Zambia ICT Journal

Power Allocation for Load Shading Using Cascading Demultiplexer Mechanism (PALSU-CDM)

Jameson Mbale — 2025-04-16

The recent drought in Zambia has severely affected the country’s hydroelectric power generation, particularly from the Kariba Dam, leading to a significant reduction in water levels. As a result, the national utility, ZESCO, has been forced to implement load shedding across the nation. The load shedding has been unevenly distributed, causing inconvenience and inefficiency in the use of available power. This paper presents a solution to this problem using a Cascading Demultiplexer Mechanism (PALSU-CDM) for more equitable power allocation. The proposed system leverages cascading demultiplexers to allocate power resources in a fair and balanced manner across various regions, towns, and individual households, based on predetermined schedules. The effectiveness of the system is demonstrated through simulations and real-world applicability, with a focus on Zambia’s power distribution challenges in 2024. The solution aims to optimize power distribution, reduce power imbalances, and ensure more predictable load shedding schedules, that will improve the quality of life for Zambians during this crisis.

An Overview of Virtual Machine Monitoring Techniques and Observability

Yolam Zimba — 2025-04-16

The adoption of cloud computing systems is rapidly increasing, necessitating robust monitoring to ensure optimal performance and a comprehensive understanding of the internal state of these systems. Effective monitoring is crucial for early anomaly detection and preventing potential failures. Unlike grid computing, cluster computing, and high-performance computing. Cloud computing introduces unique features such as scalability and elasticity, which require specialised monitoring approaches. Existing literature indicates that traditional monitoring tools from previous computing paradigms have been adapted for cloud systems. However, these tools often fall short due to the distinct characteristics of cloud environments. This paper identifies a significant gap in research on monitoring techniques specifically designed for virtual resources and highlights the importance of observability in cloud systems. Observability, which facilitates root cause analysis, is essential for quickly resolving faults by examining the internal state of the cloud system. This paper explores the primary characteristics of cloud monitoring tools, providing examples of currently used tools and their features. Additionally, it surveys virtual machine monitoring techniques and emphasises the critical role of observability in ensuring the rapid resolution of issues through logs, metrics, traces, and dependencies.

Utilizing IoT for Intelligent Agriculture: Advancing Crop Monitoring and Automating Irrigation with Real-Time Data on Environmental Variables

Jameson Mbale — 2025-04-16

Advancements in technology have significantly transformed the agriculture sector, with the Internet of Things (IoT) emerging as a key player in enhancing productivity and efficiency. By integrating IoT technologies into smart farming practices, it is possible to monitor and control critical environmental factors such as light, temperature, humidity, and soil conditions in real-time. This approach not only automates irrigation systems, reducing the need for human intervention but also optimizes resource use, lowers operational costs, and improves overall farm management. Smart farming facilitates sustainable agricultural practices by maintaining soil quality, conserving water, enhancing land biodiversity, and promoting a healthier environment. As the global demand for food rises due to population growth, IoT-driven smart farming offers a viable solution for increasing farm productivity and profitability while supporting sustainable agricultural development.

Smart Bin Management System: Transforming waste Management with Internet of Things at Mulungushi University

Charity Chembe — 2025-04-16

Urban sanitation management faces growing challenges due to increasing waste production, limited resources, and inefficiencies in traditional handling methods. The integration of Internet of Things (IoT) technologies offers a transformative solution to these issues. This study focuses on the design, development, and deployment of Smart Bins equipped with IoT sensors for real-time waste monitoring. The Smart Bin Management System, implemented at Mulungushi University, incorporates advanced features, including ultrasonic sensors for waste level detection, edge computing with Arduino devices, and a user-friendly mobile application to ensure seamless data transmission, monitoring, and accessibility. Results from this study demonstrate that Smart Bins significantly enhance waste collection efficiency by enabling dynamic scheduling, reducing operational costs, and optimizing resource allocation. The integration of IoT enables data-driven decision-making and improved scalability. Beyond waste management, the study highlights the potential of Smart Bins as a sustainable solution for urban sanitation challenges, contributing to cleaner environments and improved public health. This research establishes a replicable model that aligns with global sustainability goals.

Leveraging Artificial Intelligence to Boost Academic Performance: A Personalized Learning Framework for Struggling Students

George Kalowa — 2025-04-16

A Hybrid Epidemiological Model Approach to Improvement of Predictive Accuracy in Zambian Infectious Diseases Modelling

Grey Chibawe — 2025-04-16

Recurrent infectious disease outbreaks, including cholera and influenza, as well as recent global pandemics like COVID-19, pose persistent public health challenges in Zambia. Traditional compartmental models based on Ordinary Differential Equations (ODEs), particularly Susceptible-Exposed-Infectious-Recovered (SEIR) frameworks, have long been used to predict disease spread. While these models are relatively simple and require fewer data, they often lack the flexibility to capture non-linear and stochastic factors—such as environmental variables and abrupt policy shifts—that can critically influence epidemic trajectories in resource-limited settings. In contrast, Artificial Neural Network (ANN) approaches excel at learning complex, non-linear relationships directly from data. By incorporating diverse inputs (e.g., climatic variables, demographic distributions), ANNs can adapt to evolving outbreak patterns more effectively than traditional ODE-based methods. However, their reliance on large, high-quality datasets and considerable computational resources can hinder adoption in places with fragmented surveillance systems. To address these complementary strengths and weaknesses, this study explores a hybrid modelling strategy that integrates a parameter-optimised SEIR model with a Transformer-based ANN. Historical COVID-19 data from 2020 to 2024 and environmental data (temperature, rainfall, humidity) were used to develop and validate three models: (1) an SEIR model whose parameters were estimated via curve fitting, (2) a standalone Transformer ANN, and (3) a combined SEIR-ANN ensemble. Model performance was assessed using metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). Results indicate that the hybrid model consistently outperformed the individual SEIR and ANN models, exhibiting the lowest RMSE and MAE. Furthermore, integrating environmental factors into the ANN substantially improved predictive accuracy. These findings highlight the promise of hybrid frameworks in capturing the multifaceted dynamics of infectious diseases in Zambia. By leveraging SEIR’s mechanistic insights alongside the ANN’s capacity to learn from diverse datasets, public health practitioners can improve outbreak predictions and resource allocation. Nevertheless, barriers—such as limited data availability, computational infrastructure, and model interpretability—must be addressed to foster broader implementation. Strengthened data collection systems, increased investment in computational tools, and targeted capacity-building programs are recommended to fully realise the benefits of hybrid epidemiological modelling in Zambia.