Reactive Power Flow Convergence Adjustment Based on Deep Reinforcement Learning

Power flow calculation is the basis of power grid planning and many system analysis tasks require convergent power flow conditions.To address the unsolvable power flow problem caused by the reactive power imbalance,a method for adjusting reactive power flow convergence based on deep reinforcement learning is proposed.The deep reinforcement learning method takes switching parallel reactive compensation as the action space and sets the reward value based on the power flow convergence and reactive power adjustment.For the non-convergence power flow,the 500 kV nodes with reactive power compensation devices on the low-voltage side are converted into PV nodes by node type switching.And the quantified reactive power non-convergence index is acquired.Then,the action space and reward value of deep reinforcement learning are reasonably designed and the adjustment strategy is obtained by taking the reactive power non-convergence index as the algorithm state space.Finally,the effectiveness of the power flow convergence adjustment algorithm is verified by an actual power grid system in a province.

A QoS-Guanranteed Scheduling Algorithm with High Throughput for Edge Nodes of Optical Burst Switching Networks

A scheduling algorithm for the edge nodes of optical burst switching (OBS) networks is proposed to guarantee the delay requirement of services with different CoS (Class of Service) and provide lower burst loss ratio at the same time. The performance of edge nodes based on the proposed algorithm is presented.

Efficient optimization method for variable-specific-impulse low-thrust trajectories with shutdown constraint

This paper develops a sequential convex programming(SCP)-based method to solve the minimum-fuel variable-specific-impulse low-thrust transfer problem considering shutdown constraint,with emphasize on improving the computational efficiency.The variable parameter engine is more applicable for many low-thrust scenarios,therefore,both a continuously variable model and a ladder variable model are adopted.First,the original problem is convexified by processing the constraint feasible domain,which is composed of the nonlinear dynamic equations and second-order equality constraint,into convex sets.Then,the approximation is generated to close the optimal solution of the low-thrust problem by iteratively solving the convexified subproblem.Moreover,the switching self-detection and adaptive node refinement methods are presented,which can improve the accuracy of the solution and accelerate the convergence during the approximation process and is especially necessary and effective in the scenarios with shutdown constraint.In numerical simulations,the comparison with the homotopic approach shows that the proposed method only needs 4%computational time as that of the homotopic approach,and two variable-specificimpulse examples further demonstrate the effectiveness and efficiency of the proposed method.