ABSTRACTTime-series and machine-learning methods are being strongly exploited to improve the accuracy of short-term load forecasting (STLF) results. In developing countries, power consumption behaviors could be suddenly changed by different customers, e.g. industrial customers, residential customers, so the load-demand dataset is often unstable. Therefore, reliability assessment of the load-demand dataset is obviously necessary for STLF models. Hence, this paper proposes a novel and unified statistical data-filtering method with the best confidence interval to eliminate unexpected noises/outliers of the input dataset before performing various short-term load forecasting models. This proposed novel data-filtering method, so-called the data pre-processing method, is also compared to other existing data-filtering methods (e.g. Kalman filter, Density-Based Spatial Clustering of Applications with Noise, Wavelet transform, and Singular Spectrum Analysis). By using an SCADA system?-based database of a typical 22kV distribution network in Vietnam, NYISO database, and PJM-RTO database, case studies of short-term load forecasting have been conducted with a conventional ARIMA model, an ANN forecasting model, an LSTM-RNN model, an LSTM-CNN combined model, a deep auto-encoder (DAE) network, a Wavenet-based model, a Wavenet and LSTM hybrid model, and a Wavelet Neural Network (WNN) model, which are to validate the novel and unified statistical data-filtering method proposed. The achieved numerical results demonstrate which the accuracy of the aforementioned STLF models can be significantly improved due to the proposed statistical data-filtering method with the best confidence interval of the input load dataset. The proposed statistical data-filtering method can considerably outperform the existing data-filtering methods. 相似文献
The dominating source of particles in urban air is road traffic. In terms of number concentration, its main contribution is within the range of ultrafine particles (Dp < 100 nm). The dispersion conditions, i.e. transport and dilution, of the submicrometer particles are expected to be like for gases and therefore the particle concentrations in a street canyon can be calculated using gaseous pollutants dispersion models. Such processes, like coagulation or condensation, are less important due to the short residence time within the street canyon environment.Two extensive measuring campaigns were conducted in the street Jagtvej in Copenhagen, Denmark. The particle size distributions were measured by a Differential Mobility Analyser (DMA) coupled to a particle counter, providing high time resolution data (1/2 hourly) on a continuous basis. Measurements of NOx, CO and meteorological parameters were also available. The measured particle number concentrations, especially below 100 nm, reveal very similar dependence on the meteorological conditions as the NOx concentrations. This underpins the conclusion that dilution properties are similar for particles and NOx. For particle sizes over 100 nm, somewhat different behaviour is observed. This points toward existence of additional particle sources, not related to traffic emissions within the street canyon. A significant contribution is believed here to be attributed to long-range transport. The total particle emission from traffic, including daily variation and size distribution, has been calculated using the OSPM dispersion model. Results are in accordance with a previous analysis based on statistical modelling. 相似文献
The South American country Brazil is one of the richest countries in terms of natural resources, representing 14 percent of the world’s total biocapacity. However, the biocapacity (biosphere’s ability to generate resources and sequester waste) per capita in Brazil has shown a massive decline over the last five decades, while economic growth and urbanization have rapidly increased for the same period. Brazil is one of the largest creditors of biocapacity to the world, and biocapacity loss in Brazil can lead to devastating environmental consequences. Therefore, this work empirically investigates the influence of urbanization, economic growth, and industrialization on biocapacity controlling human capital from 1961 to 2016 in Brazil. The Bayer and Hack cointegration test, the Autoregressive Distributed Lag (ARDL) technique, and Hacker and Hatemi-J (J Econ Stud 39:144–160, 2012) causality tests are employed. The findings unfolded a U-shaped relationship between economic growth and biocapacity, evidencing that economic growth reduces biocapacity, but after achieving a threshold level, it promotes biocapacity. Urbanization has a negative relationship with biocapacity per capita, indicating that urbanization is a significant driver of the biocapacity loss in Brazil. Further, urbanization and economic growth Granger cause biocapacity. Lastly, relevant policy implications are proposed to overcome the reduction in biocapacity.
In the carbon capture and storage (CCS) chain, transport and storage set different requirements for the composition of the gas stream mainly containing carbon dioxide (CO2). Currently, there is a lack of standards to define the required quality for CO2 pipelines. This study investigates and recommends likely maximum allowable concentrations of impurities in the CO2 for safe transportation in pipelines. The focus is on CO2 streams from pre-combustion processes. Among the issues addressed are safety and toxicity limits, compression work, hydrate formation, corrosion and free water formation, including the cross-effect of H2S and H2O and of H2O and CH4. 相似文献
Many units in public housing or other low-income urban dwellings may have elevated pesticide residues, given recurring infestation, but it would be logistically and economically infeasible to sample a large number of units to identify highly exposed households to design interventions. Within this study, our aim was to devise a low-cost approach to identify homes in public housing with high levels of pesticide residues, using information that would allow the housing authority and residents to determine optimal strategies to reduce household exposures. As part of the Healthy Public Housing Initiative, we collected environmental samples from 42 public housing apartments in Boston, MA, in 2002 and 2003 and gathered housing characteristics; for example, household demographics and self-reported pesticide use information, considering information available with and without a home visit. Focusing on five organophosphate and pyrethroid pesticides, we used classification and regression tree analysis (CART) to disaggregate the pesticide concentration data into homogenous subsamples according to housing characteristics, which allowed us to identify households and associated networks impacted by the mismanagement of pesticides. The CART analysis demonstrated reasonable sensitivity and specificity given more extensive household information but generally poor performance using only information available without a home visit. Apartments with high concentrations of cyfluthrin, a pyrethroid of interest given that it is a restricted use pesticide, were more likely to be associated with Hispanic residents who resided in their current apartment for more than 5 yr, consistent with documented pesticide usage patterns. We conclude that using CART as an exploratory technique to better understand the home characteristics associated with elevated pesticide levels may be a viable approach for risk management in large multiunit housing developments. 相似文献
Since the 1980s, the eel population has been decreasing dangerously. Persistent Organic Pollutants (POPs) such as Polychlorinated Biphenyls (PCBs) are one of the suspected causes of this decline. A preliminary study of PCB contamination carried out on different fish from the Gironde estuary (southwest of France, Europe) has shown a relatively high level of contamination of eel muscles. In order to characterize the contamination level of PCBs and PBDEs (PolyBrominated Diphenyl-Ethers) in eels from this estuary more than 240 eels were collected during the years 2004-2005 in the Gironde estuarine system, from glass eels to silver eels. Individual European eels were grouped according to length and localization sites. The results have shown a low contamination level of glass eels: respectively 28 ± 11 ng g−1 dw for PCBs and 5 ± 3 ng g−1 dw for PBDEs. The contamination level in eels (expressed in ng g−1 dw) increases from glass eels to silver eels up to 3399 ng g−1 dw of PCBs for the most contaminated silver eel. Such levels of PCBs similar to those observed in Northern Europe, could raise sanitary problems connected with the World Health Organization (WHO) recommendations. These results are worrying for the local people who regularly eat eels caught in the Gironde estuary. 相似文献