My project work is optimization in power system (like load flow, parameters and position finding, filter designing, fault location etc ) and I have used PSO (particle swarm optimization), different new improved version of PSO, HS (harmony search), and different new improved version of HS but I want a new technique, which will gives best results in comparison to all other existing Optimization technique. Please can anyone suggest a new technique which will give best result in comparison to other technique?
Friend, you are most probably trying to find a single shot meta-heuristic population based search algorithm (simply an evolutionary or a swarm intelligence algorithm), that will result in the best outcome for your problem. But, In this field no algorithm can perform the best in all kind of problems (Cost Function).
Some of the issues (which make these algorithms so problem dependent) which determine the entire search process are:
1. The representation of individual (each solution string, equivalent to chromosome in GA),
2. Internal parameter setting (being a numerical algorithm, these dependence in non-negligible),
3. Neighborhood strategy (how is each solution get influenced by the others in the same population (like velocity update equation in PSO), or others (DEGL, JADE, ALCPSO, FFA etc.),
4. How each tool (Parallelism: like Niche based approach; Tools of PSO like velocity and position update equation; Selection, Crossover, Mutation in EAs) is modeled.
5. Population Size (Diversity and Computational pressure)
and many more.
What you can do, is first model your Fitness function. Study recent algorithms and its overviews, if your function matches exactly with any standard cost functions (refer CEC), you can use the algorithm which has performed best in that cost function. Generally it is a trial and error procedure, and nobody can firmly claim to the best (Refer to NO FREE LAUNCH THEOREM).
This is quiet embarrassing, yet, a hope is some algorithms and strategies are there which can give very good and acceptable results. Good luck.
Friend, you are most probably trying to find a single shot meta-heuristic population based search algorithm (simply an evolutionary or a swarm intelligence algorithm), that will result in the best outcome for your problem. But, In this field no algorithm can perform the best in all kind of problems (Cost Function).
Some of the issues (which make these algorithms so problem dependent) which determine the entire search process are:
1. The representation of individual (each solution string, equivalent to chromosome in GA),
2. Internal parameter setting (being a numerical algorithm, these dependence in non-negligible),
3. Neighborhood strategy (how is each solution get influenced by the others in the same population (like velocity update equation in PSO), or others (DEGL, JADE, ALCPSO, FFA etc.),
4. How each tool (Parallelism: like Niche based approach; Tools of PSO like velocity and position update equation; Selection, Crossover, Mutation in EAs) is modeled.
5. Population Size (Diversity and Computational pressure)
and many more.
What you can do, is first model your Fitness function. Study recent algorithms and its overviews, if your function matches exactly with any standard cost functions (refer CEC), you can use the algorithm which has performed best in that cost function. Generally it is a trial and error procedure, and nobody can firmly claim to the best (Refer to NO FREE LAUNCH THEOREM).
This is quiet embarrassing, yet, a hope is some algorithms and strategies are there which can give very good and acceptable results. Good luck.
I agree with Sudipta. It's clear from the No Free Lunch theory that a particular algorithm will perform no better than any other algorithm when considered across all problems. However, you can expect certain algorithms to be better at solving certain problems. This will come down to the nature of the problem's optimisation landscape, and the way in which the algorithm attempts to search this landscape. Evolutionary and swarm algorithms (such as PSO) show competence across a broad range of common problems. However, it is quite likely that they will be beaten by tabu search, simulated annealing, branch-and-bound methods, iterated local search, variable neighbourhood search and others on many problems.
Some recent reference books you might look at are:
Handbook of Metaheuristics, 2nd edition - Gendreau and Potvin, 2010
Derivative-free optimization - Rios and Sahinidis, 2013
Handbook of Natural Computing - Rozenberg, Back and Kok, 2012
Completely agree with Michael and Sudipta, could you give us a more detailed description of your problem and the optimisation function?
@ sudipta, Michael, : i know optimization techniques are vary problem to problem, best techniques depends on Cost function, For different cost function different methods are possible.
But my research is in the field of Power system
where problems for power system "Preparation and planning" are :
Prioritizing investments in distribution network
Optimal protection and switching device placement
Generation scheduling
Maintenance scheduling
Power mix planning
Problems for power system "Operative control"
Constrained load flow
Power plant operation optimizer
Unit commitment – economic dispatch
Optimal power flow
FACTS (Flexible AC Transmission System) control
Voltage/VAr and loss reduction
Dynamic load modeling
Short-Term load forecast
Network reconfiguration and load reduction
Market operations, etc.
And for solution Different “Traditional” techniques:
Weighting Objectives
Goal programming
Constraint programming
Stochastic
Linear Programming
Gradient Based/Hill Climbing
Sequential Optimization, etc.
some Modern techniques for solutions:
Evolutionary Computation
Genetic algorithms
Particle swarm optimization
harmony search
Fuzzy Set Theory
Ant colony search algorithm
Simulated Annealing
Pareto multi objective Optimization
BUT MY QUESTION IS...
IS ANY OTHER NEW TECHNIQUES FOR POWER SYSTEM PROBLEM SOLVING EXCEPT THIS.....
Hello Mr Nishant Kumar ,
Your question is very interesting.
Firstly, I have searched the books cited by Mr Michael Lones and I found out an interesting paper (open access) : "Derivative-free optimization: a review of algorithms and comparison of software implementations".Rios and Sahinidis, 2013. If you are interested...
I understand that you are looking for a "new techniques" for solving your problem. However, I should agree with the aforementioned issues. For each problem, there will be a specific suitable algorithm.
However, there are two method that has been recently proposed: BAT algorithm and Cuckoo Search. There are few applications of these new techniques on power system problems. I have applied these algorithms to solve problems in power system distribution planning and power system stability and the results were very promising.
These methods have been proposed by Dr Xin-she Yang in 2010.
@wesley Peres, very very thanks
i want to ask, after getting the result by BAT or Cuckoo search of the problem of power system distribution planning and power system stability. u was compared your result with another results like result of PSO or HS. And was your result best in comparison to other ?
Hi Nishant Kumar,
Unfortunately I did not compare my solutions to HS or PSO.
However, the BAT algorithm is very similar to PSO. It is a mix of PSO and local search. When these algorithms have been proposed, the author have compared them to PSO. The results shown that BAT and Cuckoo Search provided better results than PSO and Genetic Algorithm.
I have tried to enclose three papers for you in this post, but I had some problems. Please, send me an email "[email protected]" and I will send you the papers.
Regards,
Wesley
I strongly recommend you these two papers, there you have a comprehensive analysis of nearly all kind of available methods that you have:
Optimal Power Flow: A Bibliographic Survey I
Formulations and Deterministic Methods
http://www.rebennack.net/files/papers/FraSteReb12a.pdf
Optimal Power Flow: A Bibliographic Survey II
Non-Deterministic and Hybrid Methods
http://www.rebennack.net/files/papers/FraSteReb12b.pdf
@Peres
thanks for your information but i am shocked after seen your message.
BAT and Cuckoo gives better result in comparison to PSO
My mail Id. is : [email protected]
@Pablo
extremely thanks for those papers.
But OPF problem is all ready solve by this method.
i want any New method so I can work further with that method.
Try to use the tournament searching. This is simple stochastic method competitive to GA and PSO. It is for both continous and discrete optimization.
See:
https://www.researchgate.net/publication/221184961_Tournament_Searching_Method_to_Feature_Selection_Problem?ev=prf_pub
http://www.gdudek.el.pcz.pl/files/TourSearch_14.pdf
Conference Paper Tournament Searching Method to Feature Selection Problem
@Grzegorz
sir i am not thinking about simplicity, i want a strong method who can give best result in compression to other(like PSO, Harmony Search...etc)
Is this method can gives, best result...?
Dear Nishant,
There is no the best method or the strongest method. Each method has its pros and cons.
The tournament searching method is a simple generic stochastic search method. It has an efficient, flexible algorithm which can be adapted to binary, continuous and mixed binary–continuous optimization. TS in a binary version has only one parameter controlling the global/local searching properties of the algorithm – the tournament size. In the continuous version TS has the second parameter – the standard deviation used for generating new solutions.
In the comparative study I compared differential evolution, evolution strategy, PSO and TS. I used these methods for estimation of the parameters of Generalized Regression Neural Network. And TS gave the lowest error.
@ Grzegorz
thank you sir Now i am working on The tournament searching method...
i hope, i will get good results...
Dear You may try Spidr Monkey Optimization Algorithm(SMO). It is new member in group of NIAs. It gives better result in comparison to existing algorithms.
It has six steps but easy to implement.
@ Dhami
you have done work on this...
or you have any related Paper for this..
if yes please send me..
Just use advanced versions of PSO such as PSOCA, PSO-CATV or advanced versions of DE such as jDE or SADE.
Dinakara @ have you applied this Optimization(krill herd algorithm, GSA) Technique.
Bacterial foraging optimization algorithm is the latest technique for power system problem solving
@ Nishant Kumar
sir could you please send some latest and better algorithms and it papers ......
it would me much helpful for my optimization project .........
I would like to recommend you the following article: I may be helpful to you..
Mahamad Nabab Alam, Biswarup Das, Vinay Pant, A comparative study of metaheuristic optimization approaches for directional overcurrent relays coordination, Electric Power Systems Research, Volume 128, November 2015, Pages 39-52, ISSN 0378-7796, http://dx.doi.org/10.1016/j.epsr.2015.06.018.
(http://www.sciencedirect.com/science/article/pii/S0378779615001947)
Algorithm References Inventor&Year
1. Ant colony optimization (ACO) ; I Dorigo and Stutzle (2004)
2. Artificial immune system optimization; Cutello and Nicosia (2002)
3. Bacterial foraging optimization ; Kim, Abraham and Cho (2007)
4. Bee optimization ; Karaboga and Bosturk (2007)
Pham et al (2006)
5. Cuckoo algorithm ; Yang and Deb (2009, 2010)
6. Differential evolution (DE) ; Storn and Price (1995, 1997)
7. Firefly optimization ; Yang (2010)
8. Fish optimization ; Huang and Zhou (2008)
9.Genetic algorithms (GA) ; Haupt and Haupt (2004)
10.Particle swarm optimization (PSO), Binary Particle Swarm Optimization (BPSO); Eberhart and Kennedy (1995)
11.Raindrop optimization ; Shah-Hosseini (2009)
12.Simulated annealing ; Kirkpatrick, Gelatt and Vecchi (1983)
13.Biogeography-based optimization (BBO),
14. Chemical reaction optimization (CRO)
15. A group search optimizer (GSO),
16. Imperialist algorithm
17. Swine flow Optimization Algorithm.
18. Teaching Learning Based Optimization(TLBO)
19. Bayesian Optimization Algorithms (BOA)
20. Population-based incremental learning (PBIL)
21. Evolution strategy with covariance matrix adaptation (CMA-ES)
22. Charged system search Optimization Algorithm
23. Continuous scatter search (CSS) Optimization Algorithm
24. Tabu search Continuous Optimization
25. Evolutionary programming
26. League championship algorithm
27. Harmony search Optimization algorithm
28. Gravitational search algorithm Optimization
29. Evolution strategies Optimization
30. Firework algorithm, Ying Tan, 2010
31. Big-bang big-crunch Optimization algorithm, OK Erol, 2006
32. Artificial bee colony optimization (ABC), Karaboga,2005
33. Backtracking Search Optimization algorithm (BSA)
34. Differential Search Algorithm (DSA) (A modernized particle swarm optimization algorithm)
35. Hybrid Particle Swarm Optimization and Gravitational Search Algorithm (PSOGSA)
36. Multi-objective bat algorithm (MOBA) Binary Bat Algorithm (BBA)
37. Flower Pollination Algorithm
38. The Wind Driven Optimization (WDO) algorithm
39. Grey Wolf Optimizer (GWO)
40. Generative Algorithms
41. Hybrid Differential Evolution Algorithm With Adaptive Crossover Mechanism
42.Lloyd's Algorithm
43.One Rank Cuckoo Search (ORCS) algorithm: An improved cuckoo search optimization algorithm
44. Huffman Algorithm
45. Active-Set Algorithm (ASA)
46. Random Search Algorithm
47. Alternating Conditional Expectation algorithm (ACE)
48. Normalized Normal Constraint (NNC) algorithm
What are the recently invented Evolutionary algorithms (EAs)/ Optimization method? Which method you found en effective method ? - ResearchGate. Available from: https://www.researchgate.net/post/What_are_the_recently_invented_Evolutionary_algorithms_EAs_Optimization_method_Which_method_you_found_en_effective_method [accessed Nov 16, 2015].
PSO codes in MATLAB
https://www.researchgate.net/publication/296636431_Codes_in_MATLAB_for_Particle_Swarm_Optimization?ev=prf_pub
Code Codes in MATLAB for Particle Swarm Optimization
Kindly, go through the following publication.
Y. del Valle, G. Venayagamoorthy, S. Mohagheghi, J.-C. Hernandez, R. Harley, Particle swarm optimization: Basic concepts, variants and applications in power systems, IEEE Transactions on Evolutionary Computation, 12 (2) (2008) 171-195.
I hope it will be very helpful to you.
M.N.Alam
https://www.researchgate.net/publication/297245624_Particle_Swarm_Optimization_Algorithm_and_its_Codes_in_MATLAB
Research Particle Swarm Optimization: Algorithm and its Codes in MATLAB
I guess nobody mentioned the mean-variance optimization MVO technique!
http://link.springer.com/chapter/10.1007%2F978-3-319-12958-7_12
Respected Nishanth Kumar sir i i am unable to apply discrete pso please help me
Optimized location of FACTS using PSO, can anyone give me some guidelines?
The latest Optimization technique are:
1) intelligent monkey king evolution algorithm,
2) whale optimization with differential evolution,
3) Weibull Pareto sine–cosine optimisation,
4) JayaDE Algorithm
5) Cauchy and Gaussian sine cosine optimization,
Extrimelly New: 6) Human psychology optimisation (HPO),
Mr. Nishant Kumar if u want to improve the performance with latest optimization techniques then you may use hybrid optimization techniques. The newly developed techniques are good in finding the global optimal solution but if u merge these techniques with local search algorithms( for example pattern search) further with the newly developed technique then you can expect further improvement in performance. For example you can see this article of ours which is published by IET generation transmission and distribution. "Hybrid Adaptive gbest Guided Gravitational Search and Pattern Search Algorithm for Automatic Generation Control of Multi Area Power System". I hope it will provide you some good way to lead u in your work. Thank you.
Optimization methods:
Ant colony optimization
Ant lion optimizer
Artificial bee colony algorithm
Bat algorithm
Biogeography-based optimization
Brain Storm Optimization Algorithm
Cat swarm optimization
Crow search algorithm
Cuckoo optimization algorithm
Cuckoo search algorithm
Differential evolution
Dragonfly Algorithm
Earthworm Optimization Algorithm
ELephant Herd Algorithm
Evolutionary Strategy
Firefly algorithm
Flower Pollenation Algorithm
Football Game Algorithm
Genetic algorithm
Glowworm swarm optimization
Gravitational search algorithm
Grasshopper Optimization algorithm
Grey wolf optimizer
Harmony search
Hydrological Cycle Algorithm
Krill Herd algorithm
Lightning Search Algorithm
Mass and Energy Balances Algorithm
Multi-verse optimizer
Monarch Butterfly Optimizatio
Moth-Flame Optimization algorithm
Particle swarm optimization
Population-Based Incremental Learning
Quantum inspired algorithm
Rain Water Algorithm
Salp Swarm Algorithm
Shuffled complex evolution
Simulated annealing
Sine Cosine Algorithm
Tabu search
Teaching-learning-based optimization
Team game algorithm
Whale Optimization Algorithm
Please suggest latest topics in the field of power system to carry out research basically in optimal power flow
could someone tell me how to use PSO algorithm for the optimal placement of PSO
how it is used for optimization
Dear Maveeya Baba, you have to learn writing code for that. I will recommend Matpower toolbox.
- Badges
- Science topic