*Result*: An improved pathfinder algorithm using opposition-based learning for tasks scheduling in cloud environment.

*Cloud computing (CC) has become a major topic of study in recent years, providing a cost-effective deployment framework for hosting and running workflows. It is considered as the leading model for distributed computing due to its elasticity, speed, and pay-per-use model. Running scientific applications in the cloud environment with a number of criteria remains a great challenge for researchers, because it requires a robust infrastructure with high computing performance, communication and storage capabilities. Most previous works designed for cloud environments examine the fixed number of resources and aims only to reduce runtime. This has forced scientists to develop the workflow scheduling (WFS) optimization algorithms that strike the right balance between the three main qualities of service (QoS) parameters: time, cost and resource utilization. Due to its substantial implications for the front end and back end of the cloud research business, resource utilization is undoubtedly an important factor that should be taken into consideration. When efficient resource usage is performed in the cloud, good load balancing is obtained. To address the preceding problems, we propose in this paper an innovative workflow scheduling technique in the cloud employing the Pathfinder algorithm (PFA) and the oppositional-based learning algorithm (OBL). The proposed scheduler focused on three objectives (i.e., total execution time, cost, and resource utilization). Simulation tests are carried out using the workflowsim toolkit to evaluate the effectiveness of the suggested approach. The results of the experiments proved that the proposed OBLPFA algorithm outperforms other algorithms called (Particle Swarm technique (PSO), dragonfly (DFA), the Arithmetic Optimization Technique (AOA), the Reptile Search technique (RSA), the Aquila Optimization method (AO), and Lion Optimization method (LOA)) in terms of total execution time, cost, and resource utilization. • We use the OBL algorithm to initialize the population of individuals. • We present the OBLPFA method for scheduling the workflows in the cloud. • We design a multi-objective workflows scheduling strategy for finding optimal scheduling depending on a number of existing objectives namely: makespan, execution cost and resource utilization. • We compare the results of an experimental evaluation of the suggested algorithm with several recent algorithms in the literature. [ABSTRACT FROM AUTHOR]*