Search results for "FORECASTING"

The green roofs for reduction in the load on rainwater drainage in highly urbanised areas

2021

AbstractRapid weather phenomena, particularly sudden and intense rainfall, have become a problem in urban areas in recent years. During heavy rainfall, urban rainwater drainage systems are unable to discharge huge amounts of runoff into collecting reservoirs, which usually results in local flooding. This paper presents attempts to forecast a reduction in the load on the rainwater drainage system through the implementation of green roofs in a case study covering two selected districts of Opole (Poland)—the Old Town and the City Centre. Model tests of extensive and intensive roofs were carried out, in order to determine the reduction of rainwater runoff from the roof surface for the site unde…

Forecasts on the development of hydrogen refuelling infrastructures in Portugal

2021

In Portugal, the transition to new forms of mobility has begun in recent years, but there are still obstacles to overcome. Currently, hybrid vehicles (PHEVs) are the most widespread and accepted by the community and that is probably due to range anxiety, having in fact the possibility of double charging (both through the thermal engine and the electric battery). Furthermore, it must be considered that in addition to electric vehicles, another valid alternative to mobility in the near future is the hydrogen vehicles one. These appear to be even more sustainable from the point of view of air emissions, but on the other hand the costs for the production of hydrogen are still too high. Then, th…

Comparing Recurrent Neural Networks using Principal Component Analysis for Electrical Load Predictions

2021

Electrical demand forecasting is essential for power generation capacity planning and integrating environment-friendly energy sources. In addition, load predictions will help in developing demand-side management in coordination with renewable power generation. Meteorological conditions influence urban area load pattern; therefore, it is vital to include weather parameters for load predictions. Machine Learning algorithms can effectively be used for electrical load predictions considering impact of external parameters. This paper explores and compares the basic Recurrent Neural Networks (RNN); Simple Recurrent Neural Networks (Vanilla RNN), Gated Recurrent Units (GRU), and Long Short-Term Me…

Relative evaluation of regression tools for urban area electrical energy demand forecasting

2019

Abstract Load forecasting is the most fundamental application in Smart-Grid, which provides essential input to Demand Response, Topology Optimization and Abnormally Detection, facilitating the integration of intermittent clean energy sources. In this work, several regression tools are analyzed using larger datasets for urban area electrical load forecasting. The regression tools which are used are Random Forest Regressor, k-Nearest Neighbour Regressor and Linear Regressor. This work explores the use of regression tool for regional electric load forecasting by correlating lower distinctive categorical level (season, day of the week) and weather parameters. The regression analysis has been do…

Ten important articles on noninvasive ventilation in critically ill patients and insights for the future: A report of expert opinions

2017

Background Noninvasive ventilation is used worldwide in many settings. Its effectiveness has been proven for common clinical conditions in critical care such as cardiogenic pulmonary edema and chronic obstructive pulmonary disease exacerbations. Since the first pioneering studies of noninvasive ventilation in critical care in the late 1980s, thousands of studies and articles have been published on this topic. Interestingly, some aspects remain controversial (e.g. its use in de-novo hypoxemic respiratory failure, role of sedation, self-induced lung injury). Moreover, the role of NIV has recently been questioned and reconsidered in light of the recent reports of new techniques such as high-fl…

Assessment of the Present and Future Offshore Wind Power Potential: A Case Study in a Target Territory of the Baltic Sea Near the Latvian Coast

2013

Offshore wind energy development promises to be a significant domestic renewable energy source in Latvia. The reliable prediction of present and future wind resources at offshore sites is crucial for planning and selecting the location for wind farms. The overall goal of this paper is the assessment of offshore wind power potential in a target territory of the Baltic Sea near the Latvian coast as well as the identification of a trend in the future wind energy potential for the study territory. The regional climate model CLM and High Resolution Limited Area Model (Hirlam) simulations were used to obtain the wind climatology data for the study area. The results indicated that offshore wind en…

Forecasting the onset of an allergic risk to poaceae in Nancy and Strasbourg (France) with different methods

2008

International audience; Pollen of Poaceae is among the most allergenic pollen in Europe with pollen of birch. It is therefore useful to elaborate models to help pollen allergy sufferers. The objective of this study was to construct forecast models that could predict the first day characterized by a certain level of allergic risk called here the Starting Date of the Allergic Risk . Models result from four forecast methods (three summing and one multiple regression analysis) used in the literature. They were applied on Nancy and Strasbourg from 1988 to 2005 and were tested on 2006. Mean Absolute Error and Actual forecast abili ty test are the parameters used to choose best models, assess and …

E-MIP: A new mechanism for dynamic coalition formation in a robot team

2004

When mobile robots colonies move in dynamic, not predictable and time variable environments, the problem now is on how can they achieve distributed solving strategies for solving complicate and difficult tasks. The development of a new robotic architecture for the coordination of robot colonies in dangerous and dynamic environments is outlined. The name of this new architecture is Economic Metaphor of Italian Politics (E-MIP), because it takes inspiration from the political organizations of Italian democratic governments, where the leader isn't only one robot but a government of three robots constitutes it while a second group of robots, the Robot Citizens, are the executor of the mission. …

2014

Sales forecasting is an essential task in retailing. In particular, consumer-oriented markets such as fashion and electronics face uncertain demands, short life cycles and a lack of historical sales data which strengthen the challenges of producing accurate forecasts. This survey paper presents state-of-the-art methods in the sales forecasting research with a focus on fashion and new product forecasting. This study also reviews different strategies to the predictive value of user-generated content and search queries.

Comment améliorer la prévision des ventes pour le marketing ? Les apports de la théorie du chaos

2013

National audience; La littérature en marketing constate un décalage entre les avancées réalisées par les chercheurs qui développent de nouvelles méthodes de prévision des ventes, et l'usage massif de méthodes traditionnelles reposant sur l'hypothèse de linéarité des processus analysés. Cette recherche expose la contribution poten¬tielle de la théorie du chaos à l'amélioration de la prévision des ventes. Une illustration de ces apports est proposée avec une application à la prévision des ventes de consoles de jeux vidéo au Japon. Les résultats mettent en évidence la capacité de la méthode proposée à détecter la présence de chaos dans la série et montrent la possibilité de préciser l'horizon …