Accuracy improvement of various short-term load forecasting models by a novel and unified statistical data-filtering method

ABSTRACT

Time-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.     

Study of the Climate Change Impacts on Water Quality in the Upstream Portion of the Cau River Basin,Vietnam

This paper presents simulations of climate change impacts on water quality in the upstream portion of the Cau River Basin in the North of Vietnam. The integrated modeling system GIBSI was used to simulate hydrological processes, pollutant and sediment wash-off in the river basin, and pollutant transport and transformation in the river network. Three projections for climate change based on emission scenarios B1, B2, and A2 of IPCC Special Report on Emission Scenarios (SRES) were considered. By assuming that the input pollution sources and watershed configuration were constant, based on 2008 data, water quality in the river network was simulated up to the terminal year 2050. For each climate change scenario, patterns of precipitation in wet and dry year were considered. The change in annual and monthly trends for dissolved oxygen (DO), biochemical oxygen demand (BOD), and ammonium ions (NH4+) load and concentration for different portions of the watershed have been analyzed. The results of these simulations show that climate change has more impact on changing the seasonal water quality parameters than on altering the average annual load of the pollutants. The percent change and change pattern in water quality parameters are different for wet and dry year, and the changes in wet year are smaller than those in dry year.     

Assessment and monitoring of nutrient loading in the sediments of tidal creeks receiving shrimp farm effluent in Quang Ninh, Vietnam

Coastal shrimp farming may lead to the contamination of sediments of surrounding estuarine and marine ecosystems as shrimp farm effluent often contains high levels of pollutants including a range of organic compounds (from uneaten feed, shrimp feces, and living and dead organisms) which can accumulate in the sediments of receiving waterways. The assessment and monitoring of sediment quality in tidal creeks receiving shrimp farm effluent can support environmental protection and decision making for sustainable development in coastal areas since sediment quality often shows essential information on long-term aquatic ecosystem health. Within this context, this paper investigates nutrient loadings in the sediments of tidal creeks receiving shrimp farm effluent in Quang Ninh, Vietnam, which now have a high concentration of intensive and semi-intensive shrimp farms. Sediment samples taken from inside creek sections directly receiving effluent from concentrated shrimp farms (IEC), from main creeks adjacent to points of effluent discharge outside concentrated shrimp farms (OEC), and few kilometers away from shrimp farms (ASF) as reference sites were collected and analyzed before and after shrimp crops to investigate spatial and temporal variation. The results showed that there were statistically significant differences in the concentrations of total nitrogen, total phosphorus, and total organic carbon among IEC, OEC, and ASF sites while the seasonal variation being limited over study times. A sediment nutrient index (SNI) computed from coefficient scores of the factor analysis efficiently summarizes sediment nutrient loads, which are high, albeit quite variable, in canals directly receiving effluents from farms but then decline sharply with distance from shrimp farms. The visualization and monitoring of sediment quality data including SNI on maps can strongly support managers to manage eutrophication at concentrated shrimp farming areas, contributing to sustainable development and management at coastal zones.