LLM agents increasingly rely on tool calling, and the Model Context Protocol (MCP) standardizes it between agents and tool providers, reducing integration cost and driving rapid growth in tool scale. Yet a standardized interface does not make tool access work at production scale: legacy services are not MCP-callable, fast protocol evolution creates compatibility cost, large tool sets exhaust the context window, and stateful sessions complicate load balancing. We solve these with a shared control point, a centralized MCP Gateway System that makes MCP operational at cloud scale. The gateway breaks the direct-connect data plane and consolidates legacy API integration, protocol bridging, access control, and session-aware routing, while scaling out elastically at low per-call overhead. It scales agent tool access to thousands of cloud operations.

The rapid development of big data and artificial intelligence technology has given new vitality and value to smart cities, which provide rich algorithm models and knowledge computing capabilities. Since the recognition results of the traditional Convolutional Neural Network (CNN) model in the face database are prone to over-fitting, this paper proposes a face recognition algorithm based on an improved CNN model and deep learning. The improved CNN model has a good network image recognition performance, improves the data training speed, and optimizes the network structure parameters. Based on an improved CNN model, using the facial expression recognition (FER2013) data to test the model performance, to achieve more accurate face recognition. Experimental results show that the recognition rate of the improved model and deep learning algorithm on the FER2013 dataset reaches 98.36%, which is 4.63% higher than before the improvement.

The goal of this work is to characterize scientific data transfers and to determine the suitability of dynamic virtual circuit service for these transfers instead of the currently used IP-routed service. Specifically, logs collected by servers executing a commonly used scientific data transfer application, GridFTP, are obtained from three US super-computing/scientific research centers, NERSC, SLAC, and NCAR, and analyzed. Dynamic virtual circuit (VC) service, a relatively new offering from providers such as ESnet and Internet2, allows for the selection of a path on which a rate-guaranteed connection is established prior to data transfer. Given VC setup overhead, the first analysis of the GridFTP transfer logs characterizes the duration of sessions, where a session consists of multiple back-to-back transfers executed in batch mode between the same two GridFTP servers. Of the NCAR-NICS sessions analyzed, 56% of all sessions (90% of all transfers) would have been long enough to be served with dynamic VC service. An analysis of transfer logs across four paths, NCAR-NICS, SLAC-BNL, NERSC-ORNL and NERSC-ANL, shows significant throughput variance, where NICS, BNL, ORNL, and ANL are other US national laboratories. For example, on the NERSC-ORNL path, the inter-quartile range was 695 Mbps, with a maximum value of 3.64 Gbps and a minimum value of 758 Mbps. An analysis of the impact of various factors that are potential causes of this variance is also presented.

Efficient service discovery in dynamic, crossorganizational is one of the challenge aspects in ChinaGrid. Network overlay and search algorithms are two important considerations to the problem. Tree topology of organizations is easily managed but the root is a single point of failure; P2P structure tends to be conversed. To merge the advantages of both, we present a hybrid system with two layers: Tree Layer and Peer Layer. This structure is practical because organizations targeting at sub objects of a subject are inclined to be organized hierarchically as a Superpeer; and all these Superpeers construct an unstructured P2P network that adapts to peer’s interest by Learn Neighbor Algorithm. Experimental evaluation shows that our mechanism exhibits better search performance than fully hierarchical or fully distributed system.

Resource discovery is a basic service in grid computing: gives a description of resources desired and finds the available one to match the description. In computational grid, how to discover resources efficiently has become a crucial factor to evaluate the performance in the whole system. In this paper, we present a bid-based resource discovery algorithm, which converts a resource request into a bidding letter and sends it to a group of physical services owned by the same virtual service to call for bidding. All resources receiving bidding letter make offers to bid according to our algorithm. Job manager selects the best one to response client request. To evaluate the performance of our method, we compare our system with the centralized and peer-to-peer resource discovery approaches. The analysis results show that our system reduces average response time of jobs, leverages the cost of the resource discovery, and improves the system scalability.