With the continuous growth of Internet users, the high concurrency becomes a major challenge in building large-scale electricity-business website system. To solve the problem, the load-balancing algorithm is used to realize the balanced load of each node in the Web service cluster. However, the current load-balancing algorithms generally have some shortcomings. In view of this problem, this paper proposes a dynamic adaptive weight round-robin random load-balancing algorithm (DAWRRRLB). This algorithm takes into account the multiple factors that affect the performance of the server nodes in the Web service cluster, and changes the load performance of nodes in the cluster according to the node in the operation process of the real-time dynamic load. It combines with the Pick-K algorithm to improve the dynamic adaptive weight round-robin random load-balancing algorithm, ensuring the best performance of the server node is providing services. By many experiments, the DAWRRRLB algorithm is proved to be able to effectively improve the load-balancing efficiency.