Mohsen Guizani

Bio: Mohsen Guizani is an academic researcher from Qatar University. The author has contributed to research in topics: Computer science & Cloud computing. The author has an hindex of 79, co-authored 1110 publications receiving 31282 citations. Previous affiliations of Mohsen Guizani include Jaypee Institute of Information Technology & University College for Women.

An Accurate and Fast Converging Short-Term Load Forecasting Model for Industrial Applications in a Smart Grid

Abstract: Short-term load forecasting (STLF) models are very important for electric industry in the trade of energy. These models have many applications in the day-to-day operations of electric utilities such as energy generation planning, load switching, energy purchasing, infrastructure maintenance, and contract evaluation. A large variety of STLF models have been developed that trade off between forecast accuracy and convergence rate. This paper presents an accurate and fast converging STLF model for industrial applications in a smart grid. In order to improve the forecast accuracy, modifications are devised in two popular techniques: mutual information based feature selection; and enhanced differential evolution algorithm based error minimization. On the other hand, the convergence rate of the overall forecast strategy is enhanced by devising modifications in the heuristic algorithm and in the training process of the artificial neural network. Simulation results show that accuracy of the newly proposed forecast model is 99.5% with moderate execution time, i.e., we have decreased the average execution of the existing bilevel forecast strategy by 52.38%.

Software-defined networking security: pros and cons

Abstract: Software-defined networking (SDN) is a new networking paradigm that decouples the forwarding and control planes, traditionally coupled with one another, while adopting a logically centralized architecture aiming to increase network agility and programability. While many efforts are currently being made to standardize this emerging paradigm, careful attention needs to be paid to security at this early design stage too, rather than waiting until the technology becomes mature, thereby potentially avoiding previous pitfalls made when designing the Internet in the 1980s. This article focuses on the security aspects of SDN networks. We begin by discussing the new security advantages that SDN brings and by showing how some of the long-lasting issues in network security can be addressed by exploiting SDN capabilities. Then we describe the new security threats that SDN is faced with and discuss possible techniques that can be used to prevent and mitigate such threats.

A framework for a distributed key management scheme in heterogeneous wireless sensor networks

Abstract: Key management has become a challenging issue in the design and deployment of secure wireless sensor networks. A common assumption in most existing distributed key management schemes is that all sensor nodes have the same capability. However, recent research works have suggested that connectivity and lifetime of a sensor network can be substantially improved if some nodes are given greater power and transmission capability. Therefore, how to exploit those heterogeneity features in design of a good distributed key management scheme has become an important issue. This paper proposes a unified framework for distributed key management schemes in heterogeneous wireless sensor networks. Analytical models are developed to evaluate its performance in terms of connectivity, reliability, and resilience. Extensive simulation results show that, even with a small number of heterogeneous nodes, the performance of a wireless sensor network can be improved substantially. It is also shown that our analytical models can be used to accurately predict the performance of wireless sensor networks under varying conditions.

Toward energy-efficient cloud computing: Prediction, consolidation, and overcommitment

Abstract: Energy consumption has become a significant concern for cloud service providers due to financial as well as environmental factors. As a result, cloud service providers are seeking innovative ways that allow them to reduce the amount of energy that their data centers consume. They are calling for the development of new energy-efficient techniques that are suitable for their data centers. The services offered by the cloud computing paradigm have unique characteristics that distinguish them from traditional services, giving rise to new design challenges as well as opportunities when it comes to developing energy-aware resource allocation techniques for cloud computing data centers. In this article we highlight key resource allocation challenges, and present some potential solutions to reduce cloud data center energy consumption. Special focus is given to power management techniques that exploit the virtualization technology to save energy. Several experiments, based on real traces from a Google cluster, are also presented to support some of the claims we make in this article.

M2M Communications in 5G: State-of-the-Art Architecture, Recent Advances, and Research Challenges

Abstract: M2M communication offers ubiquitous applications and is one of the leading facilitators of the Internet of Things paradigm. Unlike human-tohuman communication, distinct features of M2M traffic necessitates specialized and interoperable communication technologies. However, most existing solutions offering wired or wireless connectivity have limitations that hinder widespread horizons of M2M applications. To cope with the peculiar nature of M2M traffic, the evolving 5G system considers the integration of key enabling networking technologies for ubiquitous connectivity and guaranteed QoS. This study outlines the state-of-the-art architecture, recent advances, and open research challenges in communication technologies for M2M. Also, an overview of considerable architectural enhancements and novel techniques expected in 5G networks is presented, followed by the resultant services and benefits for M2M communications.

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.