtaining forecast data of the output of a set for generating electricity from renewable energy sources and the user load, and inputting the forecast data into the dispatching model for solving; performing iterative updating on the approximate value function, importing the approximate value function after the iterative updating into the dispatching model for iterative solving, and terminating an iterative process until a solving result satisfies a preset convergence condition; and using a solving result of a last iteration

Abstract: Disclosed are a photovoltaic energy storage offline coordination system and method based on demand management. The system includes a photovoltaic generator set, an inverter, a dispatch and control device for charge-discharge, a load monitor, a first and second energy storage device, and a remote console. The photovoltaic generator set is electrically connected to the dispatch and control device for charge-discharge via the inverter; the first energy storage device is connected to a load-side power supply bus via a first dispatch and control unit; the second energy storage device is connected to the load-side power supply bus via a third dispatch and control unit; a second dispatch and control unit is connected to the load-side power supply bus; the load monitor is provided at the load-side power supply bus, and configured to monitor a load of the load-side.

Abstract: A method for intelligently adjusting a power flow based on a Q-learning algorithm includes: converting a variable, an action, and a goal in a power grid to a state, an action, and a reward in the algorithm, respectively; selecting an action from an action space, giving an immediate reward based on a result of power flow calculation, and correcting a next state; forwardly observing a next exploration action based on a strategy in the Q-learning algorithm; updating a Q value in a corresponding position in a Q-value table based on the obtained reward; if a final state is not reached, going back to step 2; otherwise, increasing the number of iterations by 1; if the number of iterations does not reach predetermined value K, that is, Episode<K, going back to step 2; otherwise, that is, Episode=K, outputting the Q-value table; and outputting an optimal unit combination.

Abstract: The present invention relates to a method for identifying parameters of a 10 kV static load model based on similar daily load curves. In the present invention, an optimization model for identifying full-period parameters of the static load model is proposed based on a large number of daily load curves with response characteristic, a structure and constraints of the static load model, and two theoretical basic assumptions about loads. Full-period (including 96 moments) static voltage model parameters of 10 kV loads are given through optimization solution. A rule that active power and reactive power of the loads at each moment change with voltage is obtained. In addition, a change rule of load constituents is obtained. The method delivers good applicability, satisfies actual demands, and is suitable for large-scale static model analyses for 10 kV loads.