Optimal configuration and control strategy in a multi-carrier-energy system using reinforcement learning methods

Author(s):  
J. Bollenbacher ◽  
B. Rhein
Author(s):  
Yujian Ye ◽  
Dawei Qiu ◽  
Jonathan Ward ◽  
Marcin Abram

The problem of real-time autonomous energy management is an application area that is receiving unprecedented attention from consumers, governments, academia, and industry. This paper showcases the first application of deep reinforcement learning (DRL) to real-time autonomous energy management for a multi-carrier energy system. The proposed approach is tailored to align with the nature of the energy management problem by posing it in multi-dimensional continuous state and action spaces, in order to coordinate power flows between different energy devices, and to adequately capture the synergistic effect of couplings between different energy carriers. This fundamental contribution is a significant step forward from earlier approaches that only sought to control the power output of a single device and neglected the demand-supply coupling of different energy carriers. Case studies on a real-world scenario demonstrate that the proposed method significantly outperforms existing DRL methods as well as model-based control approaches in achieving the lowest energy cost and yielding a representation of energy management policies that adapt to system uncertainties.


Author(s):  
Xiangjun Quan ◽  
Ruiyang Yu ◽  
Xin Zhao ◽  
Yang Lei ◽  
Tianxiang Chen ◽  
...  

2014 ◽  
Vol 257 ◽  
pp. 335-343 ◽  
Author(s):  
Michael S. Okundamiya ◽  
Joy O. Emagbetere ◽  
Emmanuel A. Ogujor

TAPPI Journal ◽  
2018 ◽  
Vol 17 (05) ◽  
pp. 295-305
Author(s):  
Wesley Gilbert ◽  
Ivan Trush ◽  
Bruce Allison ◽  
Randy Reimer ◽  
Howard Mason

Normal practice in continuous digester operation is to set the production rate through the chip meter speed. This speed is seldom, if ever, adjusted except to change production, and most of the other digester inputs are ratioed to it. The inherent assumption is that constant chip meter speed equates to constant dry mass flow of chips. This is seldom, if ever, true. As a result, the actual production rate, effective alkali (EA)-to-wood and liquor-to-wood ratios may vary substantially from assumed values. This increases process variability and decreases profits. In this report, a new continuous digester production rate control strategy is developed that addresses this shortcoming. A new noncontacting near infrared–based chip moisture sensor is combined with the existing weightometer signal to estimate the actual dry chip mass feedrate entering the digester. The estimated feedrate is then used to implement a novel feedback control strategy that adjusts the chip meter speed to maintain the dry chip feedrate at the target value. The report details the results of applying the new measurements and control strategy to a dual vessel continuous digester.


Sign in / Sign up

Export Citation Format

Share Document