Subsecond tsunamis and delays in decentralized electronic systems

Abstract

Driven by technological advances and economic gain, society’s electronic systems are becoming larger, faster, more decentralized and autonomous, and yet with increasing global reach. A prime example are the networks of financial markets which-in contrast to popular perception-are largely all-electronic and decentralized with no top-down real-time controller. This prototypical system generates complex subsecond dynamics that emerge from a decentralized network comprising heterogeneous hardware and software components, communications links, and a diverse ecology of trading algorithms that operate and compete within this all-electronics environment. Indeed, these same technological and economic drivers are likely to generate a similarly competitive all-electronic ecology in a variety of future cyberphysical domains such as e-commerce, defense and the transportation system, including the likely appearance of large numbers of autonomous vehicles on the streets of many cities. Hence there is an urgent need to deepen our understanding of stability, safety and security across a wide range of ultrafast, large, decentralized all-electronic systems-in short, society will eventually need to understand what extreme behaviors can occur, why, and what might be the impact of both intentional and unintentional system perturbations. Here we set out a framework for addressing this issue, using a generic model of heterogeneous, adaptive, autonomous components where each has a realistic limit on the amount of information and processing power available to it. We focus on the specific impact of delayed information, possibly through an accidental shift in the latency of information transmission, or an intentional attack from the outside. While much remains to be done in terms of developing formal mathematical results for this system, our preliminary results indicate the type of impact that can occur and the structure of a mathematical theory which may eventually describe it.