This paper introduces a method for adapting pretrained battery prediction models in Electric Vehicles using on-device learning, achieving significant improvements in forecasting performance.

This paper introduces packetized energy management (PEM) as a framework for transforming 6G infrastructure into energy-aware, grid-interactive assets.

This paper proposes LMS-AR, a memory bandwidth regulation mechanism for multi-core systems using a Linux kernel module with adaptive filtering for prediction and regulation.

Proposed EnerInfer framework manages energy efficiency, throughput, and thermal comfort for on-device LLM inference, improving energy efficiency up to 65% without QoE violation.

This paper introduces Bit2Watt, a vulnerability in which an adversary manipulates GPU workloads to destabilize local power infrastructure and disrupt computing services, operating entirely within the…

This paper proposes IOHMM-BO, a method using a high-order input-output hidden Markov model with Bayesian optimization for predictive dynamic power management in 5G NR user equipment, achieving 43% ene…

This paper analyzes the synchronization of power usage in large-scale AI training facilities and identifies the coupling channel in load-dependent throttling.

This paper argues that idle cores on contemporary multicore processors can return compute capacity and proposes a budget-centric view of service core systems.

A new stochastic load balancing model is introduced that allows for a tradeoff between non-adaptive policies and performance, with results showing a 2-reservation approximation to the omniscient optim…

This paper introduces BigPower, a hierarchical source-level surrogate model for fine-grained module-level power estimation during CPU design using large language models and architectural hierarchy.

This paper studies the autarky problem of scheduling energy-consuming jobs with time windows using a battery and an energy forecast, and shows NP-hardness, polynomial-time solvability, and fixed-param…

This paper introduces energy-aware learning, an approach that reduces actuator energy in closed-loop deep brain stimulation systems by incorporating actuator energy into the reinforcement learning rew…

The paper proposes EnThM, a lightweight, hierarchical verification scheme that uses statistical and rule-based checks on aggregated metering data to mitigate real-time power theft in smart grids.

This paper presents LightFARM, a predictive lighting control framework for energy-efficient indoor farming that combines finite-horizon predictive control with compact models of photosynthesis, therma…

This paper proposes an Explainable Deep Reinforcement Learning (XRL) framework to optimize energy management in complex buildings, demonstrating that on-policy algorithms provide superior cost reducti…

This paper proposes an arbiter for resolving conflicts between xApps in Open RAN by monitoring the fidelity of a network digital twin and switching between actions based on observed utility.