In the context of global climate goals and the transition to sustainable energy, modern energy transportation and distribution systems play a crucial role. Electricity transportation and distribution systems would not function without power lines. One of the most challenging tasks facing global power cable asset managers is efficiently managing the enormous and costly network of cables, most of which are nearing or beyond their intended lifespan. Since HVDC systems are more economical and technically superior to HVAC systems for transmission over long distances, they have become increasingly important in the power system. HVDC is preferred for distances ranging from 300 to 800 km for cable-based hookups and direct transmission schemes. This study aims to conduct a review study of the asset management strategies used for HVDC systems. Additionally, it explores the challenges and most recentadvancements in asset management systems incorporating machine learning. Several machine learning algorithms used inrecent studies are examined for asset management in power system applications.