Putting more brain-like intelligence into the electric power grid: What we need and how to do it

Werbos, Paul J.

doi:10.1109/ijcnn.2009.5179088

Cited by 21 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…to efficiently deliver sustainable, economic and secure electricity supplies." [3] This ambitious vision requires substantial advances in intelligent decentralized control mechanisms that increase economic efficiency, while keeping the physical properties of the network within tight permissible bounds [17].…”

Section: Introductionmentioning

confidence: 99%

Autonomous Data-Driven Decision-Making in Smart Electricity Markets

Peters

Ketter

Saar‐Tsechansky

et al. 2012

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

For the vision of a Smart Grid to materialize, substantial advances in intelligent decentralized control mechanisms are required. We propose a novel class of autonomous broker agents for retail electricity trading that can operate in a wide range of Smart Electricity Markets, and that are capable of deriving long-term, profit-maximizing policies. Our brokers use Reinforcement Learning with function approximation, they can accommodate arbitrary economic signals from their environments, and they learn efficiently over the large state spaces resulting from these signals. Our design is the first that can accommodate an offline training phase so as to automatically optimize the broker for particular market conditions. We demonstrate the performance of our design in a series of experiments using real-world energy market data, and find that it outperforms previous approaches by a significant margin.

show abstract

Section: Introductionmentioning

confidence: 99%

Autonomous Data-Driven Decision-Making in Smart Electricity Markets

Peters

Ketter

Saar‐Tsechansky

et al. 2012

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

show abstract

“…A good summary of different kinds of energy storage techniques currently used in smart grid development is given in [10], ranging from 34MW Sodium Sulfur (NaS) batteries down to 25kW residential area batteries. In [9], the authors emphasize the importance of a good control algorithm, and state that it is possible to get three times more energy from the current wind farms if there was enough storage and a good control algorithm.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Subtracting the i th term from the (i + 1) st gives us the governing recursive optimal solution of the system shown in Equation (9).…”

Section: Implications Of the Values Of The Lagrangian Multipliersmentioning

confidence: 99%

ECO-DAC Energy Control over Divide and Control

Akyürek

Torre

Rosing

2013

2013 IEEE International Conference on Smart Grid Communications (SmartGridComm)

View full text Add to dashboard Cite

The need for a smarter grid is emerging with the increase of peak demand and the integration of renewable resources. A great solution for peak shifting and renewable energy smoothing is through the usage of energy storage devices. This paper focuses on the energy storage power control problem in small to medium sized power distribution systems with loads, energy storage devices and renewable resources connected to the grid. To the best of our knowledge, solutions in this area either focus on the optimization problem with a convex optimization solver, that have high worst-case complexities or on sub-optimal heuristics. This paper provides a low-complexity solution, ECO-DAC, which is optimal in terms of minimizing a multi-tier cost function. We show on multiple case studies that it is possible to save up to 21% in costs for electricity drawn from the grid, compared to the no-battery case.

show abstract

“…Rather, each individual house might have its own intelligent control system, with values controlled and tuned by the user, such as the amount of power delivered, and for what purpose [42]. It is envisioned that the smart grid will likely have a control system that analyzes its performance using distributed, autonomous controllers that have learned successful strategies to govern the behavior of the grid in the face of an ever-changing environment, such as equipment failures.…”

Section: Visionmentioning

confidence: 99%

Representativeness models of systems: smart grid example

Schneidewind

2011

Innovations Syst Softw Eng

View full text Add to dashboard Cite

Given the great emphasis being placed on energy efficiency in contemporary society, in which the smart grid plays a prominent role, this is an opportune time to explore methodologies for appropriately representing system attributes. We suggest this is important for effective system development because the primary factor in correctly mapping between requirements and implementation is how representative the system design is of requirements. Since representativeness is an abstract term, it is imperative to identify ways to quantify it. We use several metrics. Among these is the priority of system elements (e.g., electric generator) in the set of elements, based on importance to system success. Secondly, fault tree analysis is employed to identify elements that operate in an unsafe state and the probabilities of reaching these unsafe states. Thirdly, state transition analysis provides traces of which elements are on the routes to unsafe states. These analyses provide the information needed to reduce element faults and failures on a priority basis.

show abstract

Putting more brain-like intelligence into the electric power grid: What we need and how to do it

Cited by 21 publications

References 6 publications

Autonomous Data-Driven Decision-Making in Smart Electricity Markets

Autonomous Data-Driven Decision-Making in Smart Electricity Markets

ECO-DAC Energy Control over Divide and Control

Representativeness models of systems: smart grid example

Contact Info

Product

Resources

About