Search results for "forecasting"

A new method for forecasting energy output of a large-scale solar power plant based on long short-term memory networks a case study in Vietnam

2021

Abstract This paper proposes a new model for short-term forecasting power generation capacity of large-scale solar power plant (SPP) in Vietnam considering the fluctuations of weather factors when applying the Long Short-Term Memory networks (LSTM) algorithm. At first, a configuration of the model based on the LSTM algorithm is selected in accordance with the weather and operating conditions of SPP in Vietnam. Not only different structures of LSTM model but also other conventional forecasting methods for time series data are compared in terms of error accuracy of forecast on test data set to evaluate the effectiveness and select the most suitable LSTM configuration. The most suitable config…

Forecasting daily urban electric load profiles using artificial neural networks

2004

The paper illustrates a combined approach based on unsupervised and supervised neural networks for the electric energy demand forecasting of a suburban area with a prediction time of 24 h. A preventive classification of the historical load data is performed during the unsupervised stage by means of a Kohonen's self organizing map (SOM). The actual forecast is obtained using a two layered feed forward neural network, trained with the back propagation with momentum learning algorithm. In order to investigate the influence of climate variability on the electricity consumption, the neural network is trained using weather data (temperature, relative humidity, global solar radiation) along with h…

Primi studi sulla biologia e sul controllo di Cydia funebrana (Treitschke) in susineti biologici siciliani

2011

First studies on biology and control of Cydia funebrana (treitschke) in Sicilian organic plum orchards. Cydia funebrana (Treitschke), considered the key pest in the Sicilian plum orchards. Few studies were carried out in Sicily concerning C. funebrana life cycle, forecasting models and the effectiveness of some products permitted in organic plum orchards. In 2010 researches were carried out in three Sicilian plum orchards, two in Palermo Province (Monreale and San Giuseppe Jato) and one in Agrigento Province (Castrofilippo), in order to monitor the population, to evaluate damage levels caused by the plum moth and to estimate how many generations it could complete by Charmillot’s forecasting…

MULTIPLE CLIMATE-DRIVEN CASCADING ECOSYSTEM EFFECTS AFTER THE LOSS OF A FOUNDATION SPECIES

2021

Abstract Climate change is evolving so fast that the related adverse effects on the environment are becoming noticeable. Thus, there is an urgent need to explore and understand the effects generated by multiple extreme climatic events (MECEs) on marine ecosystem functioning and the services provided. Accordingly, we combined long-term in-situ empirical observations in the Mediterranean Sea with a mesocosm manipulation to investigate the concurrence of increasing temperature and hypoxia events. By focussing on a foundation mussel species, we were able to detect several cascade events triggered by a mass mortality event caused by stressful temperature and oxygen conditions, and resulting in a…

Derivation of rainfall thresholds for pluvial flood risk warning in urbanised areas

2016

In the recent past throughout the Mediterranean area, many extreme events such as floods, debris flows and landslides occurred. Mediterranean ephemeral streams have specific features compared to other river systems; their basins are small and highly torrential and may generate flash-floods (Camarasa-Belmonte & Soriano-Garcia, 2012). Moreover, the rapid transformation processes of urban areas induced the increase of catchment imperviousness and the derived increase of surface runoff generated during rainfall events. However, flooding events in urban areas occur quite frequently as a consequence of rain events of lower intensity than the design one, even in case of correct network dimensionin…

Development of an early warning system to predict sewer overflow

Flash flooding in our city is still a fairly common phenomenon.Unfortunately, the development of a flash flood forecasting system in urban areas is not a simple and unambiguous procedure.While attending the PhD course in Civil and Environmental Engineering, research activity has been given to realize an urban overflowing prediction system that was best as possible suited to the drainage network of the city of Palermo. With the support of radar data and hybrid hydraulic model for drainage network has been possible to demonstrate the effectiveness of this instrument, while the reduction of residual flood risk has been supported by modern resilience measures.

Predicting Real-Time Roadside CO and NO2 Concentrations using Neural Networks

2008

Flax–Glass Fiber Reinforced Hybrid Composites Exposed to a Salt-Fog/Dry Cycle: A Simplified Approach to Predict Their Performance Recovery

2023

Despite natural fibers gaining significant attention in recent decades, their limited performance and poor durability under humid environments cannot allow them to fully replace their synthetic counterparts as reinforcement for structural composites. In such a context, this paper aims to investigate how exposure to a humid/dry cycle affects the mechanical response of epoxy laminates reinforced with flax and glass fibers. In particular, the main goal is to assess the performance evolution of a glass–flax hybridized stacking sequence in comparison with the full glass and flax fiber reinforced composites. To this end, the investigated composites were first exposed to salt-fog for 15 or 30 days…

Forecasting energy output of a solar power plant in curtailment condition based on LSTM using P/GHI coefficient and validation in training process, a…

2022

This study presents how to improve the short-term forecast of photovoltaic plant's output power by applying the Long Short-Term Memory, LSTM, neural networks for industrial-scale solar power plants in Vietnam under possible curtailment operation. Since the actual output power does not correspond to the available power, new techniques (Global Horizontal Irradiance - GHI interval division, P/GHI factor addition (P - Power)) have been designed and applied for processing errors and missing data. The prediction model (LSTM network, structure of hidden layers, number of nodes) has been developed by the authors in a previous work. In this new version of the model, the training technique is improve…

The Impact Of Demand And Inventory Management Policies On Bullwhip Effect In Production Networks

2004

The bullwhip effect is a phenomenon consisting in variance amplification of orders as they move up a supply chain. The immediate bullwhip effect consequences are the increase of inventory costs, poor custoiner services and inefficient utilization of resources due to the difficulties of production planning activities in highly variable conditions. There are many factors that cause the bullwhip effect, but if is particularly due to demand forecasting and inventory management policies. In this paper the impact on bullwhip effect of different policies to manage demand and inventories has been evaluated through discrete event simulation, using the ARENA (R) simulation package.