We address knowledge-free Bag-of-Tasks non-preemptive scheduling problem on heterogeneous grids, where scheduling decisions are free from information of resources and application characteristics. We consider a scheduling with task replications to overcome possible random bad resource allocation and ensure good performance. We analyze energy consumption of job allocation strategies based on variations of the replication threshold. In order to provide QoS and minimize energy consumption, we perform a joint analysis of two metrics. A case study is given and corresponding results indicate that proposed strategies reduce energy consumption without significant degradation in performance.