Information Technology Reference
In-Depth Information
Agent Class
Electricity Market
Class
Session
Management Class
Learning Algorithms
Interface
Heap Memory
Class
Offline Analysis
Module
Fig. 1. GAPEX Class Architecture
- a heap class;
- a statistical off-line analysis module;
- several algorithms and market mechanisms libraries.
Figure 1 shows the GAPEX class architecture. The Agent class is an abstract class
which is extended by all agents present in GAPEX Framework. It is worth noting that
the Agent class is directly extended in order to define any new types of Electricity Mar-
ket Agents (e.g., Wholesalers, Energy Management Divisions, etc). As concerning the
learning algorithms, they are modeled as interfaces implemented by Gencos. Current
version of GAPEX is characterized by a library of the main solutions for learning al-
gorithms proposed in the literature (e.g., Roth-Erev algorithm, Q-Learning algorithm,
Marimon-McGrattan algorithm, EWA learning and GiGa WoLF algorithm). In particu-
lar, these algorithms have been extended so to consider reward both positive, negative
and null, and the features of the enhanced Roth-Erev algorithm are discussed in Sec-
tion 4. The Electricity Market class allows one to define the market clearing algorithms
and it is based on the Agent class. Currently, the GAPEX allows one to simulate the
Italian Day Ahead Market, the EEX spot market linking DCOPFJ Package [22] and the
Spanish Day Ahead Market. It is worth nothing that all these algorithms are interfaces
as well. The Session class has a two-fold purposes. On the one hand, it acts as a clear-
ing house and allows one to run several iterations of a particular simulation and to call
the statistical off-line module at the end of the simulation. On the other hand, it stores
all market and agent information, thus acting as a repository for all data related to en-
ergy prices and quantities both at market and at agent level (e.g. choices, propensities,
etc). This feature is of crucial importance for economics application as it allows the
GAPEX framework to be used as an artificial world where computational experiments
can be performed. Indeed, such computational experiments are mandatory so to evalu-
ate reproducibility of stylized facts as well as statistical properties of the self-adaptive
complex system under investigation (see [2]). Moveover, in order to model the clear-
ing house feature and characteristics, the mechanism of Heap memory access has been
 
Search WWH ::




Custom Search