Short, medium and long term load forecasting model and virtual load forecaster based on radial basis neural networks

Artificial neural networks (ANNs) can be easily applied to short-term load forecasting (STLF) models for electric power distribution applications. However, they are not typically used in medium and long term load forecasting (MLTLF) electric power models because of the difficulties associated with collecting and processing the necessary data. Virtual instrument (VI) techniques can be applied to electric power load forecasting but this is rarely reported in the literature. In this paper, we investigate the modelling and design of a VI for short, medium and long term load forecasting using ANNs. Three ANN models were built for STLF of electric power. These networks were trained using historical load data and also considering weather data which is known to have a significant affect of the use of electric power (such as wind speed, precipitation, atmospheric pressure, temperature and humidity). In order to do this a V-shape temperature processing model is proposed. With regards MLTLF, a model was developed using radial basis function neural networks (RBFNN). Results indicate that the forecasting model based on the RBFNN has a high accuracy and stability. Finally, a virtual load forecaster which integrates the VI and the RBFNN is presented.

Electric vehicle capacity forecasting model with application to load levelling

There are many uncertainties in forecasting the charging and discharging capacity required by electric vehicles (EVs) often as a consequence of stochastic usage and intermittent travel. In terms of large-scale EV integration in future power networks this paper develops a capacity forecasting model which considers eight particular uncertainties in three categories. Using the model, a typical application of EVs to load levelling is presented and exemplified using a UK 2020 case study. The results presented in this paper demonstrate that the proposed model is accurate for charge and discharge prediction and a feasible basis for steady-state analysis required for large-scale EV integration.

Order Flow and the Monetary Model of Exchange Rates: Evidence from a Novel Data Set

We propose an exchange rate model that is a hybrid of the conventional specification with monetary fundamentals and the Evans–Lyons microstructure approach. We estimate a model augmented with order flow variables, using a unique data set: almost 100 monthly observations on interdealer order flow on dollar/euro and dollar/yen. The augmented macroeconomic, or “hybrid,” model exhibits greater in-sample stability and out of sample forecasting improvement vis-à-vis the basic macroeconomic and random walk specifications.

Habitat Isolation Reduces the Temporal Stability of Island Ecosystems in the Face of Flood Disturbance

Natural ecosystems are increasingly exposed to multiple anthropogenic stressors, including land-use change, deforestation, agricultural intensification, and urbanisation, all of which have led to widespread habitat fragmentation, which is also likely to be amplified further by predicted climate change. The potential interactive effects of these different stressors cannot be determined by studying each in isolation, although such synergies have been largely ignored in ecological field studies to date. Here, we use a model system of naturally fragmented islands in a braided river network, which is exposed to periodic inundation, to investigate the interactive effects of habitat isolation and flood disturbance. Food web structure was similar across the islands during periods of hydrological stability, but several key properties were altered in the aftermath of flood disturbance, based on distance of the islands from the regional source pool of species: taxon richness and mean food chain length declined with habitat isolation after flooding, while the proportion of basal species increased. Greater species turnover through time reflected the slower process of re-colonisation on the more distant islands following disturbance. Increased variability of several food web properties over a 1-year period highlighted the reduced temporal stability of isolated habitat fragments. Many of these effects reflected the differential successes of predator and prey species at re-colonising the islands: even though larger, more mobile consumers may reach the more distant islands first, they cannot establish populations until the lower trophic levels have successfully reassembled. These results highlight the susceptibility of fragmented ecosystems to environmental perturbations. © 2013 Elsevier Ltd.

Forecasting Death Rates Using Exogenous Determinants

Mortality models used for forecasting are predominantly based on the statistical properties of time series and do not generally incorporate an understanding of the forces driving secular trends. This paper addresses three research questions: Can the factors found in stochastic mortality-forecasting models be associated with real-world trends in health-related variables? Does inclusion of health-related factors in models improve forecasts? Do resulting models give better forecasts than existing stochastic mortality models? We consider whether the space spanned by the latent factor structure in mortality data can be adequately described by developments in gross domestic product, health expenditure and lifestyle-related risk factors using statistical techniques developed in macroeconomics and finance. These covariates are then shown to improve forecasts when incorporated into a Bayesian hierarchical model. Results are comparable or better than benchmark stochastic mortality models.

Bandwidth selection by cross-validation for forecasting long memory financial time series

The paper addresses the issue of choice of bandwidth in the application of semiparametric estimation of the long memory parameter in a univariate time series process. The focus is on the properties of forecasts from the long memory model. A variety of cross-validation methods based on out of sample forecasting properties are proposed. These procedures are used for the choice of bandwidth and subsequent model selection. Simulation evidence is presented that demonstrates the advantage of the proposed new methodology.

Is China's fifth-largest inland lake to dry-up? Incorporated hydrological and satellite-based methods for forecasting Hulun Lake water levels

Hulun Lake, China's fifth-largest inland lake, experienced severe declines in water level in the period of 2000-2010. This has prompted concerns whether the lake is drying up gradually. A multi-million US dollar engineering project to construct a water channel to transfer part of the river flow from a nearby river to maintain the water level was completed in August 2010. This study aimed to advance the understanding of the key processes controlling the lake water level variation over the last five decades, as well as investigate the impact of the river transfer engineering project on the water level. A water balance model was developed to investigate the lake water level variations over the last five decades, using hydrological and climatic data as well as satellite-based measurements and results from land surface modelling. The investigation reveals that the severe reduction of river discharge (-364±64 mm/yr, ∼70% of the five-decade average) into the lake was the key factor behind the decline of the lake water level between 2000 and 2010. The decline of river discharge was due to the reduction of total runoff from the lake watershed. This was a result of the reduction of soil moisture due to the decrease of precipitation (-49±45 mm/yr) over this period. The water budget calculation suggests that the groundwater component from the surrounding lake area as well as surface run off from the un-gauged area surrounding the lake contributed ∼ net 210 Mm3/yr (equivalent to ∼ 100 mm/yr) water inflows into the lake. The results also show that the water diversion project did prevent a further water level decline of over 0.5 m by the end of 2012. Overall, the monthly water balance model gave an excellent prediction of the lake water level fluctuation over the last five decades and can be a useful tool to manage lake water resources in the future.

Special condition wind power forecasting based on Gaussian process and similar historical data

Due to the variability of wind power, it is imperative to accurately and timely forecast the wind generation to enhance the flexibility and reliability of the operation and control of real-time power. Special events such as ramps, spikes are hard to predict with traditional methods using solely recently measured data. In this paper, a new Gaussian Process model with hybrid training data taken from both the local time and historic dataset is proposed and applied to make short-term predictions from 10 minutes to one hour ahead. A key idea is that the similar pattern data in history are properly selected and embedded in Gaussian Process model to make predictions. The results of the proposed algorithms are compared to those of standard Gaussian Process model and the persistence model. It is shown that the proposed method not only reduces magnitude error but also phase error.

Intravitreal AAV2.COMP-Ang1 prevents neurovascular degeneration in a murine model of diabetic retinopathy

Diabetic retinopathy (DR) is the leading cause of blindness in the working-age population in the United States. The vision-threatening processes of neuroglial and vascular dysfunction in DR occur in concert, driven by hyperglycemia and propelled by a pathway of inflammation, ischemia, vasodegeneration, and breakdown of the blood retinal barrier. Currently, no therapies exist for normalizing the vasculature in DR. Here we show that a single intravitreal dose of adeno-associated virus serotype 2 encoding a more stable, soluble, and potent form of angiopoietin 1 (AAV2.COMP-Ang1) can ameliorate the structural and functional hallmarks of DR in Ins2Akita mice, with sustained effects observed through six months. In early DR, AAV2.COMP-Ang1 restored leukocyte-endothelial interaction, retinal oxygenation, vascular density, vascular marker expression, vessel permeability, retinal thickness, inner retinal cellularity, and retinal neurophysiological response to levels comparable to non-diabetic controls. In late DR, AAV2.COMP-Ang1 enhanced the therapeutic benefit of intravitreally-delivered endothelial colony-forming cells by promoting their integration into the vasculature and thereby stemming further visual decline. AAV2.COMP-Ang1 single-dose gene therapy can prevent neurovascular pathology, support vascular regeneration, and stabilize vision in DR.

Time series wind power forecasting based on variant Gaussian process and TLBO

Due to the variability and stochastic nature of wind power system, accurate wind power forecasting has an important role in developing reliable and economic power system operation and control strategies. As wind variability is stochastic, Gaussian Process regression has recently been introduced to capture the randomness of wind energy. However, the disadvantages of Gaussian Process regression include its computation complexity and incapability to adapt to time varying time-series systems. A variant Gaussian Process for time series forecasting is introduced in this study to address these issues. This new method is shown to be capable of reducing computational complexity and increasing prediction accuracy. It is further proved that the forecasting result converges as the number of available data approaches innite. Further, a teaching learning based optimization (TLBO) method is used to train the model and to accelerate
the learning rate. The proposed modelling and optimization method is applied to forecast both the wind power generation of Ireland and that from a single wind farm to show the eectiveness of the proposed method.

Is there really "nothing you can do"? Pathways to enhanced flood-risk preparedness

Whilst policy makers have tended to adopt an ‘information-deficit model’ to bolster levels of flood-risk preparedness primarily though communication strategies promoting awareness, the assumed causal relation between awareness and preparedness is empirically weak. As such, there is a growing interest amongst scholars and policy makers alike to better understand why at-risk individuals are underprepared. In this vein, empirical studies, typically employing quantitative methods, have tended to focus on exploring the extent to which flood-risk preparedness levels vary depending not only on socio-demographic variables, but also (and increasingly so) the perceptual factors that influence flood risk preparedness. This study builds upon and extends this body of research by offering a more solution-focused approach that seeks to identify how pathways to flood-risk preparedness can be opened up. Specifically, through application of a qualitative methodology, we seek to explore how the factors that negatively influence flood-risk preparedness can be addressed to foster a shift towards greater levels of mitigation behaviour. In doing so, we focus our analysis on an urban community in Ireland that is identified as ‘at risk’ of flash flooding and is currently undergoing significant flood relief works. In this regard, the case study offers an interesting laboratory to explore how attitudes towards flood-risk preparedness at the individual level are being influenced within the context of a flood relief scheme that is only partially constructed. In order to redress the dearth of theoretically informed qualitative studies in this field, we draw on Protection Motivation Theory (PMT) to help guide our analysis and make sense of our results. Our findings demonstrate that flood-risk preparedness can be undermined by low levels of efficacy amongst individuals in terms of the preparedness measures available to them and their own personal capacity to implement them. We also elucidate that the ‘levee effect’ can occur before engineered flood defences are fully constructed as the flood relief works within our case study are beginning to affect people’s perception of flood risk in the case study area. We conclude by arguing that 1) individuals’ coping appraisals need to be enhanced through communication strategies and other interventions which highlight that future floods may not replicate past events; and 2) the concept of residual risk needs to be communicated at all stages of a flood relief scheme, not just upon completion.