Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissions

Multi-energy microgrids(MEMG)play an important role in promoting carbon neutrality and achieving sustainable development.This study investigates an effective energy management strategy(EMS)for MEMG.First,an energy management system model that allows for intra-microgrid energy conversion is developed,and the corresponding Markov decision process(MDP)problem is formulated.Subsequently,an improved double deep Q network(iDDQN)algorithm is proposed to enhance the exploration ability by modifying the calculation of the Q value,and a prioritized experience replay(PER)is introduced into the iDDQN to improve the training speed and effectiveness.Finally,taking advantage of the federated learning(FL)and iDDQN algorithms,a federated iDDQN is proposed to design an MEMG energy management strategy to enable each microgrid to share its experiences in the form of local neural network(NN)parameters with the federation layer,thus ensuring the privacy and security of data.The simulation results validate the superior performance of the proposed energy management strategy in minimizing the economic costs of the MEMG while reducing CO_2 emissions and protecting data privacy.

基于改进的双累积曲线法量化气候变化和人类活动对径流的影响

Quantitative assessments of the impacts of climate change and anthropogenic activities on runoff help us to better understand the mechanisms of hydrological processes.This study analyzed the dynamics of mountainous runoff in the upper reaches of the Shiyang River Basin(USRB)and its sub-catchments,and quantified the impacts of climate change and human activities on runoff using the improved double mass curve(IDMC)method,which comprehensively considers the effects of precipitation and evapotranspiration on runoff,instead of only considering precipitation as before.The results indicated that the annual runoff depth in the USRB showed a slightly increased trend from 1961 to 2018,and sub-catchments were increased in the west and decreased in the east.The seasonal distribution pattern of runoff depth in the USRB and its eight sub-catchments all showed the largest in summer,followed by autumn and spring,and the smallest in winter with an increasing trend.Quantitative assessment results using the IDMC method showed that the runoff change in the USRB is more significantly affected by climate change,however,considerable differences are evident in sub-catchments.This study further developed and improved the method of runoff attribution analysis conducted at watershed scale,and these results will contribute to the ecological protection and sustainable utilization of water resources in the USRB and similar regions.