Waheed Iqbal

Containerized workloads are gaining traction due to microservices architecture adaptation in many fields, including healthcare, finance, Internet of Things, and smart cities. Modern data centers are containerized to facilitate this growing demand. Most of the existing resource allocation methods for data centers used efficient scheduling algorithms to place the containers using static computing resources. These static resource allocation techniques are not energy efficient and do not help maximize data center utilization. Dynamic resource allocation and a migration-enabled placement method can reduce energy utilization while improving the utilization of the available computing infrastructure. This article presents and evaluates a novel dynamic resource management system that uses active migrations to minimize energy utilization to serve containerized workloads and improve data center utilization. Our approach uses a deep learning method to estimate the job execution time and then employs an unsupervised learning method to identify similar jobs. Similar jobs are placed and migrated to achieve energy efficiency and better utilization of the available data center infrastructure. Our proposed system is evaluated and compared with the existing state-of-the-art baseline methods. The proposed solution reduces the energy consumption from $\times 1.18$ to $\times 2.35$ compared to the baseline methods while maintaining similar performance.

Processing data generated at high volume and speed from the Internet of Things, smart cities, domotic, intelligent surveillance, and e-healthcare systems require efficient data processing and analytics services at the Edge to reduce the latency and response time of the applications. The fog computing edge infrastructure consists of devices with limited computing, memory, and bandwidth resources, which challenge the construction of predictive analytics solutions that require resource-intensive tasks for training machine learning models. In this work, we focus on the development of predictive analytics for urban traffic. Our solution is based on deep learning techniques localized in the Edge, where computing devices have very limited computational resources. We present an innovative method for efficiently training the gated recurrent-units (GRUs) across available resource-constrained CPU and GPU Edge devices. Our solution employs distributed GRU model learning and dynamically stops the training process to utilize the low-power and resource-constrained Edge devices while ensuring good estimation accuracy effectively. The proposed solution was extensively evaluated using low-powered ARM-based devices, including Raspberry Pi v3 and the low-powered GPU-enabled device NVIDIA Jetson Nano, and also compared them with Single-CPU Intel Xeon machines. For the evaluation experiments, we used real-world Floating Car Data. The experiments show that the proposed solution delivers excellent prediction accuracy and computational performance on the Edge when compared to the baseline methods.

An efficient full-text search is achieved by indexing the raw data with an additional 20 to 30 percent storagecost. In the context of Big Data, this additional storage space is huge and introduces challenges to entertainfull-text search queries with good performance. It also incurs overhead to store, manage, and update the largesize index. In this paper, we propose and evaluate a method to minimize the index size to offer full-text searchover Big Data using an automatic extractive-based text summarization method. To evaluate the effectivenessof the proposed approach, we used two real-world datasets. We indexed actual and summarized datasets usingApache Lucene and studied average simple overlapping, Spearman’s rho correlation, and average rankingscore measures of search results obtained using different search queries. Our experimental evaluation showsthat automatic text summarization is an effective method to reduce the index size significantly. We obtained amaximum of 82% reduction in index size with 42% higher relevance of the search results using the proposedsolution to minimize the full-text index size.

Containers provide a lightweight runtime environment for microservices applications while enabling better server utilization. Automatic optimal allocation of CPU pins to the containers serving specific workloads can help to minimize the completion time of jobs. Most of the existing state-of-the-art focused on building new efficient scheduling algorithms for placing the containers on the infrastructure, and the resources to the containers are allocated manually and statically. An automatic method to identify and allocate optimal CPU resources to the containers can help to improve the efficiency of the scheduling algorithms. In this paper, we introduce a new deep learning-based approach to allocate optimal CPU resources to the containers automatically. Our approach uses the law of diminishing marginal returns to determine the optimal number of CPU pins for containers to gain maximum performance while maximizing the number of concurrent jobs. The proposed method is evaluated using real workloads on a Docker-based containerized infrastructure. The results demonstrate the effectiveness of the proposed solution in reducing the completion time of the jobs by 23% to 74% compared to commonly used static CPU allocation methods.

Recently, the use of NoSQL databases has grown to manage unstructured data for applications to ensure performance and scalability. However, many organizations prefer to transfer data from an operational NoSQL database to a SQL-based relational database for using existing tools for business intelligence, analytics, decision making, and reporting. The existing methods of NoSQL to relational database transformation require manual schema mapping, which requires domain expertise and consumes noticeable time. Therefore, an efficient and automatic method is needed to transform an unstructured NoSQL database into a structured database. In this paper, we proposed and evaluated an efficient method to transform a NoSQL database into a relational database automatically. In our experimental evaluation, we used MongoDB as a NoSQL database, and MySQL and PostgreSQL as relational databases to perform transformation tasks for different dataset sizes. We observed excellent performance, compared to the existing state-of-the-art methods, in transforming data from a NoSQL database into a relational database.