The design of offshore wind farms requires optimizing turbine layouts and electrical cabling simultaneously to maximize annual energy production (AEP) and minimize costs. This paper proposes a novel topology-driven multi-objective evolutionary algorithm (T-MOEA) for offshore wind farm layout optimization (WFLO). The T-MOEA introduces spatial clustering and network-aware mutation operators that account for aerodynamic wake interactions and cable capacity constraints in one integrated framework. Using a bi-objective formulation (AEP vs. total cable cost), the proposed method efficiently searches for turbine placement and routing configurations that balance energy yield and infrastructure expense. We benchmark T-MOEA on a real offshore wind farm and compare it against five state-of-the-art algorithms. Results show that T-MOEA converges faster and achieves a superior Pareto front, improving the hypervolume (HV) by up to 0.65 and reducing inverted generational distance (IGD) by 50% relative to alternatives. The obtained layouts demonstrate a clear trade-off between higher energy output and lower cabling cost, giving practical insight into offshore design decisions. In conclusion, the topology-driven approach significantly enhances optimization performance for wind farm layout design.