Khaled Taouil
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Khaled Taouil has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Salma Bradai
Orange Innovation Tunisia, Sofrecom, Tunis, Tunisia
3 shared publications - Ahmed Fakhfakh
Laboratory of Signals, Systems, Artificial Intelligence and Networks (SM@RTS), Digital Research Center of Sfax (CRNS), Sfax University, Sfax 3021, Tunisia
2 shared publications - Amal Gassara
Digital Research Center of Sfax, Sfax 3021, Tunisia
2 shared publications - Badii Louati
Research and Innovation Department at Orange Innovation Tunisia-Sofrecom
2 shared publications - Faouzi Derbel
Leipzig University of Applied Sciences
2 shared publications - Michel Giordani
Orange Innovation, 38240 Meylan, France
2 shared publications
Latest Publications
- Open Access
- 23 September 2024
- Published by MDPI AG in Forecasting
- Vol. 6 (3) , 864-884
Predicting Power Consumption Using Deep Learning with Stationary Wavelet
Power consumption in the home has grown in recent years as a consequence of the use of varied residential applications. On the other hand, many families are beginning to use renewable energy, such as energy production, energy storage devices, and electric vehicles. As a result, estimating household power demand is necessary for energy consumption monitoring and planning. Power consumption forecasting is a challenging time series prediction topic. Furthermore, conventional forecasting approaches make it difficult to anticipate electric power consumption since it comprises irregular trend components, such as regular seasonal fluctuations. To address this issue, algorithms combining stationary wavelet transform (SWT) with deep learning models have been proposed. The denoised series is fitted with various benchmark models, including Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), Bidirectional Gated Recurrent Units (Bi-GRUs), Bidirectional Long Short-Term Memory (Bi-LSTM), and Bidirectional Gated Recurrent Units Long Short-Term Memory (Bi-GRU LSTM) models. The performance of the SWT approach is evaluated using power consumption data at three different time intervals (1 min, 15 min, and 1 h). The performance of these models is evaluated using metrics such as Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE). The SWT/GRU model, utilizing the bior2.4 filter at level 1, has emerged as a highly reliable option for precise power consumption forecasting across various time intervals. It is observed that the bior2.4/GRU model has enhanced accuracy by over 60% compared to the deep learning model alone across all accuracy measures. The findings clearly highlight the success of the SWT denoising technique with the bior2.4 filter in improving the power consumption prediction accuracy.
- 23 September 2024
- Published by MDPI AG in Forecasting
- Vol. 6 (3) , 864-884
Open AccessPredicting Power Consumption Using Deep Learning with Stationary Wavelet
Power consumption in the home has grown in recent years as a consequence of the use of varied residential applications. On the other hand, many families are beginning to use renewable energy, such as energy production, energy storage devices, and electric vehicles. As a result, estimating household power demand is necessary for energy consumption monitoring and planning. Power consumption forecasting is a challenging time series prediction topic. Furthermore, conventional forecasting approaches make it difficult to anticipate electric power consumption since it comprises irregular trend components, such as regular seasonal fluctuations. To address this issue, algorithms combining stationary wavelet transform (SWT) with deep learning models have been proposed. The denoised series is fitted with various benchmark models, including Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), Bidirectional Gated Recurrent Units (Bi-GRUs), Bidirectional Long Short-Term Memory (Bi-LSTM), and Bidirectional Gated Recurrent Units Long Short-Term Memory (Bi-GRU LSTM) models. The performance of the SWT approach is evaluated using power consumption data at three different time intervals (1 min, 15 min, and 1 h). The performance of these models is evaluated using metrics such as Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE). The SWT/GRU model, utilizing the bior2.4 filter at level 1, has emerged as a highly reliable option for precise power consumption forecasting across various time intervals. It is observed that the bior2.4/GRU model has enhanced accuracy by over 60% compared to the deep learning model alone across all accuracy measures. The findings clearly highlight the success of the SWT denoising technique with the bior2.4 filter in improving the power consumption prediction accuracy.
- Open Access
P2P Energy Exchange Architecture for Swarm Electrification-Driven PV Communities
Swarm electrification-driven communities face significant challenges, including implementing advanced distributed control in areas with limited ICT access and establishing trust among villagers hesitant to grant access to their assets. This paper proposes a distributed DC microgrid architecture for P2P energy exchange in these communities, ensuring stability and an effective exchange operation. By implementing a Blockchain marketplace specifically designed to suit the rural context, the proposed architecture ensures tracing of exchange transactions to fairly settle participants. Validation experiments demonstrate its efficacy in achieving peak shaving. It provides 11% of the requester’s total demand from the community even while maintaining the constraint of reducing discharge–charge cycles to one per day, thereby preserving battery life. Additionally, the solution reduces prosumer production losses by 16% of the total PV production.
Open AccessP2P Energy Exchange Architecture for Swarm Electrification-Driven PV Communities
Swarm electrification-driven communities face significant challenges, including implementing advanced distributed control in areas with limited ICT access and establishing trust among villagers hesitant to grant access to their assets. This paper proposes a distributed DC microgrid architecture for P2P energy exchange in these communities, ensuring stability and an effective exchange operation. By implementing a Blockchain marketplace specifically designed to suit the rural context, the proposed architecture ensures tracing of exchange transactions to fairly settle participants. Validation experiments demonstrate its efficacy in achieving peak shaving. It provides 11% of the requester’s total demand from the community even while maintaining the constraint of reducing discharge–charge cycles to one per day, thereby preserving battery life. Additionally, the solution reduces prosumer production losses by 16% of the total PV production.
- 16 June 2024
- Published by Springer Nature
- p. 162-182
Blockchain-Based Exchange Place: Genericity vs Performance
- 16 June 2024
- Published by Springer Nature
- p. 162-182
Blockchain-Based Exchange Place: Genericity vs Performance
- Open Access
- 27 May 2024
- Published by MDPI AG in Preprints.org
P2P Energy Exchange Architecture for Swarm Electrification-Driven PV Communities
Swarm electrification-driven communities face significant challenges, including implementing advanced distributed control in areas with limited ICT access and establishing trust among villagers hesitant to grant access to their assets. This paper proposes a distributed DC microgrid architecture for P2P energy exchange in these communities, ensuring stability and effective exchange operation. By implementing a Blockchain marketplace specifically designed to suit the rural context, the proposed architecture ensures tracing of exchange transactions to fairly settle participants. Validation experiments demonstrate its efficacy in achieving peak shaving. It provides 11% of the requester's total demand from the community even while maintaining the constraint of reducing discharge-charge cycles to one per day, thereby preserving battery life. Additionally, the solution reduces prosumer production losses by 16% of the total PV production.
- 27 May 2024
- Published by MDPI AG in Preprints.org
Open AccessP2P Energy Exchange Architecture for Swarm Electrification-Driven PV Communities
Swarm electrification-driven communities face significant challenges, including implementing advanced distributed control in areas with limited ICT access and establishing trust among villagers hesitant to grant access to their assets. This paper proposes a distributed DC microgrid architecture for P2P energy exchange in these communities, ensuring stability and effective exchange operation. By implementing a Blockchain marketplace specifically designed to suit the rural context, the proposed architecture ensures tracing of exchange transactions to fairly settle participants. Validation experiments demonstrate its efficacy in achieving peak shaving. It provides 11% of the requester's total demand from the community even while maintaining the constraint of reducing discharge-charge cycles to one per day, thereby preserving battery life. Additionally, the solution reduces prosumer production losses by 16% of the total PV production.
- Open Access
- 22 June 2022
- Published by MDPI AG in Engineering Proceedings
- Vol. 18 (1) , 26
Limitation of Deep-Learning Algorithm for Prediction of Power Consumption
In recent years, electricity consumption has become high due to the use of several domestic applications in the house. On the other hand, there is a trend of using renewable energy in many houses, such as solar energy, energy-storage systems and electric vehicles. For this reason, forecasting household electricity consumption is essential for managing and planning energy use. Forecasting power consumption is a difficult time-series-forecasting task. Additionally, the electrical load has irregular trend elements, which makes it very difficult to predict the demand for electrical energy using simple forecasting techniques. Therefore, several researchers have worked on intelligent algorithms such as machine-learning and deep-learning algorithms to find a solution for this problem. In this work, we demonstrate that deep-learning algorithms are not always reliable and accurate in predicting power consumption.
- 22 June 2022
- Published by MDPI AG in Engineering Proceedings
- Vol. 18 (1) , 26
Open AccessLimitation of Deep-Learning Algorithm for Prediction of Power Consumption
In recent years, electricity consumption has become high due to the use of several domestic applications in the house. On the other hand, there is a trend of using renewable energy in many houses, such as solar energy, energy-storage systems and electric vehicles. For this reason, forecasting household electricity consumption is essential for managing and planning energy use. Forecasting power consumption is a difficult time-series-forecasting task. Additionally, the electrical load has irregular trend elements, which makes it very difficult to predict the demand for electrical energy using simple forecasting techniques. Therefore, several researchers have worked on intelligent algorithms such as machine-learning and deep-learning algorithms to find a solution for this problem. In this work, we demonstrate that deep-learning algorithms are not always reliable and accurate in predicting power consumption.
- 1 January 2014
- Published by IGI Global Scientific Publishing
- p. 141-164
Power Management in Microgrids
Conventional power generation stations used to be centralized and located far from customers. The transport and distribution infrastructure incur power losses that are mainly due to cabling resistance. Distributed power generation resources located close to customers are sought as a solution to minimize transport power losses. They are also good alternatives in situations where connection to the grid is not possible due to geographical or economical reasons. Furthermore, the adoption of renewable energies as alternatives for the scarce fossil energy sources paves the way to more distributed energy production. These Distributed energy resources, when located in a limited region, can be interconnected with loads and eventually storages to form a microgrid. A microgrid can operate in off-grid, on-grid, or alternate between these modes while optimizing power quality and cost. Multi-Agent Systems (MAS) and Petri nets could be put into contribution for high level planning of energy exchanges within a microgrid. This strategy has been validated on the basis of a dynamic model for the simulation and optimization of power exchanges between different DERs.
- 1 January 2014
- Published by IGI Global Scientific Publishing
- p. 141-164
Power Management in Microgrids
Conventional power generation stations used to be centralized and located far from customers. The transport and distribution infrastructure incur power losses that are mainly due to cabling resistance. Distributed power generation resources located close to customers are sought as a solution to minimize transport power losses. They are also good alternatives in situations where connection to the grid is not possible due to geographical or economical reasons. Furthermore, the adoption of renewable energies as alternatives for the scarce fossil energy sources paves the way to more distributed energy production. These Distributed energy resources, when located in a limited region, can be interconnected with loads and eventually storages to form a microgrid. A microgrid can operate in off-grid, on-grid, or alternate between these modes while optimizing power quality and cost. Multi-Agent Systems (MAS) and Petri nets could be put into contribution for high level planning of energy exchanges within a microgrid. This strategy has been validated on the basis of a dynamic model for the simulation and optimization of power exchanges between different DERs.
- Open Access
- 15 February 2013
- Published by Foundation of Computer Science in International Journal of Computer Applications
- Vol. 64 (21) , 17-22
Mammographic Microcalcifications Detection using Discrete Wavelet Transform
- 15 February 2013
- Published by Foundation of Computer Science in International Journal of Computer Applications
- Vol. 64 (21) , 17-22
Open AccessMammographic Microcalcifications Detection using Discrete Wavelet Transform
- 30 August 2012
- Published by Foundation of Computer Science in International Journal of Computer Applications
- Vol. 51 (21) , 39-46
Design of Automatic Vision-based Inspection System for Monitoring in an Olive Oil Bottling Line
- 30 August 2012
- Published by Foundation of Computer Science in International Journal of Computer Applications
- Vol. 51 (21) , 39-46
Design of Automatic Vision-based Inspection System for Monitoring in an Olive Oil Bottling Line
- 31 May 2011
- Published by Foundation of Computer Science in International Journal of Computer Applications
- Vol. 21 (1) , 40-45
Implementation of an Improved Watershed Algorithm in a Virtex 5 Platform
- 31 May 2011
- Published by Foundation of Computer Science in International Journal of Computer Applications
- Vol. 21 (1) , 40-45
Implementation of an Improved Watershed Algorithm in a Virtex 5 Platform
- 1 November 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Machine Vision Based Quality Monitoring in Olive Oil Conditioning
Compliance with product specification and health measures is of major importance in agribusiness. Production idle time has to be kept to a minimum by preemptive maintenance and service. Operation of production lines has to be within severe safety conditions for workers as well as for food. Besides, high production rates need real time control that can't be done by human workers. Machine vision quality control is a very effective solution for real time quality control in high rate production lines. This paper discusses the feasibility of a video supervision system to be used for quality monitoring in olive oil conditioning line.
- 1 November 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Machine Vision Based Quality Monitoring in Olive Oil Conditioning
Compliance with product specification and health measures is of major importance in agribusiness. Production idle time has to be kept to a minimum by preemptive maintenance and service. Operation of production lines has to be within severe safety conditions for workers as well as for food. Besides, high production rates need real time control that can't be done by human workers. Machine vision quality control is a very effective solution for real time quality control in high rate production lines. This paper discusses the feasibility of a video supervision system to be used for quality monitoring in olive oil conditioning line.