An official website of the United States government
The fast development of electric vehicles (EV) and EV chargers introduces many factors that affect the grid. EV charging and charge scheduling also bring challenges to EV drivers and grid operators. In this work, we propose a human-centric, data-driven, city-scale, multivariate optimization approach for the EV-interfaced grid. This approach takes into account user historical driving and charging habits, user preferences, EV characteristics, city-scale mobility, EV charger availability and price, and grid capacity. The user preferences include the trade-off between cost and time to charge, as well as incentives to participate in different energy-saving programs. We leverage deep reinforcement learning (DRL) to make recommendations to EV drivers and optimize their welfare while enhancing grid performance.
more »
« less
A Scheduler for Smart Homes with Probabilistic User Preferences
Scheduling appliances is a challenging and interesting problem aimed at reducing energy consumption at a residential level. Previous work on appliance scheduling for smart homes assumes that user preferences have no uncertainty. In this paper, we study two approaches to address this problem when user preferences are uncertain. More specifically, we assume that user preferences in turning on or off a device are represented by Normal distributions. The first approach uses sample average approximation, a mathematical model, in computing a schedule. The second one relies on the fact that a scheduling problem could be viewed as a constraint satisfaction problem and uses depth-first search to identify a solution. We also conduct an experimental evaluation of the two approaches to investigate the scalability of each approach in different problem variants. We conclude by discussing computational challenges of our approaches and some possible directions for future work.
more »
« less
- Award ID(s):
- 1757207
- PAR ID:
- 10123209
- Date Published:
- Journal Name:
- International Conference on Principles and Practice of Multi-Agent Systems
- Page Range / eLocation ID:
- 138-152
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In autonomous robot navigation, terrain cost assignment is typically performed using a semantics-based paradigm in which terrain is first labeled using a pre-trained semantic classifier and costs are then assigned according to a user-defined mapping between label and cost. While this approach is rapidly adaptable to changing user preferences, only preferences over the types of terrain that are already known by the semantic classifier can be expressed. In this paper, we hypothesize that a machine-learning-based alternative to the semantics-based paradigm above will allow for rapid cost assignment adaptation to preferences expressed over new terrains at deployment time without the need for additional training. To investigate this hypothesis, we introduce and study PACER, a novel approach to costmap generation that accepts as input a single birds-eye view (BEV) image of the surrounding area along with a user-specified preference context and generates a corresponding BEV costmap that aligns with the preference context. Using both real and synthetic data along with a combination of proposed training tasks, we find that PACER is able to adapt quickly to new user preferences while also exhibiting better generalization to novel terrains compared to both semantics-based and representation-learning approaches.more » « less
-
Application performance variability caused by network contention is a major issue on dragonfly based systems. This work-in-progress study makes two contributions. First, we analyze real workload logs and conduct application experiments on the production system Theta at Argonne to evaluate application performance variability. We find a strong correlation between system utilization and performance variability where a high system utilization (e.g., above 95%) can cause up to 21% degradation in application performance. Next, driven by this key finding, we investigate a scheduling policy to mitigate workload interference by leveraging the fact that production systems often exhibit diurnal utilization behavior and not all users are in a hurry for job completion. Preliminary results show that this scheduling design is capable of improving system productivity (measured by scheduling makespan) as well as improving user-level scheduling metrics such as user wait time and job slowdown.more » « less
-
We study a scheduling problem for a base-station transmitting status information to multiple user-equipments (UE) with the goal of minimizing the total expected Age-of-Information (AoI). Such a problem can be formulated as a Restless MultiArmed Bandit (RMAB) problem and solved asymptoticallyoptimally by a low-complexity Whittle index policy, if each UE’s sub-problem is Whittle indexable. However, proving Whittle indexability can be highly non-trivial, especially when the value function cannot be derived in closed-form. In particular, this is the case for the AoI minimization problem with stochastic arrivals and unreliable channels, whose Whittle indexability remains an open problem. To overcome this difficulty, we develop a sufficient condition for Whittle indexability based on the notion of active time (AT). Even though the AT condition shares considerable similarity to the Partial Conservation Law (PCL) condition, it is much easier to understand and verify. We then apply our AT condition to the stochastic-arrival unreliablechannel AoI minimization problem and, for the first time in the literature, prove its Whittle indexability. Our proof uses a novel coupling approach to verify the AT condition, which may also be of independent interest to other large-scale RMAB problems.more » « less
-
Opinion prediction is an emerging research area with diverse real-world applications, such as market research and situational awareness. We identify two lines of approaches to the problem of opinion prediction. One uses topic-based sentiment analysis with time-series modeling, while the other uses static embedding of text. The latter approaches seek user-specific solutions by generating user fingerprints. Such approaches are useful in predicting user's reactions to unseen content. In this work, we propose a novel dynamic fingerprinting method that leverages contextual embedding of user's comments conditioned on relevant user's reading history. We integrate BERT variants with a recurrent neural network to generate predictions. The results show up to 13\% improvement in micro F1-score compared to previous approaches. Experimental results show novel insights that were previously unknown such as better predictions for an increase in dynamic history length, the impact of the nature of the article on performance, thereby laying the foundation for further research.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-030-33792-6_9
