Byungjin Cho

Ahmad N. L. Nabhaan, Zaki Sukma, Rakandhiya D. Rachmanto et al.

For deep learning inference on edge devices, hardware configurations achieving the same throughput can differ by 2$\times$ in power consumption, yet operators often struggle to find the efficient ones without exhaustive profiling. Existing approaches often rely on inefficient static presets or require expensive offline profiling that must be repeated for each new model or device. To address this problem, we present CORAL, an online optimization method that discovers near-optimal configurations without offline profiling. CORAL leverages distance covariance to statistically capture the non-linear dependencies between hardware settings, e.g., DVFS and concurrency levels, and performance metrics. Unlike prior work, we explicitly formulate the challenge as a throughput-power co-optimization problem to satisfy power budgets and throughput targets simultaneously. We evaluate CORAL on two NVIDIA Jetson devices across three object detection models ranging from lightweight to heavyweight. In single-target scenarios, CORAL achieves 96% $\unicode{x2013}$ 100% of the optimal performance found by exhaustive search. In strict dual-constraint scenarios where baselines fail or exceed power budgets, CORAL consistently finds proper configurations online with minimal exploration.

Byungjin Cho, Yu Xiao

Vehicular fog computing (VFC) pushes the cloud computing capability to the distributed fog nodes at the edge of the Internet, enabling compute-intensive and latency-sensitive computing services for vehicles through task offloading. However, a heterogeneous mobility environment introduces uncertainties in terms of resource supply and demand, which are inevitable bottlenecks for the optimal offloading decision. Also, these uncertainties bring extra challenges to task offloading under the oblivious adversary attack and data privacy risks. In this article, we develop a new adversarial online learning algorithm with bandit feedback based on the adversarial multi-armed bandit theory, to enable scalable and low-complexity offloading decision making. Specifically, we focus on optimizing fog node selection with the aim of minimizing the offloading service costs in terms of delay and energy. The key is to implicitly tune the exploration bonus in the selection process and the assessment rules of the designed algorithm, taking into account volatile resource supply and demand. We theoretically prove that the input-size dependent selection rule allows to choose a suitable fog node without exploring the sub-optimal actions, and also an appropriate score patching rule allows to quickly adapt to evolving circumstances, which reduce variance and bias simultaneously, thereby achieving a better exploitation-exploration balance. Simulation results verify the effectiveness and robustness of the proposed algorithm.

Byungjin Cho, Konstantinos Koufos, Kalle Ruttik et al.

In future wireless networks, a significant number of users will be vehicular. One promising solution to improve the capacity for these vehicular users is to employ moving relays or car base stations. The system forms cell inside the vehicle and then uses rooftop antenna for back-hauling to overcome the vehicular penetration loss. In this paper, we develop a model for aggregate interference distribution generated from moving/parked cars to indoor users in order to study whether indoor femto-cells can coexist on the same spectrum with vehicular communications. Since spectrum authorization for vehicular communications is open at moment, we consider two spectrum sharing scenarios (i) communication from mounted antennas on the roof of the vehicles to the infrastructure network utilizes same spectrum with indoor femto-cells (ii) in-vehicle communication utilizes same spectrum with indoor femto-cells while vehicular to infrastructure (V2I) communication is allocated at different spectrum. Based on our findings we suggest that V2I and indoor femto-cells should be allocated at different spectrum. The reason being that mounted roof-top antennas facing the indoor cells generate unacceptable interference levels. On the other hand, in-vehicle communication and indoor cells can share the spectrum thanks to the vehicle body isolation and the lower transmit power levels that can be used inside the vehicle.