• Energy Research

Edge Function-as-a-Service is an emerging computing model that dynamically schedules function executions across distributed edge (close to users) locations to reduce latency and improve user experience. Accurate time-series prediction models, which forecast the future number of function invocations, are crucial for energy-efficient function scheduling, enabling proactive resource allocation. In this work, we evaluate the impact of different neural time-series predictors based on Gaussian processes, recurrent neural networks, and transformer architectures in forecasting the number of function invocations. Furthermore, we propose the Energy-Aware Resource Management (EA-RM) scheduling algorithm, based on a mixed-integer problem, designed to minimize overall energy consumption by reducing the number of edge nodes used. We analyze how prediction accuracy influences function scheduling with respect to energy consumption, using real-world data that include different functions and resources. Experimental results show that the transformer-based predictor outperforms the other considered predictors, leading to more precise function scheduling. Moreover, resource allocation performed through the EA-RM algorithm reduces the energy consumption by ~12-45% on average w.r.t. competitors, and is proven to be more robust w.r.t. the accuracy of the prediction model used.

Railway is currently envisioned as the most promising transportation system for both people and freight to reduce atmospheric emission and combat climate change. In this context, ensuring the energy efficiency of the railway systems is paramount in order to sustain their future expandability with minimum carbon footprint. Recent advancements in computing and communication technologies are expected to play a significant role to enable novel integrated control and management strategies in which heterogeneous data is exploited to noticeably increase energy efficiency. In this paper we focus on exploiting the convergence of heterogeneous information to improve energy efficiency of railway systems, in particular on the heating system for the railroad switches, one of the major energy intensive components. To this aim, we define new policies to efficiently manage the heating of these switches exploiting also external information such as weather and forecast data. In order to assess the performance of each strategy, a stochastic model representing the structure and operation of the railroad switch heating system and environmental conditions (both weather profiles and specific failure events) has been developed and exercised in a variety of representative scenarios. The obtained results allow to understand both strengths and limitations of each energy management policy, and serves as a useful support to make the choice of the best technique to employ to save on energy consumption, given the system conditions at hand.