An official website of the United States government
Reducing our reliance on carbon-intensive energy sources is vital for reducing the carbon footprint of the electric grid. Although the grid is seeing increasing deployments of clean, renewable sources of energy, a significant portion of the grid demand is still met using traditional carbon-intensive energy sources. In this paper, we study the problem of using energy storage deployed in the grid to reduce the grid's carbon emissions. While energy storage has previously been used for grid optimizations such as peak shaving and smoothing intermittent sources, our insight is to use distributed storage to enable utilities to reduce their reliance on their less efficient and most carbon-intensive power plants and thereby reduce their overall emission footprint. We formulate the problem of emission-aware scheduling of distributed energy storage as an optimization problem, and use a robust optimization approach that is well-suited for handling the uncertainty in load predictions, especially in the presence of intermittent renewables such as solar and wind. We evaluate our approach using a state of the art neural network load forecasting technique and real load traces from a distribution grid with 1,341 homes. Our results show a reduction of >0.5 million kg in annual carbon emissions --- equivalent to a drop of 23.3% in our electric grid emissions.
more »
« less
Learning from Optimal: Energy Procurement Strategies for Data Centers
Environmental concerns and rising grid prices have motivated data center owners to invest in on-site renewable energy sources. How- ever, these sources present challenges as they are unreliable and intermittent. In an effort to mitigate these issues, data centers are incorporating energy storage systems. This introduces the oppor- tunity for electricity bill reduction, as energy storage can be used for power market arbitrage. We present two supervised learning-based algorithms, LearnBuy, that learns the amount to purchase, and LearnStore, that learns the amount to store, to solve this energy procurement problem. These algorithms utilize the idea of "learning from optimal" by using the values generated by the offline optimization as a label for training. We test our algorithms on a general case, considering buying and selling back to the grid, and a special case, considering only buying from the grid. In the general case, LearnStore achieves a 10-16% reduction compared to baseline heuristics, whereas in the special case, LearnBuy achieves a 7% reduction compared to prior art.
more »
« less
- PAR ID:
- 10173201
- Date Published:
- Journal Name:
- Proceedings of the Tenth ACM International Conference on Future Energy Systems (e-Energy ’19)
- Page Range / eLocation ID:
- 326 to 330
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Data shuffling between distributed workers is one of the critical steps in implementing large-scale learning algorithms. The focus of this work is to understand the fundamental trade-off between the amount of storage and the communication overhead for distributed data shuffling. We first present an information theoretic formulation for the data shuffling problem, accounting for the underlying problem parameters (i.e., number of workers, K, number of data points, N, and the available storage, S per node). Then, we derive an information theoretic lower bound on the communication overhead for data shuffling as a function of these parameters. Next, we present a novel coded communication scheme and show that the resulting communication overhead of the proposed scheme is within a multiplicative factor of at most 2 from the lower bound. Furthermore, we introduce an improved aligned coded shuffling scheme, which achieves the optimal storage vs communication trade-off for K <; 5, and further reduces the maximum multiplicative gap down to 7/6, for K ≥ 5.more » « less
-
null (Ed.)Machine learning applied to architecture design presents a promising opportunity with broad applications. Recent deep reinforcement learning (DRL) techniques, in particular, enable efficient exploration in vast design spaces where conventional design strategies may be inadequate. This paper proposes a novel deep reinforcement framework, taking routerless networks-on-chip (NoC) as an evaluation case study. The new framework successfully resolves problems with prior design approaches, which are either unreliable due to random searches or inflexible due to severe design space restrictions. The framework learns (near-)optimal loop placement for routerless NoCs with various design constraints. A deep neural network is developed using parallel threads that efficiently explore the immense routerless NoC design space with a Monte Carlo search tree. Experimental results show that, compared with conventional mesh, the proposed deep reinforcement learning (DRL) routerless design achieves a 3.25x increase in throughput, 1.6x reduction in packet latency, and 5x reduction in power. Compared with the state-of-the-art routerless NoC, DRL achieves a 1.47x increase in throughput, 1.18x reduction in packet latency, 1.14x reduction in average hop count, and 6.3% lower power consumption.more » « less
-
We aim to preserve a large amount of data generated insidebase station-less sensor networks(BSNs) while considering that sensor nodes are selfish. BSNs refer to emerging sensing applications deployed in challenging and inhospitable environments (e.g., underwater exploration); as such, there do not exist data-collecting base stations in the BSN to collect the data. Consequently, the generated data has to be stored inside the BSN before uploading opportunities become available. Our goal is to preserve the data inside the BSN with minimum energy cost by incentivizing the storage- and energy-constrained sensor nodes to participate in the data preservation process. We refer to the problem as DPP:datapreservationproblem in the BSN. Previous research assumes that all the sensor nodes are cooperative and that sensors have infinite battery power and design a minimum-cost flow-based data preservation solution. However, in a distributed setting and under different control, the resource-constrained sensor nodes could behave selfishly only to conserve their resources and maximize their benefit. In this article, we first solve DPP by designing an integer linear programming (ILP)-based optimal solution without considering selfishness. We then establish a game-theoretical framework that achieves provably truthful and optimal data preservation in BSNs. For a special case of DPP wherein nodes are not energy-constrained, referred to as DPP-W, we design a data preservation game DPG-1 that integrates algorithmic mechanism design (AMD) and a more efficient minimum cost flow-based data preservation solution. We show that DPG-1 yields dominant strategies for sensor nodes and delivers truthful and optimal data preservation. For the general case of DPP (wherein nodes are energy-constrained), however, DPG-1 fails to achieve truthful and optimal data preservation. Utilizing packet-level flow observation of sensor node behaviors computed by minimum cost flow and ILP, we uncover the cause of the failure of the DPG-1. It is due to the packet dropping by the selfish nodes that manipulate the AMD technique. We then design a data preservation game DPG-2 for DPP that traces and punishes manipulative nodes in the BSN. We show that DPG-2 delivers dominant strategies for truth-telling nodes and achieves provably optimal data preservation with cheat-proof guarantees. Via extensive simulations under different network parameters and dynamics, we show that our games achieve system-wide data preservation solutions with optimal energy cost while enforcing truth-telling of sensor nodes about their private cost types. One salient feature of our work is its integrated game theory and network flows approach. With the observation of flow level sensor node behaviors provided by the network flows, our proposed games can synthesize “microscopic” (i.e., selfish and local) behaviors of sensor nodes and yield targeted “macroscopic” (i.e., optimal and global) network performance of data preservation in the BSN.more » « less
-
The increasing adoption of electric vehicles (EVs) by the general population creates an opportunity to deploy the energy storage capability of EVs for performing peak energy shaving in their households and ultimately in their neighborhood grid during surging demand. However, the impact of the adoption rate in a neighborhood might be counterbalanced by the energy demand of EVs during off-peak hours. Therefore, achieving optimal peak energy shaving is a product of a sensitive balancing process that depends on the EV adoption rate. In this paper, we propose EOS, an agent-based simulation model, to represent independent household energy usage and estimate the real-time neighborhood energy consumption and peak shaving energy amount of a neighborhood. This study uses Residential Energy Consumption Survey (RECS) and the American Time Use Survey (ATUS) data to model realistic real-time household energy use. We evaluate the impact of the EV adoption rates of a neighborhood on performing energy peak shaving during sudden energy surges. Our findings reveal these trade-offs and, specifically, a reduction of up to 30% of the peak neighborhood energy usage for the optimal neighborhood EV adoption rate in a 1089 household neighborhood.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3307772.3328308
