Energy-price-driven request dispatcher that forwards client requests to data centers in an electric-cost-saving way. We prepare mapping nodes, which are used as reliable DNS servers, to forward client requests to data centers where electric prices are relatively lower. Mapping Nodes construct a structured P2P network using a distributed Hash table (DHT) for their scalability and availability. Even if the electric price in a data center is much cheaper than the others and client requests are forwarded to the data center. We need to avoid strong workload shifts to data centers even if their electric prices lower rapidly. Cloud service providers can reduce the electric bill even if data centers use the same amount of energy. And then, mapping nodes take into account application latency (measure of time delay experienced in a system) requirements and data center loads, gradually shifting client Requests to electrically-cheaper data centers.