The Internet’s architecture largely and implicitly assumes full-time connectivity, a notion that is embodied in key networking principles including fate sharing, soft state, and the end-to-end principle. In contrast, efforts to allow for more graceful operation in the presence of forced disconnectedness have recently been undertaken that change the underlying style of networking used by applications to accommodate both host-level and hop-by-hop disconnectedness (e.g., for deep space networks where connectivity depends on orbital mechanics). In this paper, we offer an initial exploration of the architectural constructs required to support selective connectivity, whereby a host can choose whether to be “connected ” or “disconnected”. While we keep our notion of selective connectivity general, the driver behind our thinking is to allow hosts to go to sleep to realize energy savings while not sacrificing their standing in the network. Studies show that enabling such sleeping offers large potential energy savings. Specifically, we explore ideas related to assistants, soft state, host-based control, and application primitives. 1

Abstract — In order to be part of a peer-to-peer (P2P) file sharing network a host must be fully powered-on all of the time. In addition to providing a user interface, a P2P host handles query messages and serves requested files. In this paper, we describe the development of a prototype Gnutella-like P2P power management proxy sub-system that handles query messages. This can allow desktop PCs acting as P2P hosts to enter a low-power sleep state for most of the time and be woken-up by the proxy only when needed to serve files. TCP connections with neighbors are maintained by the host when it is awake and by the proxy when the host is sleeping. Experiments show that a low-cost Freescale ColdFire processor can effectively proxy for a P2P host. This suggests that a controller for a Gnutella P2P proxy could be co-located on an Ethernet NIC at low cost. This could lead to significant energy savings by allowing P2P hosts to power manage into a low-power sleep state when not in active use.

The number of edge devices connected to the Internet is increasing at a rapid rate. To maintain network connectivity, the majority of these devices remain completely powered on when idle, wasting unnecessary energy. A novel idea to conserve energy while maintaining network connectivity is to place the computer in standby mode during idle periods and delegate the packet-handling functions to its network interface card (NIC). The NIC, acting as a liaison for the host, can proxy a variety of network protocols, increasing the standby time of the host without compromising its active connections. In this paper, we analyze the requirements of such a packet classifier and design a low-power hardware-based packet classification technique, which, compared to a software-based packet classification technique, consumes 59 % less energy with a 9x speedup.

The Bloom filter (BF) is a well-known space-efficient data structure that answers set membership queries with some probability of false positives. In an attempt to solve many of the limitations of current inter-networking architectures, some recent proposals rely on including small BFs in packet headers for routing, security, accountability or other purposes that move application states into the packets themselves. In this paper, we consider the design of such inpacket Bloom filters (iBF). Our main contributions are exploring the design space and the evaluation of a series of extensions (1) to increase the practicality and performance of iBFs, (2) to enable false-negative-free element deletion, and (3) to provide security enhancements. In addition to the theoretical estimates, extensive simulations of the multiple design parameters and implementation alternatives validate the usefulness of the extensions, providing for enhanced and novel iBF networking applications.