Search

We present a novel data-driven simulation environment for modeling traffic in metropolitan street intersections. Using real-world tracking data collected over an extended period of time, we train trajectory forecasting models to learn agent interactions and environmental constraints that are difficult to capture conventionally. Trajectories of new agents are first coarsely generated by sampling from the spatial and temporal generative distributions, then refined using state-of-the-art trajectory forecasting models. The simulation can run either autonomously, or under explicit human control conditioned on the generative distributions. We present the experiments for a variety of model configurations. Under an iterative prediction scheme, the way-point-supervised TrajNet++ model obtained 0.36 Final Displacement Error (FDE) in 20 FPS on an NVIDIA A100 GPU., Comment: CVPR 2024 Workshop POETS Oral

We introduce Constellation, a dataset of 13K images suitable for research on detection of objects in dense urban streetscapes observed from high-elevation cameras, collected for a variety of temporal conditions. The dataset addresses the need for curated data to explore problems in small object detection exemplified by the limited pixel footprint of pedestrians observed tens of meters from above. It enables the testing of object detection models for variations in lighting, building shadows, weather, and scene dynamics. We evaluate contemporary object detection architectures on the dataset, observing that state-of-the-art methods have lower performance in detecting small pedestrians compared to vehicles, corresponding to a 10% difference in average precision (AP). Using structurally similar datasets for pretraining the models results in an increase of 1.8% mean AP (mAP). We further find that incorporating domain-specific data augmentations helps improve model performance. Using pseudo-labeled data, obtained from inference outcomes of the best-performing models, improves the performance of the models. Finally, comparing the models trained using the data collected in two different time intervals, we find a performance drift in models due to the changes in intersection conditions over time. The best-performing model achieves a pedestrian AP of 92.0% with 11.5 ms inference time on NVIDIA A100 GPUs, and an mAP of 95.4%.

Scheduling packets with end-to-end deadline constraints in multihop networks is an important problem that has been notoriously difficult to tackle. Recently, there has been progress on this problem in the worst-case traffic setting, with the objective of maximizing the number of packets delivered within their deadlines. Specifically, the proposed algorithms were shown to achieve $\Omega(1/\log(L))$ fraction of the optimal objective value if the minimum link capacity in the network is $C_{\min}=\Omega(\log (L))$, where $L$ is the maximum length of a packet's route in the network (which is bounded by the packet's maximum deadline). However, such guarantees can be quite pessimistic due to the strict worst-case traffic assumption and may not accurately reflect real-world settings. In this work, we aim to address this limitation by exploring whether it is possible to design algorithms that achieve a constant fraction of the optimal value while relaxing the worst-case traffic assumption. We provide a positive answer by demonstrating that in stochastic traffic settings, such as i.i.d. packet arrivals, near-optimal, $(1-\epsilon)$-approximation algorithms can be designed if $C_{\min} = \Omega\big(\frac{\log (L/\epsilon) } {\epsilon^2}\big)$. To the best of our knowledge, this is the first result that shows this problem can be solved near-optimally under nontrivial assumptions on traffic and link capacity. We further present extended simulations using real network traces with non-stationary traffic, which demonstrate that our algorithms outperform worst-case-based algorithms in practical settings.

Blind and low-vision (BLV) people rely on GPS-based systems for outdoor navigation. GPS's inaccuracy, however, causes them to veer off track, run into obstacles, and struggle to reach precise destinations. While prior work has made precise navigation possible indoors via hardware installations, enabling this outdoors remains a challenge. Interestingly, many outdoor environments are already instrumented with hardware such as street cameras. In this work, we explore the idea of repurposing existing street cameras for outdoor navigation. Our community-driven approach considers both technical and sociotechnical concerns through engagements with various stakeholders: BLV users, residents, business owners, and Community Board leadership. The resulting system, StreetNav, processes a camera's video feed using computer vision and gives BLV pedestrians real-time navigation assistance. Our evaluations show that StreetNav guides users more precisely than GPS, but its technical performance is sensitive to environmental occlusions and distance from the camera. We discuss future implications for deploying such systems at scale.

Despite the rich literature on scheduling algorithms for wireless networks, algorithms that can provide deadline guarantees on packet delivery for general traffic and interference models are very limited. In this paper, we study the problem of scheduling real-time traffic under a conflict-graph interference model with unreliable links due to channel fading. Packets that are not successfully delivered within their deadlines are of no value. We consider traffic (packet arrival and deadline) and fading (link reliability) processes that evolve as an unknown finite-state Markov chain. The performance metric is efficiency ratio which is the fraction of packets of each link which are delivered within their deadlines compared to that under the optimal (unknown) policy. We first show a conversion result that shows classical non-real-time scheduling algorithms can be ported to the real-time setting and yield a constant efficiency ratio, in particular, Max-Weight Scheduling (MWS) yields an efficiency ratio of 1/2. We then propose randomized algorithms that achieve efficiency ratios strictly higher than 1/2, by carefully randomizing over the maximal schedules. We further propose low-complexity and myopic distributed randomized algorithms, and characterize their efficiency ratio. Simulation results are presented that verify that randomized algorithms outperform classical algorithms such as MWS and GMS.

Applications in data-parallel computing typically consist of multiple stages. In each stage, a set of intermediate parallel data flows (Coflow) is produced and transferred between servers to enable starting of next stage. While there has been much research on scheduling isolated coflows, the dependency between coflows in multi-stage jobs has been largely ignored. In this paper, we consider scheduling coflows of multi-stage jobs represented by general DAGs (Directed Acyclic Graphs) in a shared data center network, so as to minimize the total weighted completion time of jobs. This problem is significantly more challenging than the traditional coflow scheduling, as scheduling even a single multi-stage job to minimize its completion time is shown to be NP-hard. In this paper, we propose a polynomial-time algorithm with approximation ratio of $O(\mu\log(m)/\log(\log(m)))$, where $\mu$ is the maximum number of coflows in a job and $m$ is the number of servers. For the special case that the jobs' underlying dependency graphs are rooted trees, we modify the algorithm and improve its approximation ratio. To verify the performance of our algorithms, we present simulation results using real traffic traces that show up to $53 \%$ improvement over the prior approach. We conclude the paper by providing a result concerning an optimality gap for scheduling coflows with general DAGs.

We consider a distributed server system consisting of a large number of servers, each with limited capacity on multiple resources (CPU, memory, disk, etc.). Jobs with different rewards arrive over time and require certain amounts of resources for the duration of their service. When a job arrives, the system must decide whether to admit it or reject it, and if admitted, in which server to schedule the job. The objective is to maximize the expected total reward received by the system. This problem is motivated by control of cloud computing clusters, in which, jobs are requests for Virtual Machines or Containers that reserve resources for various services, and rewards represent service priority of requests or price paid per time unit of service by clients. We study this problem in an asymptotic regime where the number of servers and jobs' arrival rates scale by a factor $L$, as $L$ becomes large. We propose a resource reservation policy that asymptotically achieves at least $1/2$, and under certain monotone property on jobs' rewards and resources, at least $1-1/e$ of the optimal expected reward. The policy automatically scales the number of VM slots for each job type as the demand changes, and decides in which servers the slots should be created in advance, without the knowledge of traffic rates. It effectively tracks a low-complexity greedy packing of existing jobs in the system while maintaining only a small number, $g(L)=\omega(\log L)$, of reserved VM slots for high priority jobs that pack well.

Motivated by modern parallel computing applications, we consider the problem of scheduling parallel-task jobs with heterogeneous resource requirements in a cluster of machines. Each job consists of a set of tasks that can be processed in parallel, however, the job is considered completed only when all its tasks finish their processing, which we refer to as "synchronization" constraint. Further, assignment of tasks to machines is subject to "placement" constraints, i.e., each task can be processed only on a subset of machines, and processing times can also be machine dependent. Once a task is scheduled on a machine, it requires a certain amount of resource from that machine for the duration of its processing. A machine can process ("pack") multiple tasks at the same time, however the cumulative resource requirement of the tasks should not exceed the machine's capacity. Our objective is to minimize the weighted average of the jobs' completion times. The problem, subject to synchronization, packing and placement constraints, is NP-hard, and prior theoretical results only concern much simpler models. For the case that migration of tasks among the placement-feasible machines is allowed, we propose a preemptive algorithm with an approximation ratio of $(6+\epsilon)$. In the special case that only one machine can process each task, we design an algorithm with improved approximation ratio of $4$. Finally, in the case that migrations (and preemptions) are not allowed, we design an algorithm with an approximation ratio of $24$. Our algorithms use a combination of linear program relaxation and greedy packing techniques. We present extensive simulation results, using a real traffic trace, that demonstrate that our algorithms yield significant gains over the prior approaches.

In this paper, we consider the problem of scheduling real-time traffic in wireless networks under a conflict-graph interference model and single-hop traffic. The objective is to guarantee that at least a certain fraction of packets of each link are delivered within their deadlines, which is referred to as delivery ratio. This problem has been studied before under restrictive frame-based traffic models, or greedy maximal scheduling schemes like LDF (Largest-Deficit First) that provide poor delivery ratio for general traffic patterns. In this paper, we pursue a different approach through randomization over the choice of maximal links that can transmit at each time. We design randomized policies in collocated networks, multi-partite networks, and general networks, that can achieve delivery ratios much higher than what is achievable by LDF. Further, our results apply to traffic (arrival and deadline) processes that evolve as positive recurrent Markov Chains. Hence, this work is an improvement with respect to both efficiency and traffic assumptions compared to the past work. We further present extensive simulation results over various traffic patterns and interference graphs to illustrate the gains of our randomized policies over LDF variants.

We consider a natural scheduling problem which arises in many distributed computing frameworks. Jobs with diverse resource requirements (e.g. memory requirements) arrive over time and must be served by a cluster of servers, each with a finite resource capacity. To improve throughput and delay, the scheduler can pack as many jobs as possible in the servers subject to their capacity constraints. Motivated by the ever-increasing complexity of workloads in shared clusters, we consider a setting where the jobs' resource requirements belong to a very large number of diverse types or, in the extreme, even infinitely many types, e.g. when resource requirements are drawn from an unknown distribution over a continuous support. The application of classical scheduling approaches that crucially rely on a predefined finite set of types is discouraging in this high (or infinite) dimensional setting. We first characterize a fundamental limit on the maximum throughput in such setting, and then develop oblivious scheduling algorithms that have low complexity and can achieve at least 1/2 and 2/3 of the maximum throughput, without the knowledge of traffic or resource requirement distribution. Extensive simulation results, using both synthetic and real traffic traces, are presented to verify the performance of our algorithms.

We study the problem of scheduling VMs (Virtual Machines) in a distributed server platform, motivated by cloud computing applications. The VMs arrive dynamically over time to the system, and require a certain amount of resources (e.g. memory, CPU, etc) for the duration of their service. To avoid costly preemptions, we consider non-preemptive scheduling: Each VM has to be assigned to a server which has enough residual capacity to accommodate it, and once a VM is assigned to a server, its service \textit{cannot} be disrupted (preempted). Prior approaches to this problem either have high complexity, require synchronization among the servers, or yield queue sizes/delays which are excessively large. We propose a non-preemptive scheduling algorithm that resolves these issues. In general, given an approximation algorithm to Knapsack with approximation ratio $r$, our scheduling algorithm can provide $r\beta$ fraction of the throughput region for $\beta < r$. In the special case of a greedy approximation algorithm to Knapsack, we further show that this condition can be relaxed to $\beta<1$. The parameters $\beta$ and $r$ can be tuned to provide a tradeoff between achievable throughput, delay, and computational complexity of the scheduling algorithm. Finally extensive simulation results using both synthetic and real traffic traces are presented to verify the performance of our algorithm., Comment: 29 pages

Full-duplex (FD) wireless is an attractive communication paradigm with high potential for improving network capacity and reducing delay in wireless networks. Despite significant progress on the physical layer development, the challenges associated with developing medium access control (MAC) protocols for heterogeneous networks composed of both legacy half-duplex (HD) and emerging FD devices have not been fully addressed. Therefore, we focus on the design and performance evaluation of scheduling algorithms for infrastructure-based heterogeneous HD-FD networks (composed of HD and FD users). We first show that centralized Greedy Maximal Scheduling (GMS) is throughput-optimal in heterogeneous HD-FD networks. We propose the Hybrid-GMS (H-GMS) algorithm, a distributed implementation of GMS that combines GMS and a queue-based random-access mechanism. We prove that H-GMS is throughput-optimal. Moreover, we analyze the delay performance of H-GMS by deriving lower bounds on the average queue length. We further demonstrate the benefits of upgrading HD nodes to FD nodes in terms of throughput gains for individual nodes and the whole network. Finally, we evaluate the performance of H-GMS and its variants in terms of throughput, delay, and fairness between FD and HD users via extensive simulations. We show that in heterogeneous HD-FD networks, H-GMS achieves 16-30x better delay performance and improves fairness between HD and FD users by up to 50% compared with the fully decentralized Q-CSMA algorithm., Comment: A partial and preliminary version of this paper appeared in IEEE INFOCOM'18

We study the following one-way asymmetric transmission problem, also a variant of model-based compressed sensing: a resource-limited encoder has to report a small set $S$ from a universe of $N$ items to a more powerful decoder (server). The distinguishing feature is asymmetric information: the subset $S$ is comprised of i.i.d. samples from a prior distribution $\mu$, and $\mu$ is only known to the decoder. The goal for the encoder is to encode $S$ obliviously, while achieving the information-theoretic bound of $|S| \cdot H(\mu)$, i.e., the Shannon entropy bound. We first show that any such compression scheme must be {\em randomized}, if it gains non-trivially from the prior $\mu$. This stands in contrast to the symmetric case (when both the encoder and decoder know $\mu$), where the Huffman code provides a near-optimal deterministic solution. On the other hand, a rather simple argument shows that, when $|S|=k$, a random linear code achieves near-optimal communication rate of about $k\cdot H(\mu)$ bits. Alas, the resulting scheme has prohibitive decoding time: about ${N\choose k} \approx (N/k)^k$. Our main result is a computationally efficient and linear coding scheme, which achieves an $O(\lg\lg N)$-competitive communication ratio compared to the optimal benchmark, and runs in $\text{poly}(N,k)$ time. Our "multi-level" coding scheme uses a combination of hashing and syndrome-decoding of Reed-Solomon codes, and relies on viewing the (unknown) prior $\mu$ as a rather small convex combination of uniform ("flat") distributions.

In data-parallel computing frameworks, intermediate parallel data is often produced at various stages which needs to be transferred among servers in the datacenter network (e.g. the shuffle phase in MapReduce). A stage often cannot start or be completed unless all the required data pieces from the preceding stage are received. \emph{Coflow} is a recently proposed networking abstraction to capture such communication patterns. We consider the problem of efficiently scheduling coflows with release dates in a shared datacenter network so as to minimize the total weighted completion time of coflows. Several heuristics have been proposed recently to address this problem, as well as a few polynomial-time approximation algorithms with provable performance guarantees. Our main result in this paper is a polynomial-time deterministic algorithm that improves the prior known results. Specifically, we propose a deterministic algorithm with approximation ratio of $5$, which improves the prior best known ratio of $12$. For the special case when all coflows are released at time zero, our deterministic algorithm obtains approximation ratio of $4$ which improves the prior best known ratio of $8$. The key ingredient of our approach is an improved linear program formulation for sorting the coflows followed by a simple list scheduling policy. Extensive simulation results, using both synthetic and real traffic traces, are presented that verify the performance of our algorithm and show improvement over the prior approaches., Comment: 12 pages, 11 figures

Content Delivery Networks (CDNs) deliver a majority of the user-requested content on the Internet, including web pages, videos, and software downloads. A CDN server caches and serves the content requested by users. Designing caching algorithms that automatically adapt to the heterogeneity, burstiness, and non-stationary nature of real-world content requests is a major challenge and is the focus of our work. While there is much work on caching algorithms for stationary request traffic, the work on non-stationary request traffic is very limited. Consequently, most prior models are inaccurate for production CDN traffic that is non-stationary. We propose two TTL-based caching algorithms and provide provable guarantees for content request traffic that is bursty and non-stationary. The first algorithm called d-TTL dynamically adapts a TTL parameter using a stochastic approximation approach. Given a feasible target hit rate, we show that the hit rate of d-TTL converges to its target value for a general class of bursty traffic that allows Markov dependence over time and non-stationary arrivals. The second algorithm called f-TTL uses two caches, each with its own TTL. The first-level cache adaptively filters out non-stationary traffic, while the second-level cache stores frequently-accessed stationary traffic. Given feasible targets for both the hit rate and the expected cache size, f-TTL asymptotically achieves both targets. We implement d-TTL and f-TTL and evaluate both algorithms using an extensive nine-day trace consisting of 500 million requests from a production CDN server. We show that both d-TTL and f-TTL converge to their hit rate targets with an error of about 1.3%. But, f-TTL requires a significantly smaller cache size than d-TTL to achieve the same hit rate, since it effectively filters out the non-stationary traffic for rarely-accessed objects.

Wireless object tracking applications are gaining popularity and will soon utilize emerging ultra-low-power device-to-device communication. However, severe energy constraints require much more careful accounting of energy usage than what prior art provides. In particular, the available energy, the differing power consumption levels for listening, receiving, and transmitting, as well as the limited control bandwidth must all be considered. Therefore, we formulate the problem of maximizing the throughput among a set of heterogeneous broadcasting nodes with differing power consumption levels, each subject to a strict ultra-low-power budget. We obtain the oracle throughput (i.e., maximum throughput achieved by an oracle) and use Lagrangian methods to design EconCast - a simple asynchronous distributed protocol in which nodes transition between sleep, listen, and transmit states, and dynamically change the transition rates. EconCast can operate in groupput or anyput modes to respectively maximize two alternative throughput measures. We show that EconCast approaches the oracle throughput. The performance is also evaluated numerically and via extensive simulations and it is shown that EconCast outperforms prior art by 6x - 17x under realistic assumptions. Moreover, we evaluate EconCast's latency performance and consider design tradeoffs when operating in groupput and anyput modes. Finally, we implement EconCast using the TI eZ430-RF2500-SEH energy harvesting nodes and experimentally show that in realistic environments it obtains 57% - 77% of the achievable throughput., Comment: Partial and preliminary version appeared in ACM CoNEXT'16

Motivated by emerging big streaming data processing paradigms (e.g., Twitter Storm, Streaming MapReduce), we investigate the problem of scheduling graphs over a large cluster of servers. Each graph is a job, where nodes represent compute tasks and edges indicate data-flows between these compute tasks. Jobs (graphs) arrive randomly over time, and upon completion, leave the system. When a job arrives, the scheduler needs to partition the graph and distribute it over the servers to satisfy load balancing and cost considerations. Specifically, neighboring compute tasks in the graph that are mapped to different servers incur load on the network; thus a mapping of the jobs among the servers incurs a cost that is proportional to the number of "broken edges". We propose a low complexity randomized scheduling algorithm that, without service preemptions, stabilizes the system with graph arrivals/departures; more importantly, it allows a smooth trade-off between minimizing average partitioning cost and average queue lengths. Interestingly, to avoid service preemptions, our approach does not rely on a Gibbs sampler; instead, we show that the corresponding limiting invariant measure has an interpretation stemming from a loss system., Comment: 14 pages

In this paper we look at content placement in the high-dimensional regime: there are n servers, and O(n) distinct types of content. Each server can store and serve O(1) types at any given time. Demands for these content types arrive, and have to be served in an online fashion; over time, there are a total of O(n) of these demands. We consider the algorithmic task of content placement: determining which types of content should be on which server at any given time, in the setting where the demand statistics (i.e. the relative popularity of each type of content) are not known a-priori, but have to be inferred from the very demands we are trying to satisfy. This is the high- dimensional regime because this scaling (everything being O(n)) prevents consistent estimation of demand statistics; it models many modern settings where large numbers of users, servers and videos/webpages interact in this way. We characterize the performance of any scheme that separates learning and placement (i.e. which use a portion of the demands to gain some estimate of the demand statistics, and then uses the same for the remaining demands), showing it is order-wise strictly suboptimal. We then study a simple adaptive scheme - which myopically attempts to store the most recently requested content on idle servers - and show it outperforms schemes that separate learning and placement. Our results also generalize to the setting where the demand statistics change with time. Overall, our results demonstrate that separating the estimation of demand, and the subsequent use of the same, is strictly suboptimal.