Papers by Abdelaaziz EL HIBAOUI
Applying Deep Learning Model to Predict Smart Grid Stability
2021 9th International Renewable and Sustainable Energy Conference (IRSEC), 2021
Smart grid is an advanced concept of power systems which harmonizes electricity and communication... more Smart grid is an advanced concept of power systems which harmonizes electricity and communication in systems networks. It provides information for the producers, operators, and the consumers in real time. There is an extreme demand to efficiently conduct the power supplied to the consumption domains such as households, organizations, industries, and smart cities. In this respect, a smart grid with a stable system is being required to supply the dynamic power requirements. Predicting smart grid stability is still challenging due to the many factors which affect the stability of grid, one of these factors is customer and producer participation because identifying the participation can lead to the stability of smart grid. In this work, we propose a deep learning model based on Densely Connected Convolutional Network and Residual network structure to detect the stability of smart grids. The results of the proposed model are compared to other popular classifier models used in different studies. Those models are Support Vector Machine, Logistic Regression, Decision Tree, Random Forest, Gradient Boosted Trees, Multilayer neural network, Gated Recurrent Units, Recurrent Neural Networks and Long Short-Term Memory and the proposed model outperforms the other models.
Probabilistic algorithms are designed to handle problems which do not admit ecient deterministic ... more Probabilistic algorithms are designed to handle problems which do not admit ecient deterministic solutions. In the case of the election problem in a network of processors, many algorithms are available which are applicable under appropriate assumptions. The goal of this study is to introduce a uniform probabilistic distributed algorithm.
International Journal of Electrical and Computer Engineering, 2021
Predicting electricity power is an important task, which helps power utilities in improving their... more Predicting electricity power is an important task, which helps power utilities in improving their systems’ performance in terms of effectiveness, productivity, management and control. Several researches had introduced this task using three main models: engineering, statistical and artificial intelligence. Based on the experiments, which used artificial intelligence models, multilayer neural networks model has proven its success in predicting many evaluation datasets. However, the performance of this model depends mainly on the type of activation function. Therefore, this paper introduces an experimental study for investigating the performance of the multilayer neural networks model with respect to different activation functions and different depths of hidden layers. The experiments in this paper cover the comparison among eleven activation functions using four benchmark electricity datasets. The activation functions under examination are sigmoid, hyperbolic tangent, SoftSign, SoftPl...
E_Swish Beta: Modifying Swish Activation Function for Deep Learning Improvement
Enabling Machine Learning Applications in Data Science, 2021
Data for: Algorithms for Smart Grid Management
This tool is developed in Java using Sockets. It allows to implement and simulate the execution o... more This tool is developed in Java using Sockets. It allows to implement and simulate the execution of distributed algorithms on distributed systems. Each node is able to perform its own tasks. Nodes communicate only by exchanging messages and no global clock or other information is needed.
Survey and a New Taxonomy of Proofs of Retrievability on the Cloud Storage
The 4th International Conference on Networking, Information Systems amp Security., 2021
Proof of Retrievability (PoR) is a technique used to ensure the authenticity of data on outsource... more Proof of Retrievability (PoR) is a technique used to ensure the authenticity of data on outsourced storage services. It improves the soundness and the robustness of the data integrity scheme and allows clients to recover the remote data. Under the circumstance of considering untrusted parties including the Cloud Storage Provider (CSP) and Third Party Authenticator (TPA), incorporating PoR and zero-knowledge Proofs, which is another technique used to allow a prover to convince a verifier that a secret exists without revealing the secret itself, will ensure client integrity verification, strengthen privacy, and improve fairness to both sides. In this paper, we present, on one hand, the state-of-the-art of PoR under zero-knowledge constructs following an existing data integrity scheme taxonomy of cloud storage. We analyze the PoR scheme formalism and its similarities with zero-knowledge concepts, in addition to the techniques used to settle robustness and zero-knowledge proofs methods. On the other hand, we propose our improved taxonomy of proofs of retrievability enriched by the zero-knowledge, the cryptography model, and the cryptographic setup. The proposed taxonomy equips researchers with a tool to think about the PoR scheme from those perspectives. In the end, we state some fruitful lines of works that PoR can take advantage of; i.e Bulletproofs, Interactive Oracle Proofs, and Interactive Oracle Proofs of Proximity For Reed-Solomon.
Modelization of Smart Grid - managing the local level
2016 International Renewable and Sustainable Energy Conference (IRSEC), 2016
The revolutionary evolution of the ICT (Information and Communication Technologies) has completel... more The revolutionary evolution of the ICT (Information and Communication Technologies) has completely changed our lifestyle. It becomes more comfortable and smarter. Against this background, Smart Grid is an electrical network on which smart components are being added to reach better performances, together in production, in distribution and consumption. This paper presents a modelization of Smart Grid and proposes a Branch and Bound algorithm to manage its local level.
2018 6th International Renewable and Sustainable Energy Conference (IRSEC), 2018
In recent times, consumers and politicians from Central and Eastern Europe complain that some foo... more In recent times, consumers and politicians from Central and Eastern Europe complain that some food products sold in their regions are of lower quality and less healthy if compared to those sold under the same brands in Western Europe. This situation, that concerns exclusively food produced and sold under even well-known multinational brands, is brought back by many food MultiNational Companies to the necessity to adapt their products to local tastes and gastronomic traditions. Many tests and studies carried out at European level prove poorer-quality products offered by MultiNational Companies to Central and Eastern Europe consumers even if with the same packaging and prices (or even more expensive) of Western countries. This is a very novel issue, and to the best of our knowledge, there is not any scientific paper yet dealing with this issue. Therefore, the aim of the study is to add new knowledge to this field and to shed light on the multiple aspects linked to dual quality food. The analysis, essentially theoretical, has pointed out that in addition to the traditional problems of market failures, there can be positive implications in terms of opportunities of competitiveness for multinational food companies.
E_Swish Beta: Modifying Swish Activation Function for Deep Learning Improvement
Enabling Machine Learning Applications in Data Science, 2021
Modelization of Smart Grid - managing the local level
2016 International Renewable and Sustainable Energy Conference (IRSEC), 2016
The revolutionary evolution of the ICT (Information and Communication Technologies) has completel... more The revolutionary evolution of the ICT (Information and Communication Technologies) has completely changed our lifestyle. It becomes more comfortable and smarter. Against this background, Smart Grid is an electrical network on which smart components are being added to reach better performances, together in production, in distribution and consumption. This paper presents a modelization of Smart Grid and proposes a Branch and Bound algorithm to manage its local level.
Energy consumption prediction model with deep inception residual network inspiration and LSTM
Mathematics and Computers in Simulation, 2021
Abstract Predicting electricity consumption is not an easy task depending on many factors that af... more Abstract Predicting electricity consumption is not an easy task depending on many factors that affect energy consumption. Therefore, electricity utilities and governments are always searching for intelligent models to improve the accuracy of prediction and recently, deep learning becomes the most used field in prediction. In this paper, we introduce a deep learning model based on deep feedforward neural networks and Long Short-Term Memory. The deep feedforward neural networks architecture was inspired by the Inception Residual Network v2, which achieved the highest accuracy in image classification. We compared our proposed model to other recent deep learning models in two different datasets: dataset from the Distribution Network Station of Tetouan city in Morocco and dataset from the North American Utility. The proposed model achieved the smallest error of Root Mean Square Error comparing to its counterparts.
Energy consumption prediction model with deep inception residual network inspiration and LSTM
Mathematics and Computers in Simulation, 2021
Abstract Predicting electricity consumption is not an easy task depending on many factors that af... more Abstract Predicting electricity consumption is not an easy task depending on many factors that affect energy consumption. Therefore, electricity utilities and governments are always searching for intelligent models to improve the accuracy of prediction and recently, deep learning becomes the most used field in prediction. In this paper, we introduce a deep learning model based on deep feedforward neural networks and Long Short-Term Memory. The deep feedforward neural networks architecture was inspired by the Inception Residual Network v2, which achieved the highest accuracy in image classification. We compared our proposed model to other recent deep learning models in two different datasets: dataset from the Distribution Network Station of Tetouan city in Morocco and dataset from the North American Utility. The proposed model achieved the smallest error of Root Mean Square Error comparing to its counterparts.
Sustainable Cities and Society, 2018
In this paper, we will consider a modelization of Smart Grid on three subcomponents: local level,... more In this paper, we will consider a modelization of Smart Grid on three subcomponents: local level, microgrid level and T &D level. Thus and on one hand, we will propose an algorithm that manages its local level. Our algorithm is paired with Branch and Bound algorithm to solve Knapsack Problem. The main goal of this algorithm is to regulate consumption peaks and manage the priority of domestic appliances, by spreading at best the energy depending on the priority and consumption without exceeding the total energy received. Furthermore, we will introduce an asynchronous distributed max-flow algorithm to resolve the routing problem in order to optimize the T &D level. This algorithm uses a local computation to compute max-flow. Nodes communicate only by exchanging messages and no global information is needed. Our algorithm uses more than one augmenting path at each iteration allowing optimization of the execution time required for computing the max-flow.
Sustainable Cities and Society, 2018
In this paper, we will consider a modelization of Smart Grid on three subcomponents: local level,... more In this paper, we will consider a modelization of Smart Grid on three subcomponents: local level, microgrid level and T &D level. Thus and on one hand, we will propose an algorithm that manages its local level. Our algorithm is paired with Branch and Bound algorithm to solve Knapsack Problem. The main goal of this algorithm is to regulate consumption peaks and manage the priority of domestic appliances, by spreading at best the energy depending on the priority and consumption without exceeding the total energy received. Furthermore, we will introduce an asynchronous distributed max-flow algorithm to resolve the routing problem in order to optimize the T &D level. This algorithm uses a local computation to compute max-flow. Nodes communicate only by exchanging messages and no global information is needed. Our algorithm uses more than one augmenting path at each iteration allowing optimization of the execution time required for computing the max-flow.
Analyse de quelques algorithmes probabilistes à délais aléatoires
Http Www Theses Fr, 2006
Dans la premiere partie de cette etude, nous proposons et analysons des algorithmes probabilistes... more Dans la premiere partie de cette etude, nous proposons et analysons des algorithmes probabilistes d'election uniforme dans des graphes de types arbres, les k-arbres et les polyominoides. Ces algorithmes utilisent des durees de vie aleatoires associees aux sommets decouverts (sommets feuilles ou simpliciaux). Ces durees sont des variables aleatoires independantes et sont localement engendrees au fur et a mesure que les sommets sont decouverts. Dans la seconde partie, nous analysons un algorithme probabiliste de synchronisation pour le probleme de rendez-vous avec agendas dynamiques. L'objectif est de trouver un couplage maximal dans un graphe donne. Ensuite, nous proposons et etudions un modele de diffusion a delai aleatoire pour la transmission d'un message dans un reseau. Finalement, dans la derniere partie, nous exposons les outils utilises pour implementer la simulation des algorithmes distribues.
International Journal of Advanced Computer Science and Applications, 2015
Over the past two decades, the use of distributed embedded systems is wide in many applications. ... more Over the past two decades, the use of distributed embedded systems is wide in many applications. One way to guarantee that these systems tolerate transient faults is done by making them self-stabilizing systems, which automatically recover from any transient fault. In this paper we present a formalism of self-stabilization concept based on Linear Temporal Logic (LTL), and model checked the self-stabilization in embedded systems. Using a case study inspired by industrial practice, we present in detail a model checking to verify the self stabilization property of our embedded system.
International Journal of Advanced Computer Science and Applications, 2013
Probabilistic algorithms are designed to handle problems that do not admit deterministic effectiv... more Probabilistic algorithms are designed to handle problems that do not admit deterministic effective solutions. In the case of the election problem, many algorithms are available and applicable under appropriate assumptions, for example: the uniform election in trees, k−trees and polyominoids. In this paper, first, we introduce a probabilistic algorithm for the uniform election in the triangular grid graphs, then, we expose the set of rules that generate the class of the triangular grid graphs. The main of this paper is devoted to the analysis of our algorithm. We show that our algorithm is totally fair in so far as it gives the same probability to any vertex of the given graph to be elected.
Hypergraph model for anonymous communications
2012 International Conference on Multimedia Computing and Systems, 2012
Distributed networks such as virtual networks like P2P networks or physical networks like mobile ... more Distributed networks such as virtual networks like P2P networks or physical networks like mobile ad hoc networks have no centralized structure. Communications across these networks are exposed to attacks, particularly against the respect for private information of users. Two ideas are used to improve the security of users' privacy. The first is gathering of users in communities of trust. The second is the use of anonymity techniques that preserve identity of users but also of these communities of trust. In this paper, we propose HypAnoCom, a new model for anonymous communications based on hypergraph paradigm. Participants belong to different communities can communicate without disclosing their identities. We develop an algorithm for discovering minimal transversals. Those transversals are used to preserve privacy of users or groups. Indeed, we define a routing protocol based on selective hierarchy to insure communications. We show that our model satisfies following security conditions: identity privacy, location privacy and robustness against several attacks. Our model is particularly suitable for distributed and dynamic networks such as Ad-hoc mobile and Peer-to-Peer networks. Our model tackles churn by using hyperedges at each hop.
In this paper we introduce and analyze a probabilistic distributed algorithm for minimum spanning... more In this paper we introduce and analyze a probabilistic distributed algorithm for minimum spanning tree construction. Our algorithm is based firstly on the handshake algorithm that produces firstly k sub-spanning trees, where k is the size of the maximal matching produced. Secondly, the merged step of our algorithm is executed in a distributed manner and following some roles to reduce the total number of those sub-spanning from k to 1. We proof that the residual graph is acyclic and all vertices belong to it. A detailed analysis of the number of exchanged messages is carried on to validate the effectiveness of our algorithm.
Uploads
Papers by Abdelaaziz EL HIBAOUI