TY - JOUR
T1 - Energy and uncertainty
T2 - Models and algorithms for complex energy systems
AU - Powell, Warren Buckler
N1 - Publisher Copyright:
Copyright © 2014, Association for the Advancement of Artificial Intelligence. All rights reserved.
PY - 2014/9/1
Y1 - 2014/9/1
N2 - The problem of controlling energy systems (generation, transmission, storage, investment) introduces a number of optimization problems that need to be solved in the presence of different types of uncertainty. I highlight several of these applications, using a simple energy storage problem as a case application. Using this setting, I describe a modeling framework that is based on five fundamental dimensions and that is more natural than the standard canonical form widely used in the reinforcement learning community. The framework focuses on finding the best policy, where I identify four fundamental classes of policies consisting of policy function approximations (PFAs), cost function approximations (CFAs), policies based on value function approximations (VFAs), and look-ahead policies. This organization unifies a number of competing strategies under a common umbrella.
AB - The problem of controlling energy systems (generation, transmission, storage, investment) introduces a number of optimization problems that need to be solved in the presence of different types of uncertainty. I highlight several of these applications, using a simple energy storage problem as a case application. Using this setting, I describe a modeling framework that is based on five fundamental dimensions and that is more natural than the standard canonical form widely used in the reinforcement learning community. The framework focuses on finding the best policy, where I identify four fundamental classes of policies consisting of policy function approximations (PFAs), cost function approximations (CFAs), policies based on value function approximations (VFAs), and look-ahead policies. This organization unifies a number of competing strategies under a common umbrella.
UR - http://www.scopus.com/inward/record.url?scp=84907612473&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84907612473&partnerID=8YFLogxK
U2 - 10.1609/aimag.v35i3.2540
DO - 10.1609/aimag.v35i3.2540
M3 - Article
AN - SCOPUS:84907612473
SN - 0738-4602
VL - 35
SP - 8
EP - 21
JO - AI Magazine
JF - AI Magazine
IS - 3
ER -