Intelligence of Smart Systems: Model, Bounds, and Algorithms

Abstract

We present a general framework for understanding system intelligence, i.e., the level of system smartness perceived by users, and propose a novel metric for measuring intelligence levels of dynamical human-in-the-loop systems, defined to be the maximum average reward obtained by proactively serving user demands, subject to a resource constraint. Our metric captures two important elements of smartness, i.e., being able to know what users want and pre-serve them, and achieving good resource management while doing so. We provide an explicit characterization of the system intelligence, and show that it is jointly determined by user demand volume (opportunity to impress), demand correlation (user predictability), and system resource and action costs (flexibility to pre-serve).We then propose an online learning-aided control algorithm called Learning-aided Budget-limited Intelligent System Control (LBISC). We show that LBISC achieves an intelligence level that is within O(N (T ) − 1 2 + ) of the highest level, where N (T ) represents the number of data samples collected within a learning period T and is proportional to the user population size in the system, while guaranteeing an O(max(N (T ) − 1 2 / , log(1/ ) 2 )) average resource deficit. Moreover, we show that LBISC possesses an O(max(N (T ) − 1 2 / , log(1/ ) 2 ) + T ) convergence time, which is much smaller compared to the Θ(1/ ) time required for nonlearning based algorithms. The analysis of LBISC rigorously quantifies the impacts of data and user population (captured by N (T )), learning (captured by our learning method), and control (captured by LBISC) on achievable system intelligence, and provides novel insight and guideline into designing future smart systems.

Connectors of smart design and smart systems

“…Obviously, for this reason, their overall design is more challenging than designing their hardware, software, and cyberware components even in the application cases of moderate complexity. This is evidenced by many studies in the literature (Lieberman et al, 2014;Huang, 2016;Mallikarjuna et al, 2020).…”

Towards a Characterisation of Smart Systems: A Systematic Literature Review

“…This could reflect the importance of the interaction between Smart Systems and the users. Moreover, some definitions are already based on systems that are user-centred [106,107,108].…”

Joint Pushing and Caching for Bandwidth Utilization Maximization in Wireless Networks

“…For user k, we assume that A k (t) evolves according to a first-order (F +1)-state Markov chain, denoted as {A k (t) : t = 0, 1, 2, · · · }, which captures temporal correlation of order one of user k's demand process and is a widely adopted traffic model [16]. Let Pr[A k (t + 1) = j|A k (t) = i] denote the transition probability of going to state j ∈F at time slot t + 1 given that the demand state at time slot t is i ∈F for user k's demand process.…”

“…In most cases, the assumption cannot be satisfied, and hence the proposed joint design has limited applications. To address this problem, [10]- [15] consider joint pushing and caching based on statistical information of content requests (e.g., content popularity), while [16] considers online learning-aided joint design adaptive to instantaneous content requests and without priori knowledge of statistical information of content requests. Specifically, [10] optimizes joint pushing and caching to maximize the network capacity in a push-based converged network with limited user storage.…”

“…In [16], the authors maximize the average reward obtained by proactively serving user demands and propose an online learning-aided control algorithm. However, in [15] and [16], only a single user setup is considered without reflecting asynchronous demands for common contents from multiple users, and hence the proposed joint designs may not be directly applied to practical networks with multiple users. Moreover, the pushing policy in [16] can predownload contents only one time slot ahead.…”