A fast optimization method for dynamic dispatching of cross-regional interconnected power grid based on knowledge transfer

Abstract

The invention discloses a fast optimization method for dynamic dispatching of a cross-regional interconnected power grid based on knowledge transfer. Firstly, the optimized optimal knowledge matrix ofeach source task is stored in a knowledge base as empirical knowledge in the pre-learning stage of the source task; then the source task with the highest similarity to the target task is obtained inthe learning stage of the target task, and the initial knowledge matrix of the target task is obtained by transferring its optimal knowledge matrix so as to perform fast optimization of the target task; and finally the optimal knowledge matrix of the target task is stored in the knowledge base as the empirical knowledge. The dispatching mechanism can select a reasonable action scheme according tothe actual operation state of the power grid at the dispatching time under the obtained strategy to realize dynamic dispatching of the cross-regional interconnected power grid. The mechanism of hierarchical learning and knowledge transfer can avoid the problem of "dimension disaster" of reinforcement learning to a certain extent, accelerate the convergence speed of the algorithm and promote fast solving of the dispatching strategy.

Description

technical field [0001] The invention belongs to the field of dispatching of inter-regional interconnected power grids, in particular to a fast optimization method for dynamic dispatching of inter-regional interconnected power grids based on knowledge transfer. Background technique [0002] Cross-regional power grid interconnection is one of the important means to optimize the allocation of resources and improve utilization efficiency across the country. The construction of inter-provincial and cross-regional interconnected power grids can give full play to the adjustment of surplus and shortage of large power grids, optimal allocation of resources, backup sharing, and accident support. It has many benefits and can greatly improve the consumption level of new energy. [0003] There are few existing studies on the joint optimization of inter-regional tie lines and intra-regional units in the cross-regional interconnection grid system. The "curse of dimensionality" problem ari...

AI Technical Summary

Problems solved by technology

[0003] There are few existing studies on the joint optimization of inter-regional tie lines and intra-regional units in the cross-regional interconnection grid system. The "curse of dimensionality" problem caused by the continuous expansion of the problem scale

In addition, traditional reinforcement learning methods believe that different learning tasks are irrelevant to each other, and need to be remodeled and re-solved for different tasks, but in fact different learning tasks are often related to each other

Images