Generator tripping scheme(GTS)is the most commonly used scheme to prevent power systems from losing safety and stability.Usually,GTS is composed of offline predetermination and real-time scenario match.However,it is e...Generator tripping scheme(GTS)is the most commonly used scheme to prevent power systems from losing safety and stability.Usually,GTS is composed of offline predetermination and real-time scenario match.However,it is extremely time-consuming and labor-intensive for manual predetermination for a large-scale modern power system.To improve efficiency of predetermination,this paper proposes a framework of knowledge fusion-based deep reinforcement learning(KF-DRL)for intelligent predetermination of GTS.First,the Markov Decision Process(MDP)for GTS problem is formulated based on transient instability events.Then,linear action space is developed to reduce dimensionality of action space for multiple controllable generators.Especially,KF-DRL leverages domain knowledge about GTS to mask invalid actions during the decision-making process.This can enhance the efficiency and learning process.Moreover,the graph convolutional network(GCN)is introduced to the policy network for enhanced learning ability.Numerical simulation results obtained on New England power system demonstrate superiority of the proposed KF-DRL framework for GTS over the purely data-driven DRL method.展开更多
Circulating fluidized bed combustion （CFBC） ash exhibits the desirable pozzolanic activity which makes it a potential supplementary cementitious material to replace cement for concrete production. However, the high ...Circulating fluidized bed combustion （CFBC） ash exhibits the desirable pozzolanic activity which makes it a potential supplementary cementitious material to replace cement for concrete production. However, the high unburnt carbon content and porous surface structure of CFBC ash may adsorb water reducer and thereby significantly reduce the efficiency of water-reducing agents. The adsorption mechanism of polycarboxylate superplasticizer in CFBC ash-Portland cement paste was investigated by ultraviolet-visible spectrophotometer, and the conception of ＂invalid adsorption site＂ of CFBC ash was presented. The results show that the adsorption behavior of polycarboxylate superplasticizer in coal ash-Portland cement paste can be described by Langmuir isothermal adsorption equation. The adsorption capacity of CFBC ash-Portland cement paste is higher than that of pulverized coal combustion （PCC） fly ash-Portland cement paste. Moreover, the adsorption amount of polycarboxylate superplasticizer increases with the ratio of ash-to-cement in the paste. At last, the fluidity of CFBC ash-Portland cement paste is lower than that of the PCC fly ash paste. This work suggests that when CFBC ash is used as concrete admixture, the poor flowability of the cementitious system due to the high adsorption of water and water-reducing agent should be taken into consideration.展开更多
基金supported by National Natural Science Foundation of China(No.U22B20111,No.U1866602)。
文摘Generator tripping scheme(GTS)is the most commonly used scheme to prevent power systems from losing safety and stability.Usually,GTS is composed of offline predetermination and real-time scenario match.However,it is extremely time-consuming and labor-intensive for manual predetermination for a large-scale modern power system.To improve efficiency of predetermination,this paper proposes a framework of knowledge fusion-based deep reinforcement learning(KF-DRL)for intelligent predetermination of GTS.First,the Markov Decision Process(MDP)for GTS problem is formulated based on transient instability events.Then,linear action space is developed to reduce dimensionality of action space for multiple controllable generators.Especially,KF-DRL leverages domain knowledge about GTS to mask invalid actions during the decision-making process.This can enhance the efficiency and learning process.Moreover,the graph convolutional network(GCN)is introduced to the policy network for enhanced learning ability.Numerical simulation results obtained on New England power system demonstrate superiority of the proposed KF-DRL framework for GTS over the purely data-driven DRL method.
基金Funded by the National Natural Science Foundation of China(Nos.51132010 and 51272222)the Programs for Science and Technology Development of Yantai City,Shandong Province,China(No.2012ZH249)
文摘Circulating fluidized bed combustion （CFBC） ash exhibits the desirable pozzolanic activity which makes it a potential supplementary cementitious material to replace cement for concrete production. However, the high unburnt carbon content and porous surface structure of CFBC ash may adsorb water reducer and thereby significantly reduce the efficiency of water-reducing agents. The adsorption mechanism of polycarboxylate superplasticizer in CFBC ash-Portland cement paste was investigated by ultraviolet-visible spectrophotometer, and the conception of ＂invalid adsorption site＂ of CFBC ash was presented. The results show that the adsorption behavior of polycarboxylate superplasticizer in coal ash-Portland cement paste can be described by Langmuir isothermal adsorption equation. The adsorption capacity of CFBC ash-Portland cement paste is higher than that of pulverized coal combustion （PCC） fly ash-Portland cement paste. Moreover, the adsorption amount of polycarboxylate superplasticizer increases with the ratio of ash-to-cement in the paste. At last, the fluidity of CFBC ash-Portland cement paste is lower than that of the PCC fly ash paste. This work suggests that when CFBC ash is used as concrete admixture, the poor flowability of the cementitious system due to the high adsorption of water and water-reducing agent should be taken into consideration.
