The response of purifying capability, enzyme activity, nitrification potentials, and total number of bacteria in the rhizosphere in December to wetland plants, substrates, and earthworms was investigated in integrated vertical flow constructed wetlands (IVFCW). The removal efficiency of total nitrogen (TN), NH4-N, chemical oxygen demand (COD), and total phosphorus (TP) was increased when earthworms were added into IVFCW. A significantly average removal efficiency of N in IVFCW that employed river sand as substrate and in IVFCW that employed a mixture of river sand and Qing sand as substrate was not found. However, the average removal efficiency of P was higher in IVFCW with a mixture of river sand and Qing sand as substrate than in IVFCW with river sand as substrate. Invertase activity in December was higher in IVFCW that used a mixture of river sand and Qing sand as substrate than in IVFCW which used only river sand as substrate. However, urease activity, nitrification potential, and total number of bacteria in December was higher in IVFCW that employed river sand as substrate than in IVFCW with a mixture of river sand and Qing sand as substrate. The addition of earthworms into the integrated vertical flow constructed wetland increased the above-ground biomass, enzyme activity (catalase, urease, and invertase), nitrification potentials, and total number of bacteria in December. The above-ground biomass of wetland plants was significantly positively correlated with urease and nitrification potentials (p < 0.01). The addition of earthworms into IVFCW increased enzyme activity and nitrification potentials in December, which resulted in improving purifying capability.
With the increasing penetration and installation of renewable energy such as photovoltaic (PV) generation, ultra-short-term PV output prediction is necessary to guarantee the stability of the power system. However, the traditional methods cannot capture the important features of PV power data, and prediction accuracy cannot be guaranteed. Focusing on these problems, this paper presents a novel PV prediction method based on LSTM with a multi-head attention mechanism. The mechanism can make the matrix operation run in parallel. At the same time, the model assigns weight to different features of the input data to improve the prediction. To show the effectiveness, this paper constructs four scale types for PV power prediction. Case studies show that the multi-head attention mechanism can improve the prediction performance, and the prediction accuracy decreases following the increase of time scale.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.