Placing containerized microservices across a fog-cloud continuum requires jointly optimizing network latency, node power consumption, and load balance. This paper studies LJWOA, a three-stage hybrid metaheuristic that adds a Jayastyle elitist refinement and a Lévy-flight restart of the weakest individuals to the Whale Optimization Algorithm (WOA). Evaluation uses six benchmark functions (dimension 30) and synthetic fog-cloud placement instances with 50–300 microservices (CPU workload 200–1500 MI, payload 1–50 MB) on 12–36 heterogeneous fog and cloud nodes, with 15–30 independent runs per setting and Holm-corrected Wilcoxon signed-rank tests. In the original experiments LJWOA attains a lower weighted objective than Jaya, GWO, and PSO at all five scales and than WOA at 50 and 100 microservices, is statistically indistinguishable from WOA at 150–200, and is significantly worse at 300. Additional experiments requested during review use an equal function-evaluation budget and an independent re-implementation: LJWOA remains ahead of Jaya, GWO, SMA, and NSGA-II at every scale and ties with PSO, but its advantage over WOA is not significant at 50–200 and reverses at 300 (0.612 vs. 0.576), and GA and L-SHADE reach lower objective values at all scales. The Lévy stage improves on the twostage variant on held-out instances (raw p < 0.01 at every scale), whereas the stage order has no consistent effect. LJWOA costs 1.36–1.43× WOA per iteration, and all algorithms overload on average 53–91% of nodes under the soft capacity constraint. LJWOA is therefore a modest improvement within the WOA family rather than a state-of-the-art placement method.