The Contribution of Teleworking towards a Green Computing Environment

The aims of the chapter are to consider the strategic green issues of teleworking in terms of the environment, transport, location, office space, and resource use for modern organisations and business sectors and to formulate a conceptual model of the processes involved. In fact, teleworking technologies are variously implemented for green computing initiatives, and the many advantages include lower greenhouse gas emissions related to travel, greater worker satisfaction, and as a result of lower overhead office costs, increased profit margins. The chapter initially investigates the appropriateness of a working definition of teleworking with regard to green computing, and following this, explores the benefits and barriers of teleworking in a green computing environment. The theoretical frameworks and models of teleworking are then considered, and a conceptual model of the contribution of teleworking to green computing is formulated. It is the intention of the chapter to identify and articulate those teleworking concepts that will be useful to academicians, scientists, business entrepreneurs, practitioners, managers, and policy makers, and to indicate future research directions for research scholars and students with similar interests.

Green Computing and Its Impact

The mission “Saving Earth” has become need of all of us to sustain life on the earth. There are many holistic approaches for Green Computing which impact on stack holders of the computing system including hardware, software and people. There are many reasons to develop green computing like environmental friendly, saving powers, long term profit, reduce pollution, power management and increasing performance etc. Approach to develop green computing can be broadly divided into four parts: hardware device manufacturing, software techniques, people awareness and standard policies.

From Optimization to Clustering

In the past two decades, Swarm Intelligence (SI)-based optimization techniques have drawn the attention of many researchers for finding an efficient solution to optimization problems. Swarm intelligence techniques are characterized by their decentralized way of working that mimics the behavior of colony of ants, swarm of bees, flock of birds, or school of fishes. Algorithmic simplicity and effectiveness of swarm intelligence techniques have made it a powerful tool for solving global optimization problems. Simulation studies of the graceful, but unpredictable, choreography of bird flocks led to the design of the particle swarm optimization algorithm. Studies of the foraging behavior of ants resulted in the development of ant colony optimization algorithm. This chapter provides insight into swarm intelligence techniques, specifically particle swarm optimization and its variants. The objective of this chapter is twofold: First, it describes how swarm intelligence techniques are employed to solve various optimization problems. Second, it describes how swarm intelligence techniques are efficiently applied for clustering, by imposing clustering as an optimization problem.

Theoretical Analyses of the Universal Approximation Capability of a Class of Higher Order Neural Networks Based on Approximate Identity

One of the most important problems in the theory of approximation functions by means of neural networks is universal approximation capability of neural networks. In this study, we investigate the theoretical analyses of the universal approximation capability of a special class of three layer feedforward higher order neural networks based on the concept of approximate identity in the space of continuous multivariate functions. Moreover, we present theoretical analyses of the universal approximation capability of the networks in the spaces of Lebesgue integrable multivariate functions. The methods used in proving our results are based on the concepts of convolution and epsilon-net. The obtained results can be seen as an attempt towards the development of approximation theory by means of neural networks.

Using Self Organizing Maps for Banking Oversight

This chapter combines two methods based on neural networks (trait recognition and self-organizing maps) to develop a model of bankruptcy prediction. The authors apply the method to the Spanish savings banks, most of them rescued by the Government between 2008 and 2013 in a costly massive process. First, the authors detect the combinations of variables (performance, asset structure, and capitalization) that best describe the profile of the rescued savings banks. Then, the authors use these combinations on a yearly basis to generate bi-dimensional maps in which banks are placed according to their risk and similarities. This method provides a visual tool that can improve the oversight of policy makers on the whole financial system and enable time pertinent answers to some threatens to the country financial stability. The maps are useful means to detect and understand how the financial threats emerge over time too.

Comparative Analysis of Statistical, Machine Learning, and Grey Methods for Short-Term Electricity Load Forecasting

Electricity load forecasting is crucial for electricity generation companies, distributors and other electricity market participants. In this study, several forecasting techniques are applied to time series modeling and forecasting of the hourly loads. Seasonal grey model, support vector regression, random forests, seasonal ARIMA and linear regression are benchmarked on seven data sets. A rolling forecasting model is developed and 24 hours of the next day is predicted for the last 14 days of each data set. This day-ahead forecasting model is especially important in day-ahead market activities and plant scheduling operations. Experimental results indicate that support vector regression and seasonal grey model outperforms other approaches in terms of forecast accuracy for day-ahead load forecasting.

Utilizing Feature Selection on Higher Order Neural Networks

Artificial Neural Network has shown its impressive ability on many real world problems such as pattern recognition, classification and function approximation. An extension of ANN, higher order neural network (HONN), improves ANN's computational and learning capabilities. However, the large number of higher order attributes leads to long learning time and complex network structure. Some irrelevant higher order attributes can also hinder the performance of HONN. In this chapter, feature selection algorithms will be used to simplify HONN architecture. Comparisons of fully connected HONN with feature selected HONN demonstrate that proper feature selection can be effective on decreasing number of inputs, reducing computational time, and improving prediction accuracy of HONN.

Application of Genetic Algorithms in Inventory Control

The genetic algorithm (GA) is an adaptive heuristic search procedures based on the mechanics of natural selection and natural genetics. Inventory control is widely used in the area of mathematical sciences, management sciences; system science, industrial engineering, production engineering etc. but they have wide differences in mathematical and computation maturity. This chapter enables the reader to understand the basic theory of genetic algorithm and how to apply the genetic algorithms for optimizing the parameters in inventory control The current and future trend of the research with the definition of key terms of genetic algorithm has also incorporated in this chapter.

Navigation Control of a Mobile Robot under Time Constraint using Genetic Algorithms, CSP Techniques, and Fuzzy Logic

This chapter proposes a two-input-and-one-output fuzzy controller for a two-wheeled mobile robot. The robot moves following a hybrid plan based on Genetic Algorithms and Constraint Satisfaction Problem techniques. The path yielded by this hybrid plan is structured by artificial beacons. In each position of these beacons, the current velocity of the controlled robot is by itself an input for the fuzzy controller. The second input is the time delay between the current position and the next sub goal to be reached. The proposed fuzzy controller aims to converge the time delay between positions in the path tracking closely to a time window. It gives the appropriate acceleration so that the time delay becomes closer to the time window.

Higher Order Neural Network for Financial Modeling and Simulation

Financial market creates a complex and ever changing environment in which population of investors are competing for profit. Predicting the future for financial gain is a difficult and challenging task, however at the same time it is a profitable activity. Hence, the ability to obtain the highly efficient financial model has become increasingly important in the competitive world. To cope with this, we consider functional link artificial neural networks (FLANNs) trained by particle swarm optimization (PSO) for stock index prediction (PSO-FLANN). Our strong experimental conviction confirms that the performance of PSO tuned FLANN model for the case of lower number of ahead prediction task is promising. In most cases LMS updated algorithm based FLANN model proved to be as good as or better than the RLS updated algorithm based FLANN but at the same time RLS updated FLANN model for the prediction of stock index system cannot be ignored.