The service placement problem in a fog-cloud pertains to the intricate task of ascertaining the optimal placement locations for diverse service replicas that constitute an Internet of Things (IoT) application within a distributed computing architecture. Nonetheless, due to the heterogeneous nature of fog nodes and cloud data centers, the constantly evolving nature of IoT applications, the pressing demand for real-time data processing with minimal latency, and the imperative of cost optimization, service placement remains an arduous and intricate challenge. Heuristic algorithms are widely employed to derive near-optimal solutions. The present study introduces a novel heuristic approach to service placement and load distribution in fog-cloud environments called Delay and Cost-aware Service Placement (DCSP). This approach takes into account both delay and cost and thereby enables the optimal utilization of resources, delay, and cost for delay-sensitive services. DCSP features continual adjustment of the number of service replicas based on workload and resource availability, ensuring efficient usage of fog and cloud computing resources and optimal delay for each request. The results of simulation experiments that compare various algorithms demonstrate the superiority of DCSP, which outperforms other methods in cost, average delay, and resource utilization. The experimental results not only illustrate the exceptional superiority of our method over MOHGA, MVC, and the Local method in terms of delay and utilization but also demonstrate our efforts to maintain cost at a comparable level. Our method surpasses all of them in utilization, achieving remarkable improvements ranging from 7.4 % to 49.7 %. Furthermore, it outperforms them in terms of delay, with significant enhancements ranging from 2.1 % to 19.3 %.
