Grid-Interactive Efficient Buildings Technical Report Series: Whole-Building Controls, Sensors, Modeling, and Analytics

Roth, Aaron; Reyna, Janet

doi:10.2172/1580329

Cited by 34 publications

(19 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the 77 studies we surveyed, only 11% of RL controllers were implemented and tested in an actual building. Significant barriers limiting the applications of RL controller for real building controls include (1) the training process is timeconsuming and data-demanding, (2) the security of controls needs to be addressed, i.e., making sure the RL controller would not mess up the building controls, especially during the training stage, (3) it is yet unknown how to implement the transfer learning so that controllers trained by a small number of buildings could be generalized and used for other buildings, and (4) a data-rich, open-sourced, and interoperable virtual testbed is needed to facilitate cross-study validations and benchmarking of performance of RL controllers.…”

Section: Resultsmentioning

confidence: 99%

“…Other popular subjects include the charging/discharging of batteries and scheduling of home appliances. In addition to the number of articles published, another important index for estimating the quality and influence of those publications is the number of citations, 3 which was listed in Figure 3b. Articles in this field, in general, are cited between 20-70 times per paper.…”

Section: Literature Searchmentioning

confidence: 99%

“…An article might be counted twice if it controls multiple building components 3. The number of citations were retrieved from Google Scholar until December 23,2019.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Reinforcement learning for building controls: The opportunities and challenges

2020

View full text Add to dashboard Cite

Building controls are becoming more important and complicated due to the dynamic and stochastic energy demand, on-site intermittent energy supply, as well as energy storage, making it difficult for them to be optimized by conventional control techniques. Reinforcement Learning (RL), as an emerging control technique, has attracted growing research interest and demonstrated its potential to enhance building performance while addressing some limitations of other advanced control techniques, such as model predictive control. This study conducted a comprehensive review of existing studies that applied RL for building controls. It provided a detailed breakdown of the existing RL studies that use a specific variation of each major component of the Reinforcement Learning: algorithm, state, action, reward, and environment. We found RL for building controls is still in the research stage with limited applications (11%) in real buildings. Three significant barriers prevent the adoption of RL controllers in actual building controls: (1) the training process is time consuming and data demanding, (2) the control security and robustness need to be enhanced, and (3) the generalization capabilities of RL controllers need to be improved using approaches such as transfer learning. Future research may focus on developing RL controllers that could be used in real buildings, addressing current RL challenges, such as accelerating training and enhancing control robustness, as well as developing an opensource testbed and dataset for performance benchmarking of RL controllers.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Literature Searchmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement learning for building controls: The opportunities and challenges

2020

View full text Add to dashboard Cite

show abstract

“…BEM can also be used to design buildings that are inherently more flexible in their energy use and better able to respond to dynamic grid conditions. In 2019, BTO published a report that describes the role of BEM in GEB, and identifies gaps and opportunities (Roth and Reyna 2019). The most significant gaps identified all dealt with lacking integration with different domains of models and workflows: (1) control design and implementation workflows, (2) advanced district thermal generation, distribution and storage, and (3) electrical distribution models.…”

Section: Lack Of Capabilities Supporting Use In Building Operation Anmentioning

confidence: 99%

Innovations in Building Energy Modeling: Research and Development Opportunities for Emerging Technologies

Roth

Reyna

2020

Self Cite

View full text Add to dashboard Cite

Building energy modeling (BEM) is a multipurpose tool for building energy efficiency (EE). The U.S. Department of Energy Building Technologies Office (BTO) seeks to expand the use and effectiveness of BEM in the design and operation of commercial and residential buildings with the goal of achieving lasting reductions in total and peak energy use. This report identifies gaps and outlines recommended initiatives to achieve this goal, based on a combination of technical analysis and stakeholder input. In addition to BTO, this report can benefit BEM professionals (architects, mechanical engineers, energy consultants, building auditors, equipment manufacturers, and BEM software vendors) and BEM clients (building owners and operators, EE program administrators, EE service providers, policymakers, and policy and code jurisdictions such as states and cities). This report was developed in two phases. In the first, BTO worked with a team from Navigant Consulting (now Guidehouse) to characterize objectives, opportunities, and current activities; identify gaps and barriers; and define initiatives. To collect input, Navigant conducted telephone interviews and workshops with industry experts. The initial phase produced a draft report, which was released for public review in 2016 and yielded over 400 comments. Based on these comments, BTO compiled a second draft report that addressed many of those comments while acknowledging changes that had occurred both at BTO and in the industry. Unlike the first draft report, the second focused much more heavily on BTO's own role, portfolio, and activities. BTO is a direct player in the BEM field-it funds the development of several significant software packages that are embedded in commercial products-and transparency about its goals and future plans is requisite. BTO recognizes that a great number of other public and private organizations contribute to the BEM enterprise. With the second draft report, BTO did not attempt to produce a blueprint for the industry as a whole, but rather a working document BTO can use to iteratively solicit stakeholder input and synthesize it into a program. BTO released the second draft report for public review in 2019. The second round of review generated 83 pages of feedback and comments-almost exactly the length of the draft report itself-a significant portion of which was collected and synthesized by IBPSA-USA Advocacy Committee. This final report incorporates this feedback. This report does not address the use of BEM in support of building-based grid services, a recent BTO initiative called Grid-interactive Efficient Buildings (GEB). In 2019, BTO published a report that specifically addresses the role of BEM-and other "integration" technologies-in GEB (Roth and Reyna 2019).

show abstract

“…The consumption on demand strategy, however, requires a significant amount of load flexibility in the demand side. Demand response (DR) can reveal and utilize this demand flexibility by enabling the participation of a large number of grid-interactive efficient buildings (GEB) [2]. DR programs aim to modify the electricity consumption of end users, by means of incentives, in favor of the operational needs of the power grid [3].…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Model-Free Transactional Control of Building Loads to Support Grid Services

et al. 2020

View full text Add to dashboard Cite

A transition from generation on demand to consumption on demand is one of the solutions to overcome the many limitations associated with the higher penetration of renewable energy sources. Such a transition, however, requires a considerable amount of load flexibility in the demand side. Demand response (DR) programs can reveal and utilize this demand flexibility by enabling the participation of a large number of grid-interactive efficient buildings (GEB). Existing approaches on DR require significant modelling or training efforts, are computationally expensive, and do not guarantee the satisfaction of end users. To address these limitations, this paper proposes a scalable hierarchical model-free transactional control approach that incorporates elements of virtual battery, game theory, and model-free control (MFC) mechanisms. The proposed approach separates the control mechanism into upper and lower levels. The MFC modulates the flexible GEB in the lower level with guaranteed thermal comfort of end users, in response to the optimal pricing and power signals determined in the upper level using a Stackelberg game integrated with aggregate virtual battery constraints. Additionally, the usage of MFC necessitates less burdensome computational and communication requirements, thus, it is easily deployable even on small embedded devices. The effectiveness of this approach is demonstrated through a large-scale case study with 10,000 heterogenous GEB. The results show that the proposed approach can achieve peak load reduction and profit maximization for the distribution system operator, as well as cost reduction for end users while maintaining their comfort. INDEX TERMS Demand response, model-free control, Stackelberg game, thermostatically controlled loads, transactive control, virtual battery K. Amasyali et al.: Hierarchical Model-Free Transactional Control of Building Loads to Support Grid Services

show abstract

Grid-Interactive Efficient Buildings Technical Report Series: Whole-Building Controls, Sensors, Modeling, and Analytics

Cited by 34 publications

References 52 publications

Reinforcement learning for building controls: The opportunities and challenges

Reinforcement learning for building controls: The opportunities and challenges

Innovations in Building Energy Modeling: Research and Development Opportunities for Emerging Technologies

Hierarchical Model-Free Transactional Control of Building Loads to Support Grid Services

Contact Info

Product

Resources

About