More and more people are using the internet for data processing, transfer, and storage. With it comes a higher demand for computational power from data servers. Unsurprisingly, the data center industry is becoming an increasingly large industry that is important for people’s daily lives. Data centers cover 2 % of the world’s total electrical consumption and this number is expected to become higher. Running data centers with optimal performance while operating efficiently and as sustainably as possible is a task that is of utmost importance.The way data centers are cooled today is through a CRAH unit that features cooling coils and a fan, the fan blows air over cold coils to prevent damage to server components. Another task for this fan is to create a high differential pressure over the servers using this air, to ensure the air flows in the right direction. The air is uniformly distributed over the servers. With dynamic air-handling measures, it is possible to match the cooling for individual servers, because all servers have different workloads. They generate different amounts of heat. This thesis investigates manual redistribution between servers and how an air-handling damper unit, that sits on the server, is designed to investigate how it can reduce total power draw. Different tests are run in a wind tunnel which houses room for six servers whereas three prototypes are mounted on three of the servers. The main idea to test is that instead of running an even amount of stress on six servers, the same amount of stress is redistributed on only three servers. The ones now running idle have a damper unit blocking the server's rear side. That way the CRAH fan is using less power to create the same differential pressure. Also, the total power draw to all servers is reduced as well. One of the tests was the conventional way of cooling servers today and it had a total power draw of 1362 watts. The test with both redistribution, dampers closed at the rear and turned off servers had a power draw of 951 watts. That is a 30% decrease.