For an ISP (Internet Service Provider) which has deployed P2P caches in more than one AS (autonomous system), cooperative caching which makes their caches cooperate with each other can save more cost of carrying P2P traffic than independent caching for the ISP. However, existing cooperative caching schemes only use objects' popularity as the measurement to decide which objects should be cached, and cost on intra-ISP links that has great impact on the benefits of cooperative caching is not considered. In this paper, we propose a novel cooperative caching scheme named C-LGV (Cooperative, Lowest Global Value). C-LGV uses cost on intra-ISP links as well as objects' popularity to evaluate each object's global value (a new concept defined to estimate the benefits of caching or replacing an object), and objects with the lowest global values will be evicted when each local cache needs to replace its cached contents. Results of both synthetic and real traces driven simulations indicate that C-LGV can reduce the cost of carrying P2P traffic by at least 23% compared to existing cooperative caching schemes.

The idea of performing client-server computing by transmission of executable programs between clients and servers has become highly popular among researchers and developers who are engaged in intelligent network services. Computing based on mobile agents is an important aspect of this idea. This paper focuses on researching the migration process of agents. A model based on modules is devised for constructing agents. A concurrent schedule method is presented, with which the agent migration can be easily implemented. Most of unnecessary transmission of codes and data can be avoided by module reuse. Consequently, the executing period of mobile agents is reduced and their efficiency is improved. Additionally, a Fault-tolerance mechanism is designed in the system to ensure that the agent can work even when some faults occur in the network or in the host.