Preferred Language
Articles
/
3BaXAowBVTCNdQwCxfVm
Deep clustering of Lagrangian trajectory for multi-task learning to energy saving in intelligent buildings using cooperative multi-agent
...Show More Authors

The intelligent buildings provided various incentives to get highly inefficient energy-saving caused by the non-stationary building environments. In the presence of such dynamic excitation with higher levels of nonlinearity and coupling effect of temperature and humidity, the HVAC system transitions from underdamped to overdamped indoor conditions. This led to the promotion of highly inefficient energy use and fluctuating indoor thermal comfort. To address these concerns, this study develops a novel framework based on deep clustering of lagrangian trajectories for multi-task learning (DCLTML) and adding a pre-cooling coil in the air handling unit (AHU) to alleviate a coupling issue. The proposed DCLTML exhibits great overall control and is suitable for multi-objective optimisation based on cooperative multi-agent systems (CMAS). The framework of DCLTML is used greedy iterative training to get an optimal set of weights and tabulated as a layer for each clustering structure. Such layers can deal with the challenges of large space and its massive data. Then the layer weights of each cluster are tuned by the Quasi-Newton (QN) algorithm to make the action sequence of CMAS optimal. Such a policy of CMAS effectively manipulates the inputs of the AHU, where the agents of the AHU activate the natural ventilation and set chillers into an idle state when the outdoor temperature crosses the recommended value. So, it is reasonable to assess the impact potential of thermal mass and hybrid ventilation strategy in reducing cooling energy; accordingly, the assigning results of the proposed DCLTML show that its main cooling coil saves >40% compared to the conventional benchmarks. Besides significant energy savings and improving environmental comfort, the DCLTML exhibits superior high-speed response and robustness performance and eliminates fatigue and wear due to shuttering valves. The results show that the DCLTML algorithm is a promising new approach for controlling HVAC systems. It is more robust to environmental variations than traditional controllers, and it can learn to control the HVAC system in a way that minimises energy consumption. The DCLTML algorithm is still under development, but it can potentially revolutionise how HVAC systems are controlled.

Scopus Clarivate Crossref
View Publication
Publication Date
Thu Sep 14 2023
Journal Name
Al-khwarizmi Engineering Journal
Applying Scikit-learn of Machine Learning to Predict Consumed Energy in Al-Khwarizmi College of Engineering, Baghdad, Iraq
...Show More Authors

Globally, buildings use about 40% of energy. Many elements, such as the physical properties of the structure, the efficiency of the cooling and heating systems, the activity of the occupants, and the building’s sustainability, affect the energy consumption of a building. It is really difficult to predict how much energy a building will need. To improve the building’s sustainability and create sustainable energy sources to reduce carbon dioxide emissions from fossil fuel combustion, estimating the building's energy use is necessary. This paper explains the energy consumed in the lecture building of the Al-Khwarizmi College of Engineering, University of Baghdad (UOB), Baghdad, Iraq. The weather data and the building construction informati

... Show More
Publication Date
Tue Apr 02 2024
Journal Name
Al-iraqia Journal Of Scientific Engineering Research
Prioritise Five Tafseer Translators Using Clustering Technique for Surah Al-Baqarah
...Show More Authors

View Publication Preview PDF
Crossref
Publication Date
Fri Oct 30 2020
Journal Name
Journal Of Economics And Administrative Sciences
The use of multi choice Goal Programming to reduce storage and shortage costs of blood units in health care centers
...Show More Authors

We use of multi-choice Goal Programming (MCGP), which is a developed model of Goal Programming where it is used in circumstances of the multiplicity and difference of goals when choosing between decision alternatives in cases of allocating resources, as it is a model that seeks to find the closest and best solutions to the specific values ​​of the goals within the aspiration levels, as the first goal in the multi-choice goal programming model that is used to reduce the total cost of storage and shortage, while the other goal was to reduce the difference between the real demand that the hospitals need from the blood transfusion center and the units that already achieved. The case Iraqi Center

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sat Jan 03 2015
Journal Name
Journal Of Engineering And Development
3D Presentation for Baghdad University Buildings Using Total Station Device
...Show More Authors

capable of the measuring with a high degree of precision in a single instrument. Total stations device are used for station setting up, setting-outmany points from one station. Their major purpose of this work is to take advantage of total station for setting up building and to establish 3D representation using AutoCAD program. The area of the study was Civil Engineering Department at Baghdad University campus AL Jadiriyah. The completion of the work is done in two stages; 1. The field work: In this stage, the Total Station Nikon Nivo-5C was selected for the current study. This device was measured horizontal and vertical distance, elevations, and coordinates from a single set up. This data directly stored on memory. 2. The office work: In t

... Show More
Publication Date
Mon Oct 02 2023
Journal Name
Journal Of Engineering
Microgrid Integration Based on Deep Learning NARMA-L2 Controller for Maximum Power Point Tracking
...Show More Authors

This paper presents a hybrid energy resources (HER) system consisting of solar PV, storage, and utility grid. It is a challenge in real time to extract maximum power point (MPP) from the PV solar under variations of the irradiance strength.  This work addresses challenges in identifying global MPP, dynamic algorithm behavior, tracking speed, adaptability to changing conditions, and accuracy. Shallow Neural Networks using the deep learning NARMA-L2 controller have been proposed. It is modeled to predict the reference voltage under different irradiance. The dynamic PV solar and nonlinearity have been trained to track the maximum power drawn from the PV solar systems in real time.

Moreover, the proposed controller i

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sun Jun 20 2021
Journal Name
Baghdad Science Journal
Wireless Propagation Multipaths using Spectral Clustering and Three-Constraint Affinity Matrix Spectral Clustering
...Show More Authors

This study focused on spectral clustering (SC) and three-constraint affinity matrix spectral clustering (3CAM-SC) to determine the number of clusters and the membership of the clusters of the COST 2100 channel model (C2CM) multipath dataset simultaneously. Various multipath clustering approaches solve only the number of clusters without taking into consideration the membership of clusters. The problem of giving only the number of clusters is that there is no assurance that the membership of the multipath clusters is accurate even though the number of clusters is correct. SC and 3CAM-SC aimed to solve this problem by determining the membership of the clusters. The cluster and the cluster count were then computed through the cluster-wise J

... Show More
View Publication Preview PDF
Scopus (5)
Crossref (3)
Scopus Clarivate Crossref
Publication Date
Thu Feb 01 2018
Journal Name
Journal Of Economics And Administrative Sciences
The technique of converting multi-choice mathematical programming into linear mathematical programming to find the optimal solution
...Show More Authors

The study deals with the issue of multi-choice linear mathematical programming. The right side of the constraints will be multi-choice. However, the issue of multi-purpose mathematical programming can not be solved directly through linear or nonlinear techniques. The idea is to transform this matter into a normal linear problem and solve it In this research, a simple technique is introduced that enables us to deal with this issue as regular linear programming. The idea is to introduce a number of binary variables And its use to create a linear combination gives one parameter was used multiple. As well as the options of linear programming model to maximize profits to the General Company for Plastic Industries product irrigation sy

... Show More
View Publication Preview PDF
Crossref
Publication Date
Wed Jan 01 2020
Journal Name
International Conference Of Numerical Analysis And Applied Mathematics Icnaam 2019
Functionalized multi-walled carbon nanotubes network sensor for NO2 gas detection at room temperature
...Show More Authors

View Publication
Scopus (6)
Crossref (6)
Scopus Clarivate Crossref
Publication Date
Wed Mar 10 2021
Journal Name
Periodicals Of Engineering And Natural Sciences (pen)
A hybrid Grey Wolf optimizer with multi-population differential evolution for global optimization problems
...Show More Authors

View Publication
Scopus (2)
Crossref (1)
Scopus Crossref
Publication Date
Wed Nov 01 2017
Journal Name
Journal Of Computational And Theoretical Nanoscience
Solution for Multi-Objective Optimisation Master Production Scheduling Problems Based on Swarm Intelligence Algorithms
...Show More Authors

The emphasis of Master Production Scheduling (MPS) or tactic planning is on time and spatial disintegration of the cumulative planning targets and forecasts, along with the provision and forecast of the required resources. This procedure eventually becomes considerably difficult and slow as the number of resources, products and periods considered increases. A number of studies have been carried out to understand these impediments and formulate algorithms to optimise the production planning problem, or more specifically the master production scheduling (MPS) problem. These algorithms include an Evolutionary Algorithm called Genetic Algorithm, a Swarm Intelligence methodology called Gravitational Search Algorithm (GSA), Bat Algorithm (BAT), T

... Show More
View Publication Preview PDF
Scopus (15)
Crossref (11)
Scopus Crossref