Impacts of vehicle automation and connectivity have been studied widely from the perspectives of fuel economy, ecology, and safety. Synthesis of various segments of this literature through review papers has also been presented. However, a systematic review is needed for the growing body of recent literature examining how energy consumption of automated vehicles is influenced by the advancements in powertrain operation and planning/control of driving patterns in different traffic conditions. To address this need, we have first developed an AI-based methodology to effectively find the most relevant papers from a very high volume of related literature. The methodology, comprising natural language processing and machine learning models with humans in the loop, has two phases: search query refinement and relevancy determination. The former ensures that almost all the potentially relevant papers are identified. The latter seeks to automatically eliminate (most) irrelevant papers. Application of our method reduced several thousands of papers from an initial step to 430 potentially relevant papers. Manual review of these papers further characterized many as irrelevant resulting in the final pool of 172 papers. We organized these papers based on various means of influencing power consumption, which are powertrain control, platooning, car-following, intersection management, speed planning, traffic control, lane changing, and on-ramp merging. Synthesis of the papers reveals that the existing studies vary greatly in their design, implementation, and comparison baselines, and thus offer widely differing predictions. Hence, more application specific and comprehensive studies are required to appropriately benchmark energy consumption impact of vehicle automation.