Deep reinforcement learning based power system optimal carbon emission flow

Under the strain of global warming and constant depletion fossil energy supplies, power system must pursue a mode operation development with minimal carbon emissions. There are methods to reduce emissions on both production consumption sides, such as using renewable alternatives aggregating distributed resources. However, issue how during transmission electricity is ignored. Consequently, multi-objective optimal emission flow (OCEF) proposed, which takes into account not only economic indices in conventional (OPF) but also reduction unnecessary process, i.e., losses (CEFL). This paper presents deep reinforcement learning (DRL) based OCEF solving method that handles generator dispatching scheme by utilizing current state parameters known quantities. The case study IEEE-30 demonstrates DRL-based solver more effective, efficient, stable than traditional methods.