Distributed clouds (DCs) often require a huge amount of energy to provide multiple services to users around the world. Users bring revenue to DC providers based on the quality of service (QoS) of tasks. These tasks are transmitted to DCs through many available Internet service providers (ISPs) with different bandwidth prices and capacities. Besides, power grid prices, and green energy in different DCs differ with different geographical sites. Consequently, it is challenging to execute tasks among DCs in a high-QoS and high-profit way. This work proposes a bi-objective optimization algorithm to maximize the profit of a DC provider, and minimize the loss possibility of all tasks by specifying the allocation of tasks among different ISPs, and task service rates of each DC. A constrained optimization problem is given and solved by a novel Simulated-annealing-based Bi-objective Differential Evolution (SBDE) algorithm to produce a close-to-optimal Pareto set of solutions. The minimum Manhattan distance is further used to obtain a knee solution, and it determines Pareto optimal service rates and task allocation among ISPs. Realistic trace-driven results demonstrate that SBDE realizes less loss possibility of tasks, and higher profit than several state-of-the-art scheduling algorithms.