2.1 Modeling and Simulation
19
individual model techniques and provides a structure to study different aspects of
a real-world problem.
2.1.2 Hybrid Modeling and Simulation
Tolk defines hybrid—biologically and technically speaking—as “the result of
merging two or more components of different categories to generate something
new, that combines the characteristics of these components into something more
useful. A mule is a biological hybrid, the crossbred of a donkey and a horse with
better endurance and a longer useful lifespan than its parents. Crops grown from
hybrid seeds produce plants of high quantity and quality. A hybrid car combines the advantages of gasoline engines and electric motors. Hybrid golf clubs
combine the characteristics of wood and iron. Hybrids take two—or more—
components and create something better” [Mu+2017, p. 1640]. The reason for
mixing methods is that real world problems are usually very complex and neither completely event-discrete, nor completely continuous. “They require different
methods to address the multiplicity of dimensions of a problem. Additionally, all
methods have different strengths and weaknesses so mixing methods can overcome the limitations of one method” [Mu+2017, p. 1638]. There is no consensus
in literature or throughout the hybrid simulation community on one precise definition of hybrid simulation. “Furthermore, new terms have been introduced which,
arguably, have the same meaning, e.g., multi-method simulation, multiparadigm
modeling, cross-paradigm simulation, mixed-modeling and combined simulation”
[Mu+2017, p. 1631]. All approaches describe a combination of two or three of
the most commonly applied simulation techniques DES, ABS and SD in connection with the occurrence of the term hybrid simulation or one of its derivates.
Hybrid simulation is usually applied in the implementation stage of a simulation.
At this point, it is important to differentiate hybrid simulation from hybrid systems
modeling (HSM), which describes the combination of simulation techniques “with
methods and techniques from disciplines such as Applied Computing, Computer
Science, Systems Engineering, and OR” [MP2018, p. 1430], to name for example
problem structuring methods, forecasting, classical optimization techniques, process mining, data mining, and machine learning. HSM is not only applied in the
implementation phase of the simulation study life cycle but can also be applied
in the conceptual modeling phase, the model verification and validation phase, as
well as in the experimental stages 8 .
8 Compare here the full paper of Mustafee and Powell for further reading [MP2018].
19
individual model techniques and provides a structure to study different aspects of
a real-world problem.
2.1.2 Hybrid Modeling and Simulation
Tolk defines hybrid—biologically and technically speaking—as “the result of
merging two or more components of different categories to generate something
new, that combines the characteristics of these components into something more
useful. A mule is a biological hybrid, the crossbred of a donkey and a horse with
better endurance and a longer useful lifespan than its parents. Crops grown from
hybrid seeds produce plants of high quantity and quality. A hybrid car combines the advantages of gasoline engines and electric motors. Hybrid golf clubs
combine the characteristics of wood and iron. Hybrids take two—or more—
components and create something better” [Mu+2017, p. 1640]. The reason for
mixing methods is that real world problems are usually very complex and neither completely event-discrete, nor completely continuous. “They require different
methods to address the multiplicity of dimensions of a problem. Additionally, all
methods have different strengths and weaknesses so mixing methods can overcome the limitations of one method” [Mu+2017, p. 1638]. There is no consensus
in literature or throughout the hybrid simulation community on one precise definition of hybrid simulation. “Furthermore, new terms have been introduced which,
arguably, have the same meaning, e.g., multi-method simulation, multiparadigm
modeling, cross-paradigm simulation, mixed-modeling and combined simulation”
[Mu+2017, p. 1631]. All approaches describe a combination of two or three of
the most commonly applied simulation techniques DES, ABS and SD in connection with the occurrence of the term hybrid simulation or one of its derivates.
Hybrid simulation is usually applied in the implementation stage of a simulation.
At this point, it is important to differentiate hybrid simulation from hybrid systems
modeling (HSM), which describes the combination of simulation techniques “with
methods and techniques from disciplines such as Applied Computing, Computer
Science, Systems Engineering, and OR” [MP2018, p. 1430], to name for example
problem structuring methods, forecasting, classical optimization techniques, process mining, data mining, and machine learning. HSM is not only applied in the
implementation phase of the simulation study life cycle but can also be applied
in the conceptual modeling phase, the model verification and validation phase, as
well as in the experimental stages 8 .
8 Compare here the full paper of Mustafee and Powell for further reading [MP2018].