Shuffled Complex Evolution combined with Stochastic Ranking for Reservoir Scheduling PhD Dissertation Writing Services - Phdassistance.com
                     Shuffled Complex  
Evolution Combined 
With  Stochastic 
Ranking for  Reservoir 
Scheduling
An Academic presentation by
Dr. Nancy Agens, Head, Technical Operations, 
Phdassistance  Group www.phdassistance.com
Email: [email protected]
TODAY'S  In Brief  
In t rod uc t ion
DISCUSSI Shuf f led complex  evo lu t ion  
(SCE)  SCE-SR
ON Shuf f led Complex Evolut ion  - Stochast ic  
 Ranking A lgor i thm
Outlin SR – Stochast ic  Ranking 
e  SCE-SR A lgor i thm
Two Main Character is t ics  of  SCE-SR 
 Four Vi tal  Parameters of  SCE  
Cri ter ia for  SCE-SR
Conclus ion  
Future Scope
In 
You will find the best dissertatioBn rerseiaerchf areas / topics for future researchers 
enrolled in  Engineering and technology.
In order to identify the future research topics, we have reviewed the Engineering 
literature  (recent peer-reviewed studies) on Shuffled Complex Evolution and 
Stochastic Ranking for  Reservoir Scheduling
Nature-Inspired Optimization Algorithm is the recent trend in Cloud technology.
Shuffled Complex Evolution Algorithm is one of Nature-Inspired Optimization 
Algorithm.
Shuffled Complex Evolution Algorithm is used for Reservoir Scheduling and 
Stochastic  Ranking.
Introductio
n
Water is one of the most valuable resources and humans have built dams to optimize the 
 use of this precious resource.
Dams are a life-sustaining resource for people throughout the world.
These dams have internally water storage spaces called reservoirs, and the operation  
priorities of these reservoirs are based on a sequence of rules to recognize the amount of 
 water stored and released according to system constraints.
The process of prioritizing the reservoir operation is known as "reservoir scheduling" and 
 we use various machine learning methods or algorithms for reservoir scheduling.
Shuffled complex evolution (SCE) is a method, where
SHUFFLE its general purpose is global optimization.
D  The SCE algorithm is capable of finding optimum  
COMPLEX  globally and it does not rely on the availability of an  explicit expression for the objective function or the 
EVOLUTIO  derivatives.
N  (SCE) Another method “stochastic ranking (SR)” is capable 
 of balancing objectives and penalty functions and is 
 highly competitive compared to other methods.
The application of a "Shuffled Complex Evolution-  
Stochastic Ranking (SCE-SR)" therefore provides an 
 effective solution to the above mentioned problems.
SCE combines the strengths of the simplex method 
 and the complex algorithm of competitive evolution 
 and SR is free from complicated parameter tuning, 
 The SCE-SR takes advantage of both.
SCE-
SCE-SR makes SCE suitable for constrained  
SR reservoir scheduling problems and may achieve  global convergence properties.
The SCE-SR method is an efficient and effective  
method to optimize hydropower generation and  
quickly identify feasible areas, with adequate global 
 convergence properties and robustness.
SCE algorithm uses the concept of complex shuffling to solve the 
 non- linear optimization problem.
Shuffled The method involves the following terminologies:
Complex  
Points (candidate solutions),
Evolution -  
Stochastic  Population (the community containing all points),
Ranking Complex (the community containing several points Partitioned 
Algorithm  from the sample),
Complex shuffling (points in complexes reassigned and mixed 
SCE 
 to generate a new community).
Algorithm
One of the main components of SCE is the CCE algorithm, 
 which can be described briefly as follows:
Contd..
Construction of a sub-complex (containing q points) according to the trapezoidal probability  
distribution.
Ranking: identification of the worst point u of the sub-complex and computation of the centroid 
 g of the q−1 points without including the worst one.
Reflection: reflection of point u through the centroid to generate a new point r and calculation  
of its objective function value fr. If the newly generated point r is within the feasible space and 
 fr>fu, where fu is the objective function value of point u, u is replaced with r, and the process  
moves to step (6). Otherwise, it goes to step (4).
Contd..
Contraction: determination of a point c halfway between the centroid and the worst point, and  
then calculation of fc. If point c is within the feasible space and fc>fu, u is replaced with the 
 contraction point c and the process goes to step (6). Otherwise, it goes to step (5).
Mutation: random generation of a point z within the feasible space and replacement of the 
 worst point with z.
Steps (2) through (5) are repeated α time, where α≥1 is the number of consecutive offspring 
 generated by each sub-complex.
Steps (1) through (6) are repeated β times, where β≥1 is the number of evolution steps taken 
 by each complex before complexes are shuffled.
Figure 1 Flow 
Chart of  SCE-SR 
Algorithm
The SR is capable of balancing objective and penalty  
functions and improving the search performance.
SR – 
The main idea is to compare two adjacent individuals  
Stochastic  according to the objective function values or the degree of  
Ranking constraint violations by introducing a predetermined  parameter Pf.
An increase in the number of ranking sweeps (N) is 
 effectively equivalent to changing parameter .
Contd
..
Thus, the number of ranking sweeps is fixed to N = s (number of points in sample 
 population generated by SCE), and is adjusted within [0, 1] to achieve the best  
performance.
The comparison mechanism of two adjacent individuals can be briefly described 
 as follows: if both individuals are feasible, or a randomly generated number  
w∈[0,1] is less than Pf, they are compared according to the objective function  
values; otherwise, they are compared based on the degree of constraint  
violations.
Ranking of the whole sample population is then achieved through a bubble-like 
 procedure.
Thus, the number of ranking sweeps is fixed to N = s (number of  
points in sample population generated by SCE), and
SCE-SR is adjusted  within [0, 1] to achieve the best performance.
The comparison mechanism of two adjacent individuals can be  
Algorith briefly described as follows: if both individuals are feasible, or a  
m randomly generated number w∈[0,1] is less than Pf, they are  compared according to the objective function values; otherwise, 
 they are compared based on the degree of constraint 
violations.
Ranking of the whole sample population is then achieved 
 through a bubble-like procedure.
The combination of the deterministic approach and 
 competitive evolution.
Two Main  
This is conducive to directing the search in an improving  
Characteristi direction and improving global convergence efficiency by 
 making use of information carried by both feasible and  
cs  of SCE-SR non-feasible individuals.
The combination of the probabilistic approach and  
complex shuffling. This guarantees the survivability of 
 individuals and the flexibility and robustness of the  
algorithm.
Four Vital  The number of points in a complex, m=2n+1, where n is the 
 dimension of the decision vector,
Paramete
The number of points in a sub-complex, q=n+1,
rs  of SCE
The number of consecutive offspring generated by each sub- 
 complex, α=1,
The number of iterations taken by each complex, β=m.
For SR, the required range of the parameter is 0.4