A Review on Waste Management Techniques for Sustainable Energy Production

Sekar Kidambi

doi:https://doi.org/10.54216/MOR.040202

Journal of Intelligent Systems and Internet of Things | 2025

DeepBalance: A Deep Reinforcement Learning Framework for Dynamic Load Balancing in Software-Defined Networks

Software-Defined Networks (SDNs) offer unparalleled network control flexibility, yet efficient load balancing is still challenging in dynamic environments. DeepBalance is a novel framework presented in this paper, which deploys dynamic load balancing in SDNs using Deep Reinforcement Learning (DRL). Our solution employs a Deep Q-Network (DQN) agent, which learns the optimal routing policies by monitoring network states and being rewarded based on load distribution. DeepBalance continuously tracks link utilization and intelligently reshifts traffic to alleviate congestion and achieve maximal throughput. We employ a comprehensive simulation environment, which emulates actual network conditions and traffic patterns. Experimental results demonstrate that DeepBalance significantly outperforms traditional load balancing techniques, lowering link utilisation variance by 37% and total throughput by 28% over shortest-path routing. The infrastructure adapts with changing traffic patterns automatically without the necessity of manual reconfiguration, thus naturally circumventing hotspots by making forward-looking path decisions. Additionally, our visualizations illustrate how the DRL agent learns over time to distribute network load more evenly across alternative paths. DeepBalance is a strong candidate for autonomous network optimization in future SDN deployments.

groups

Ali Abdullah Ali mail -

Ghaith Ali Hussein mail -

Bushra Majeed Muter mail -

Oday Ali Hassen mail

link https://doi.org/10.54216/JISIoT.170120

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

Optimizing Hybrid Renewable Energy Systems for Electric Vehicle Charging Stations: A Feasibility Study in Iraqi Cities

The transition from conventional vehicles to electric vehicles (EV) represents an important development in the field of sustainable transportation. To prevent concerns about battery drain, the use of EVs requires the establishment of sufficient charging stations (CS) to recharge vehicle batteries. In Iraq, the infrastructure of electric vehicle charging stations (EVCS) is still limited, which reduces the reliance and reliability of EVs. This study assessed the economic efficiency and feasibility of optimizing hybrid renewable energy systems (HRES) for EVCS in three cities of Iraq addressing the growing demand for renewable energy due to concerns regarding fossil fuel depletion, environmental sustainability, and escalating conventional energy expenses. Hybrid Optimization Model for Multiple Energy Resources (HOMER) program was used considering weather data, load profiles, and equipment specifications. The results indicated that the system with a capacity of 300 kW of photovoltaic (PV), 100 kW of generator (GEN), and 78 units of batteries is found to be the optimal system in all three cities, with the lowest cost of energy (COE) around 0.025 $/kw. The renewable energy fractions of the optimal system in Mosul, Baghdad, and Basrah are 53%, 52.7%, and 52.7%, respectively. This setup achieves annual energy production of 704351 kWh from PV and 509681 kWh from GEN. This arrangement keeps the battery storage at a high state of charge (SoC), guaranteeing system stability and prolonging the battery's life. The system's capacity to reliably fulfil load requirements with less dependence on the DG. These results provide valuable insights into the deployment of HRES to achieve a more sustainable environment.

groups

Othman J. alhayali mail -

Abdalrahman Fatikhan Ataalla mail -

Qusay Hatem Alsultan mail -

Abdullah Fawzi Shafeeq mail -

Sameh aljanabi mail -

Mustafa Abd jalil mail

link https://doi.org/10.54216/JISIoT.170121

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

AI-Driven Decentralized Energy Systems: A Review of Peer-to-Peer Renewable Energy Networks

This work examines the transformational potential of AI-based decentralized energy systems: P2P renewable energy networks interconnect AI, blockchain technology, and multi-agent systems, thus circumventing the barriers of traditional centralized grids. This paper will trace how their latest trends in real-time energy optimization, secure smart contracts, and autonomous coordination of distributed resources can enhance grid resilience, minimize transmission losses, and democratize energy markets. However, it becomes evident that to enable mass adoption; significant challenges must be addressed regarding renewable energy intermittency, scalability limitations, regulatory loopholes, and cybersecurity threats. Through synthesizing current research and the analytical case of Brooklyn Microgrid, this paper discusses some of the barriers and potential future directions that must be emphasized, such as hybrid optimization models, standardized frameworks, and inclusive design for accelerating transitions towards sustainable and equitable energy systems.

groups

M. El-Said mail -

Marwa M. Eid mail

link https://doi.org/10.54216/MOR.040101

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

A Review of Adversarial Deep Learning Models in Neuroscience Research and Clinical Practice

Adversarial deep learning has, therefore, been tabled as one of the key research focus areas in neurosciences, and both the opportunities and drawbacks for the operation of deep learning models on neuroimaging and diagnostic jobs have been unveiled. This review examines these models' weaknesses from adversarial attacks, which can severely affect diagnosis and patient care. For example, it has been shown that slight disturbances in the level of EEG signals can confuse more profound learning algorithms employed for the identification of epilepsy, which can lead to severe diagnostic mistakes. In addition, GANs have the dual role of generating realistic neuroimaging data that can improve diagnostic processes while at the same time using adversarial images that expose the deficits of current models. This duality highlights the need to securely defend models against such risks and employ adversarial training and bio-mimic-based resilient neural network techniques. The consequence of these discoveries should not be underestimated because they reveal the necessity of showing further safety in using deep learning techniques in clinical practices. In addressing these weaknesses, the principle goal of this research is not only to help improve the diagnostic systems but also to expand the knowledge on how adversarial deep learning might affect the health, well-being and safety of patients in neuroscience.

groups

Khaled Sh. Gaber mail -

Ehsan khodadadi mail

link https://doi.org/10.54216/MOR.040102

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

Strategies for Managing and Analyzing Large-Scale Neurological Datasets: A Review of Advanced Computational Methods

The progress of neuroimaging and the availability of big neuro data have brought both opportunities and difficulties in the fast-developing scientific area of computational neuroscience. As this review will show, new ways of managing and analyzing these large and layered datasets are emerging, highlighting the importance of various computational approaches to achieve valuable insights. We assess various methods for performing such analyses, among which we focus on machine learning algorithms like deep learning capable of addressing high-dimensional data characteristics for neuroimaging studies. The proposed method of analyzing multiple structural and functional MRI data in conjunction with electrophysiological and genetic data should help model neurological disorders more accurately. We also describe the preprocessing methods for dealing with data noise and variability, combined with statistical analysis that depends on existing databases to identify previously unknown patterns concerning brain functions and disorders. We also discussed the importance of open-source teamwork spaces and applications, which allow datasets and results to be shared and replicated. This review, therefore, aimed at reviewing the most effective strategies and filling the gaps within the current methodologies that may help enhance the strength and reliability of vast neurological datasets, hence diminishing diagnostic errors and helping formulate the right therapeutic intercessions in neurological disorders. This synthesis emphasizes the choice of a multidisciplinary approach when studying the neural tissues since the issue appears complex.

groups

Abdelaziz Rabehi mail

link https://doi.org/10.54216/MOR.040103

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

Optimization of Carbon Dioxide Emissions Reduction Using Artificial Intelligence: A Review for Industrial and Electric Vehicle Perspectives

Artificial intelligence systems are revolutionizing how industries reduce carbon dioxide emissions in numerous business fields. This study combines research on how artificial intelligence merges with carbon reduction methods, specifically in industrial procedures and electric vehicle manufacturing, with an environmental sustainability focus. Multiple empirical studies and advanced AI models provide insight into sustainability effects caused by AI systems and emission decrease processes. AI technology performs three essential functions to enhance energy optimization pro, mote eco-friendly research, and improve environmental prediction accuracy. The identified information provides essential guidance to policymakers and industrial leaders about AI applications for achieving zero emissions and sustainability targets. The review presents evidence that AI technology can redefine sustainability throughout vehicle production while managing transportation and other fields thus helping solve escalating climate issues and drive eco-friendly developments.

groups

Omnia M. Osama mail -

Marwa M. Eid mail -

El-Sayed M. El Rabaie mail

link https://doi.org/10.54216/MOR.040104

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

Metaheuristic Optimization for Enhancing Cybersecurity Frameworks: An Overview of Methods and Impacts

The increasing number of cyber security threats, notably ransomware and malware, make traditional methods ineffective, hence the need for intelligent methods. This literature review delves into the latest advancements in cyber security technologies that leverage artificial intelligence (AI), machine learning (ML), and deep learning (DL) to enhance system defenses. Key focus areas include improving ransomware detection, developing more effective intrusion detection systems (IDS), securing Internet of Things (IoT) networks, and strengthening cryptographic methods. The reviewed studies highlight how AI-driven techniques—such as convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and adversarial training—automate the detection of threats, optimize cyber security measures, and offer real-time responses to evolving risks. Innovative frameworks like Zero Trust Architecture (ZTA) and AI further bolster security by offering automated threat mitigation and anomaly detection. Furthermore, new metaheuristic algorithms are integrated into IDS systems to enhance the detection rate and minimize false positives. The advanced approaches show how AI could solve the constantly emerging challenges in cyber security and focus on a continuous development approach to make cyber security scalable, robust, and transparent when considering complex attacks.

groups

Shahid Mahmood mail

link https://doi.org/10.54216/MOR.040105

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Galoitica: Journal of Mathematical Structures and Applications | 2025

Linear-Branch-Decomposition of Digraph

The study of graph width parameters is a well-established field within graph theory. Recently, numerous researchers have been actively extending undirected width parameters to directed graphs, resulting in a wide range of studies on directed width parameters. In this paper, we introduce a new concept called Directed Linear-Branch-Width, which extends the (Undirected) Linear-Branch-Width to digraphs. We also investigate its relationship and hierarchy with Directed Path-width, Directed Cut-width, and Directed Neighbourhood- width

groups

Takaaki Fujita mail

link https://doi.org/10.54216/GJMSA.0120104

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

A Review of Generative Deep Learning Techniques for Enhanced Mental Health Diagnostics and Therapeutics

The incredible progress seen in artificial intelligence and the generative deep learning component has catalyzed improvements in diagnosing and treating mental illnesses, something promising for the mental health field today. The review takes a deep dive into various generative deep learning strategies (for instance, GANs, VAEs, and transformers) and their application in mental health. These technologies can also offer better action to analyze the data even before the disorder is fully blown, looking at the patterns of the data collected on individual patients. In addition, we assess the ethical concerns and barriers to adopting such sophisticated methods in healthcare practice, including data management, fairness, and the monitoring of these techniques by professionals. It is argued that generative deep learning can disrupt mental healthcare in a positive way as new ideas that do not even exist in therapies today can be proposed and used to supplement available therapies, which will enhance the quality of care that patients receive and will improve the outcomes. Furthermore, we explore new approaches to research focused on the use of generative models in mental health, calling attention to the need for cross-disciplinary cooperation that would allow us to make the most of these technologies for the benefit of clinical practice and offer them to different groups of patients.

groups

Asifa Iqbal mail

link https://doi.org/10.54216/MOR.040201

Volume & Issue

Vol. Volume 4 / Iss. Issue 2

Details open_in_new

Metaheuristic Optimization Review | 2025

A Review on Waste Management Techniques for Sustainable Energy Production

Energy consumption worldwide is increasing due to increased populations, industrialization, and technological development, underlining the importance of efficient energy use. Waste-to-energy technologies are also known as waste-to-energy systems, whereby the production of Energy and Waste Management are considered interrelated. This review summarizes the present trends and state–of–the–art waste management technologies, where renewable energy systems have been integrated into waste management infrastructure and how optimization algorithms help to improve waste management systems. Anaerobic digestion, pyrolysis, and gasification processes raise wastes and convert them into energy products like biogas and syngas, which follow material flow and recovery. Another important area covered in the study is implementing machine learning-optimized methods, genetic algorithms, and artificial neural networks for waste processing and energy recovery. These threats become as follows: high capital costs, feedstock fluctuations, and public perception are tackled alongside solutions like policy support or engagement of the communities involved. This review focuses on the importance of multi-disciplinary systems to achieve future sustainable Waste-to-Energy systems for both the global environment and energy objectives.

groups

Sekar Kidambi Raju mail

link https://doi.org/10.54216/MOR.040202

Volume & Issue

Vol. Volume 4 / Iss. Issue 2

Details open_in_new