Search for: All records

The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computational demands on execution platforms, posing challenges to real-time control deadlines. Traditional distributed CPS architectures typically favor on-device inference to avoid network variability and contention-induced delays on remote platforms. However, this design choice places significant energy and computational demands on the local hardware. In this work, we revisit the assumption that cloud-based inference is intrinsically unsuitable for latency-sensitive control tasks. We demonstrate that, when provisioned with high-throughput compute resources, cloud platforms can effectively amortize network and queueing delays, enabling them to match or surpass on-device performance for real-time decision-making. Specifically, we develop a formal analytical model that characterizes distributed inference latency as a function of the sensing frequency, platform throughput, network delay, and task-specific safety constraints. We instantiate this model in the context of emergency braking for autonomous driving and validate it through extensive simulations using real-time vehicular dynamics. Our empirical results identify concrete conditions under which cloud-based inference adheres to safety margins more reliably than its on-device counterpart. These findings challenge prevailing design strategies and suggest that the cloud is not merely a feasible option, but often the preferred inference location for distributed CPS architectures. In this light, the cloud is not as distant as traditionally perceived; in fact, it is closer than it appears. 

Reducing buildings’ carbon emissions is an important sustainability challenge. While scheduling flexible building loads has been previously used for a variety of grid and energy optimizations, carbon footprint reduction using such flexible loads poses new challenges since such methods need to balance both energy and carbon costs while also reducing user inconvenience from delaying such loads. This article highlights the potential conflict between electricity prices and carbon emissions and the resulting tradeoffs in carbon-aware and cost-aware load scheduling. To address this tradeoff, we propose GreenThrift, a home automation system that leverages the scheduling capabilities of smart appliances and knowledge of future carbon intensity and cost to reduce both the carbon emissions and costs of flexible energy loads. At the heart of GreenThrift is an optimization technique that automatically computes schedules based on user configurations and preferences. We evaluate the effectiveness of GreenThrift using real-world carbon intensity data, electricity prices, and load traces from multiple locations and across different scenarios and objectives. Our results show that GreenThrift can replicate the offline optimal and retains 97% of the savings when optimizing the carbon emissions. Moreover, we show how GreenThrift can balance the conflict between carbon and cost and retain 95.3% and 85.5% of the potential carbon and cost savings, respectively. 

Complex events (CEs) play a crucial role in CPS-IoT applications, enabling high-level decision-making in domains such as smart monitoring and autonomous systems. However, most existing models focus on short-span perception tasks, lacking the long-term reasoning required for CE detection. CEs consist of sequences of short-time atomic events (AEs) governed by spatiotemporal dependencies. Detecting them is difficult due to long, noisy sensor data and the challenge of filtering out irrelevant AEs while capturing meaningful patterns. This work explores CE detection as a case study for CPS-IoT foundation models capable of long-term reasoning. We evaluate three approaches: (1) leveraging large language models (LLMs), (2) employing various neural architectures that learn CE rules from data, and (3) adopting a neurosymbolic approach that integrates neural models with symbolic engines embedding human knowledge. Our results show that the state-space model, Mamba, which belongs to the second category, outperforms all methods in accuracy and generalization to longer, unseen sensor traces. These findings suggest that state-space models could be a strong backbone for CPS-IoT foundation models for long-span reasoning tasks. 

We study a hinted heterogeneous multi-agent multi-armed bandits problem (HMA2B), where agents can query low-cost observations (hints) in addition to pulling arms. In this framework, each of the M agents has a unique reward distribution over K arms, and in T rounds, they can observe the reward of the arm they pull only if no other agent pulls that arm. The goal is to maximize the total utility by querying the minimal necessary hints without pulling arms, achieving time-independent regret. We study HMA2B in both centralized and decentralized setups. Our main centralized algorithm, GP-HCLA, which is an extension of HCLA, uses a central decision-maker for arm-pulling and hint queries, achieving O(M^4 K) regret with O(M K log T) adaptive hints. In decentralized setups, we propose two algorithms, HD-ETC and EBHD-ETC, that allow agents to choose actions independently through collision-based communication and query hints uniformly until stopping, yielding O(M^3 K^2) regret with O(M^3 K log T) hints, where the former requires knowledge of the minimum gap and the latter does not. Finally, we establish lower bounds to prove the optimality of our results and verify them through numerical simulations. 

We study the cooperative asynchronous multi-agent multi-armed bandits problem, where each agent's active (arm pulling) decision rounds are asynchronous. That is, in each round, only a subset of agents is active to pull arms, and this subset is unknown and time-varying. We consider two models of multi-agent cooperation, fully distributed and leader-coordinated, and propose algorithms for both models that attain near-optimal regret and communications bounds, both of which are almost as good as their synchronous counterparts. The fully distributed algorithm relies on a novel communication policy consisting of accuracy adaptive and on-demand components, and successive arm elimination for decision-making. For leader-coordinated algorithms, a single leader explores arms and recommends them to other agents (followers) to exploit. As agents' active rounds are unknown, a competent leader must be chosen dynamically. We propose a variant of the Tsallis-INF algorithm with low switches to choose such a leader sequence. Lastly, we report numerical simulations of our new asynchronous algorithms with other known baselines. 

We introduce and study spatiotemporal online allocation with deadline constraints (SOAD), a new online problem motivated by emerging challenges in sustainability and energy. In SOAD, an online player completes a workload by allocating and scheduling it on the points of a metric space (X,d) while subject to a deadlineT. At each time step, a service cost function is revealed that represents the cost of servicing the workload at each point, and the player must irrevocably decide the current allocation of work to points. Whenever the player moves this allocation, they incur a movement cost defined by the distance metricd(⋅, ⋅) that captures, e.g., an overhead cost. SOAD formalizes the open problem of combining general metrics and deadline constraints in the online algorithms literature, unifying problems such as metrical task systems and online search. We propose a competitive algorithm for SOAD along with a matching lower bound establishing its optimality. Our main algorithm, ST-CLIP, is a learning-augmented algorithm that takes advantage of predictions (e.g., forecasts of relevant costs) and achieves an optimal consistency-robustness trade-off. We evaluate our proposed algorithms in a simulated case study of carbon-aware spatiotemporal workload management, an application in sustainable computing that schedules a delay-tolerant batch compute job on a distributed network of data centers. In these experiments, we show that ST-CLIP substantially improves on heuristic baseline methods. 

Electric power and broadband have become essential services for modern economies, but utilities face substantial challenges in providing disruption-free access. Recent legislation, including the US Infrastructure Investment and Jobs Act of 2021, has allocated enormous resources toward improving infrastructure systems. Historically, undergrounding has enhanced system reliability but has been cost effective only in densely populated areas. We investigate the conditions under which undergrounding becomes cost effective, particularly when co-deployed with fiber optic lines. We introduce a novel data-driven cost-benefit model and conduct a detailed localized case study in Shrewsbury, Massachusetts. The results indicate that when undergrounding is viable, aggressively co-undergrounding yields the highest net benefit. This finding is robust across various assumptions. Importantly, our model highlights the importance of assumptions regarding undergrounding’s effectiveness in reducing outages. Our model is readily deployable to other study areas, providing effective decision-making capabilities even with limited data. 

Effective processing, interpretation, and management of sensor data have emerged as a critical component of cyber-physical systems. Traditionally, processing sensor data requires profound theoretical knowledge and proficiency in signal-processing tools. However, recent works show that Large Language Models (LLMs) have promising capabilities in processing sensory data, suggesting their potential as copilots for developing sensing systems. To explore this potential, we construct a comprehensive benchmark, SensorBench, to establish a quantifiable objective. The benchmark incorporates diverse real-world sensor datasets for various tasks. The results show that while LLMs exhibit considerable proficiency in simpler tasks, they face inherent challenges in processing compositional tasks with parameter selections compared to engineering experts. Additionally, we investigate four prompting strategies for sensor processing and show that self-verification can outperform all other baselines in 48% of tasks. Our study provides a comprehensive benchmark and prompting analysis for future developments, paving the way toward an LLM-based sensor processing copilot.