scispace - formally typeset
Search or ask a question
ReportDOI

Particle Swarm Social Adaptive Model for Multi-Agent Based Insurgency Warfare Simulation

TL;DR: In this article, a social adaptive model for modeling multiple insurgent groups attacking multiple military and civilian targets is proposed and investigated, and the results show that unified leadership, strategic planning, and effective communication between insurgent groups are not the necessary requirements for insurgents to efficiently attain their objective.
Abstract: To better understand insurgent activities and asymmetric warfare, a social adaptive model for modeling multiple insurgent groups attacking multiple military and civilian targets is proposed and investigated. This report presents a pilot study using the particle swarm modeling, a widely used non-linear optimal tool to model the emergence of insurgency campaign. The objective of this research is to apply the particle swarm metaphor as a model of insurgent social adaptation for the dynamically changing environment and to provide insight and understanding of insurgency warfare. Our results show that unified leadership, strategic planning, and effective communication between insurgent groups are not the necessary requirements for insurgents to efficiently attain their objective.

Summary (2 min read)

Figure Page

  • To better understand insurgent activities and asymmetric warfare, a social adaptive model for modeling multiple insurgent groups attacking multiple military and civilian targets is proposed and investigated.
  • In the last century, relatively modern studies about insurgency warfare have provided general insights and practical guidance into the perspective of insurgents and counter-insurgents [5, 8].
  • Numerous empiricalbased multi-agent simulators [11] have been constructed over recent years to model complex dynamic systems in numerous disciplines.
  • The authors present a modified particle swarm model for simulating the insurgent groups’ social interaction and adaptation in a complex insurgency warfare system.
  • Each particle also has memory to record the “best location” in the problem space that it has experienced so far, and the knowledge of the best location found so far by all the particles of the swarm.

4.1 SIMULATION SCENARIO

  • Different groups of insurgent agents seek efficient attacking methods to strike the dominant power’s targets.
  • The insurgent agents do not have any prior-knowledge about the targets.
  • The insurgent agent that attacks the authority’s targets will receive a feedback on the results of the current and historic attack strategy.

4.2 AGENTS

  • Two types of agents are specified in the particle swarm social adaptive model – the insurgency and the target.
  • There can be multiple insurgencies and targets in the simulation.
  • The insurgent agent can be affiliated with different groups.
  • In contrast, the targets seek to avoid being detected and to increase protection to reduce their loss from insurgent attacks.
  • All agents behave, act, and react in accordance with the environment they have detected.

4.3 INSURGENT INFORMATION EXCHANGE RULE

  • Insurgents belonging to the same group can exchange information without any restriction.
  • But the information exchanged between different groups will be delayed for a pre-defined number of timesteps and some noise will be added to the value of the information to reduce the information’s accuracy.

4.4 INSURGENT AGENT STRATEGIC SEARCHING RULE

  • The PSO algorithm is used to control the insurgent strategic searching.
  • Each insurgent particle has two associated properties, a current position x and a velocity v. Each particle has a memory of its best location where the biggest lose to the authority targets was caused so far in the attack strategic searching space.
  • When the delayed and noisy gbest value from other groups arrives, the gbest value from other groups will replace the gbest value within the group.
  • The velocity vector is influenced by both the particle’s previous velocity, its current location and its pbest and gbest value.
  • Therefore, at each step, the size and direction of each particle’s movement is a function of its own history and the social influence of its peers.

4.5 TARGET DYNAMICAL ADAPTIVE RULE

  • When they are attacked, they will gradually increase their protection level to reduce the loss that the insurgent can generate after each attack and to decrease the detectable distance to make itself more difficult to be detected.
  • Once a target has not been attacked for several time-steps, this target will change its protection level to its original value.

4.6 MEMORY UPDATE RULE

  • Based on the target dynamical adaptive rule, targets can randomly move in the environment and the fitness value of each target in the environment may change over time after insurgent attacks.
  • Depending on the particle’s current stored best fitness value f(P) and the current fitness value f(X) the particle acquired, the particle will update its best fitness value more frequently by using its current fitness value when the f(P) is lower and the f(X) is higher.
  • Fig. 3 illustrates that, in the dynamic environment, the insurgent group modeled with PSO model without the memory update rule fails to track the randomly moving optimal solution.
  • As shown in Fig. 6, the simulation of twenty insurgent groups can cause more loss of targets than both the one group and the two groups do, although there is no unified leadership, planning or effective communication among these twenty insurgent groups in the simulation compared to the one group insurgent simulation.

Did you find this useful? Give us your feedback

Content maybe subject to copyright    Report

ORNL/TM-2007/20
Particle Swarm Social Adaptive Model
for Multi-Agent Based Insurgency
Warfare Simulation
Date: January, 2007
Prepared by:
Xiaohui Cui
Associate Staff

DOCUMENT AVAILABILITY
Reports produced after January 1, 1996, are generally available free via the U.S. Department of
Energy (DOE) Information Bridge.
Web site http://www.osti.gov/bridge
Reports produced before January 1, 1996, may be purchased by members of the public from the
following source.
National Technical Information Service
5285 Port Royal Road
Springfield, VA 22161
Telephone 703-605-6000 (1-800-553-6847)
TDD 703-487-4639
Fax 703-605-6900
E-mail info@ntis.gov
Web site http://www.ntis.gov/support/ordernowabout.htm
Reports are available to DOE employees, DOE contractors, Energy Technology Data Exchange
(ETDE) representatives, and International Nuclear Information System (INIS) representatives from the
following source.
Office of Scientific and Technical Information
P.O. Box 62
Oak Ridge, TN 37831
Telephone 865-576-8401
Fax 865-576-5728
E-mail reports@osti.gov
Web site http://www.osti.gov/contact.html
This report was prepared as an account of work sponsored by an
agency of the United States Government. Neither the United States
Government nor any agency thereof, nor any of their employees, makes
any warranty, express or implied, or assumes any legal liability or
responsibility for the accuracy, completeness, or usefulness of any
information, apparatus, product, or process disclosed, or represents that
its use would not infringe privately owned rights. Reference herein to
any specific commercial product, process, or service by trade name,
trademark, manufacturer, or otherwise, does not necessarily constitute
or imply its endorsement, recommendation, or favoring by the United
States Government or any agency thereof. The views and opinions of
authors expressed herein do not necessarily state or reflect those of the
United States Government or any agency thereof.

ORNL/TM-2007/20
Computational Science and Engineering Division
PARTICLE SWARM SOCIAL ADAPTIVE MODEL FOR MULTI-
AGENT BASED INSURGENCY WARFARE SIMULATION
Xiaohui Cui and Thomas E. Potok
Date Published: August, 2007
Prepared by
OAK RIDGE NATIONAL LABORATORY
Oak Ridge, Tennessee 37831-6283
managed by
UT-BATTELLE, LLC
for the
U.S. DEPARTMENT OF ENERGY
under contract DE-AC05-00OR22725


iii
CONTENTS
Page
LIST OF FIGURES ............................................................................................................................... v
ABSTRACT...........................................................................................................................................1
1. INTRODUCTION ...........................................................................................................................1
2. PARTICLE SWARM OPTIMIZATION ALGORITHM................................................................ 1
3. RELATED WORK..........................................................................................................................3
4. PARTICLE SWARM SOCIAL ADAPTIVE MODEL FOR INSURGENCY WARFARE
SIMULATION................................................................................................................................. 3
4.1 SIMULATION SCENARIO...................................................................................................... 3
4.2 AGENTS.................................................................................................................................... 4
4.3 INSURGENT INFORMATION EXCHANGE RULE.............................................................. 4
4.4 INSURGENT AGENT STRATEGIC SEARCHING RULE ....................................................4
4.5 TARGET DYNAMICAL ADAPTIVE RULE..........................................................................4
4.6 MEMORY UPDATE RULE ..................................................................................................... 4
5. EXPERIMENTAL SETTINGS AND RESULTS .......................................................................... 5
6. DISCUSSION AND CONCLUSION.............................................................................................. 7
7. REFERENCES ................................................................................................................................ 8

Citations
More filters
Book ChapterDOI
31 Jan 2012
TL;DR: This article presents an agent-based computational model of civil violence, which shows that a central authority seeks to suppress decentralized rebellion and communal violence between two warring ethnic groups.
Abstract: This article presents an agent-based computational model of civil violence. Two variants of the civil violence model are presented. In the first a central authority seeks to suppress decentralized rebellion. In the second a central authority seeks to suppress communal violence between two warring ethnic groups.

277 citations

References
More filters
Proceedings ArticleDOI
06 Aug 2002
TL;DR: A concept for the optimization of nonlinear functions using particle swarm methodology is introduced, and the evolution of several paradigms is outlined, and an implementation of one of the paradigm is discussed.
Abstract: A concept for the optimization of nonlinear functions using particle swarm methodology is introduced. The evolution of several paradigms is outlined, and an implementation of one of the paradigms is discussed. Benchmark testing of the paradigm is described, and applications, including nonlinear function optimization and neural network training, are proposed. The relationships between particle swarm optimization and both artificial life and genetic algorithms are described.

35,104 citations


"Particle Swarm Social Adaptive Mode..." refers methods in this paper

  • ...Although the PSO algorithm has been widely used as a function optimization tool since it was first published in 1995, the initial research target of the PSO was to develop a human social model and the algorithm itself represents an abstract model of human knowledge social adaptation behavior [6, 7]....

    [...]

Proceedings ArticleDOI
13 Apr 1997
TL;DR: The paper introduces the algorithm, begins to develop a social science context for it, and explores some aspects of its functioning.
Abstract: Particle swarm adaptation is an optimization paradigm that simulates the ability of human societies to process knowledge The algorithm models the exploration of a problem space by a population of individuals; individuals' successes influence their searches and those of their peers The algorithm is relevant to cognition, in particular the representation of schematic knowledge in neural networks Particle swarm optimization successfully optimizes network weights, simulating the adaptive sharing of representations among social collaborators The paper introduces the algorithm, begins to develop a social science context for it, and explores some aspects of its functioning

1,630 citations


"Particle Swarm Social Adaptive Mode..." refers background or methods in this paper

  • ...Researchers from Europe have applied the PSO model to the simulation of the social behavior in animals [7, 8] and the strategic adaptation in organizations [9]....

    [...]

  • ...c1 and c2 are two positive acceleration constants; w is the constriction coefficient[7] and it is computed according to Equation 2a:...

    [...]

  • ...Mathematically, given a multi-dimensional problem space, the ith particle changes its velocity and location according to the following equations[7, 9]:...

    [...]

  • ...Although the PSO algorithm has been widely used as a function optimization tool since it was first published in 1995, the initial research target of the PSO was to develop a human social model and the algorithm itself represents an abstract model of human knowledge social adaptation behavior [6, 7]....

    [...]

Book
01 Jan 1961
TL;DR: Mao Tse-tung's pamphlet on guerrilla warfare has become the basic textbook for waging revolution in underdeveloped and emergent areas throughout the world as mentioned in this paper, where Mao's pamphlet is used as a starting point for many guerilla campaigns.
Abstract: Mao Tse-tung's pamphlet on guerrilla warfare has become the basic textbook for waging revolution in underdeveloped and emergent areas throughout the world

477 citations

Journal ArticleDOI
TL;DR: In this paper, an agent-based computational model of civil violence is presented, in which a central authority seeks to suppress decentralized rebellion and another central authority aims to suppress communal violence between two warring ethnic groups.
Abstract: This article presents an agent-based computational model of civil violence. Two variants of the civil violence model are presented. In the first a central authority seeks to suppress decentralized rebellion. In the second a central authority seeks to suppress communal violence between two warring ethnic groups.

420 citations

Frequently Asked Questions (1)
Q1. What contributions have the authors mentioned in the paper "Particle swarm social adaptive model for multi-agent based insurgency warfare simulation" ?

This report presents a pilot study using the particle swarm modeling, a widely used nonlinear optimal tool to model the emergence of insurgency campaign. The objective of this research is to apply the particle swarm metaphor as a model of insurgent social adaptation for the dynamically changing environment and to provide insight and understanding of insurgency warfare.