Symbioitc Sphere Bc Short Version

Paskorn Champrasert and Junichi Suzuki

Department of Computer ScienceUniversity of Massachusetts, Boston

A Biologically-inspired QoS-aware Architecture for Scalable, Adaptive and Survival Network Systems

October 30 2008 DSSG Group Meeting 2/20

Content• Goal

• Design Approach

• Overview of SymbioticSphere

• Simulation Results

• Conclusion


Motivation• Large-scale network systems

e.g., Internet Data Center• A tons of servers and network devices (e.g. router,

load manager) are connected through the high speed network.

• A lots of users access several services (e.g. web server) and data (web pages) that Internet Data Center provides.

• Such network systems stillrapidly keep increasing intheir scale.


Goal• Making network systems ( e.g. Internet data centers and grid

clusters) to be– autonomous to avoid interrupting users/administrators frequently

– adaptable to various dynamic changes in network conditions

• e.g., network traffic and resource availability

• in order to…– improve user experience (i.e. response time)– expand system’s operational longevity

(e.g. users and administrators don’t want applications down for long time)

– reduce maintenance cost (e.g. Save money and relieve developers from time-consuming maintenance)


Observation and Approach• Observation

– Various biological systems have already developed the mechanisms to achieve key requirements of network systems. • e.g. autonomy, adaptability• c.f. bee colonies, bird flocks, fish schools, etc.

• Approach – Apply biological concepts and mechanisms to

design network systems (i.e. application services and middleware platforms).


SymbioticSphere• SymbioticSphere is a biologically-inspired architecture for network

systems( network applications and middleware platforms)

• An application service (Agent)– is implemented by an autonomous and distributed agent.

• an agent may implement a web service and contains web pages.

• A middleware platform (Platform)– runs on a network host and operates agents.

• Each agent/platform is designed as a biological entity.– Some biological principles are applied to design agents and

platforms


Design PrinciplesDesign PrinciplesPrinciples Biological Systems SymbioticSphere

Life Cycle and Life Cycle and Food chainFood chain

Biological entities seek and consume food for living.-Reproduce (enough food) -Die (lack of food)

Agents/platforms seek and consume energy for living -Reproduce (enough energy) -Die (lack of energy)

DecentralizationDecentralization No centralize entities in biological systems.

No centralized entities to control agents/platforms

AutonomyAutonomy

Biological entities sense their local environments and autonomously invoke theirbehaviors.

Agents/platforms sense local network environments (e.g., resource availability) and autonomously invoke behaviors (e.g., migration replication, death)

EvolutionEvolutionBiological entities evolve so that the entities that fit betterto the environment become more abundant

Agents/platforms evolve their genes (i.e., behavior policies).Agents/platforms that have effective behavior policies become abundant


Energy Exchange

• Human users = the sun• have unlimited amount of

energy.• Agents = producers

( e.g. shrubs)• gain energy from users• pay some of its energy

level to platforms to utilize resources

• Platforms = consumers(e.g. hares)

• gain energy from agents• periodically evaporate

some of its energy level.


Migrate

Replicate

Die

Reproduce

Replicate

Die

Reproduce

Agent

Platform

Host

Agents and PlatformsAgent:- Energy level- Service (e.g., web pages)- Behaviors*(reproduction, replication, migration, death)**- Behavior policies

Platform:- Energy level- Middleware services- Behaviors*(reproduction, replication, death)**- Behavior policies

*When an agent/platform invokes a behavior, it pays energy.

** replication is a special case of reproduction. Replications happens when an agent/platform cannot find a mate to invoke reproduction.


Behavior Policy

• Each agent/platform has its own policy for each behavior.• A behavior policy

defines when to and how to invoke a particular behavior.

• A behavior policyconsists of factors (Fi), which evaluate environment conditions.

• Each factor is given a weight (Wi) relative to its importance.

• A behavior is invoked if the weighted sum of its factor values exceeds a threshold.

• Agents/Platforms periodically check weighted sum to invoke behaviors

Factor ( F1 )

Factor ( F2 )

Factor ( Fn)

..

..

..

Threshold Invoke behavior or not

w1

w2

w

?ThresholdFWi

ii >∑Factor ( F1 )

Factor ( F2 )

Factor ( Fn)

..

..

..

Threshold Invoke behavior or not

w1

w2

wn

?Thresholdi

ii >∑


Agent Behavior Policy• Factors in agent reproduction behavior

1. Energy Level: ( the agent energy level )• encourages agents to reproduce their

offspring in response to their high energy level.

2. Request Queue Length:• The length of a queue, which the local platform

stores incoming service request to. • encourages agents to reproduce their offspring

in response to high demands for their services.

When the weighted sum of the factors exceeds a threshold, an agent seeks a mate from the local and neighboring platforms.

If a mate is found the agent invokes the reproduction behavior. Otherwise, it invokes the replication behavior


Platform Behavior PolicyFactors in platform reproduction behavior1. Energy Level: Platform energy level

• encourages platforms to reproduce their offspring in response to higher energy level.

2. Resource Availability Ratio: The ratio of resource availability on a remote host to the local host. • encourages platforms to reproduce their offspring on

healthier neighboring hosts.

3. The Number of Agents: The number of agents working on the local platform• encourages platforms to reproduce their offspring in

response to high agent population on them

Reproduce


Constraint-aware Evolution• The weight and threshold values in behavior policies have significant

impacts on the adaptability of agents and platforms.

• It is hard to test all possible network conditions and find an appropriate set of weight and threshold values for the conditions.

There are 18 weight and threshold variables in total. Assuming that 10 different values can be assign to each variable, there are 1018

possible combinations of weight and threshold values.

• SymbioticSphere allows agents and platforms to autonomously findappropriate weight and threshold values through evolution.

• Behavior policies are encoded as genes for agents and platforms


Mating Partner• When an agent/platform wants to invoke reproduction behavior, it

finds a mate.• A mate is selected by ranking agents/platforms on the local and

neighboring hosts. A mate is the agent/platform in the first rank.• Agents/platforms are ranked with the notion of constraint

domination, which considers:– Optimization objective

• Energy Level• The total number of behavior invocations.• The resource availability of the underlying host.

– QoS constraint violation• Response Time

(e.g., repose time must be less than 1 second)• Throughput

The agent/platform that satisfies all of given constraints is said to be feasible.


Constraint Domination• Agent/platform i constraint-dominate another agent/platform j if

any of the following conditions are true.1) i is feasible, and j is not2) Both i and j are feasible but i dominates j in optimization

objective domain3) Both i and j are infeasible, but i dominates j in constraint

violation domain

Case 2 Case 3


Genetic Operations• When an agent/platform invokes reproduction behavior;

it perform genetic operations (crossover and mutation)

• If an agent/platform cannot find a mate, it invokes replication behavior and perform mutation


Simulation Configurations• A simulated network system is modeled

as a sever farm.• 7x7 grid network topology.

– 49 network hosts• Each agent implements a web service in

its body• There is one agent and one platform on

each host at the beginning of simulation.– 49 agents and 49 platforms

0

2000

4000

6000

8000

10000

0 2 4 6 8 10 12 14 16 18 20 22 24Serv

ice

Req

uest

Rat

e(#

of r

eque

sts /

min

)

Simulation time (hour)

Input:

This service request rate is taken from a workload trace of the 1998 Winter Olympic official website


Simulation Results0

2000

4000

6000

8000

10000

0 2 4 6 8 10 12 14 16 18 20 22 24Serv

ice

Req

uest

Rat

e(#

of r

eque

sts /

min

)


0

50

100

150

200

250

300

350

0 1 2 3 4 5 6 7 8 9 10

Simulation time (day)

The

num

ber o

f age

nts

0

0.5

1

1.5

2

2.5

3

3.5

0 1 2 3 4 5 6 7 8 9 10

Simulation time (day)R

espo

nse

time

(sec

)

The biologically-inspired mechanisms in SymbioticSphere allow agents to improve and maintain response time.

The biologically-inspired mechanisms in SymbioticSphere allow agents to evolve their behavior policies and adaptively adjust their availability.


Simulation Results

• The response time constraint is given:“An agent must operate a service request in 5 second.”

• After adding the response time constraint,– The average response time is 15% decreased (1.95 1.66) – The number of violations is 90% decreased (849 78)

http://dssg.cs.umb.edu/[email protected]

Thank youThank you

http://dssg.cs.umb.edu/~paskorn


Conclusion• This paper

– describes how evolution happens in SymbioticSphere and how QoS is maintained by using QoS-aware evolution.

• Simulation results show that – agents and platforms autonomously adapt to dynamic environmental

conditions (e.g., user location, network traffic and resource availability) by using their regular behaviors.

– a quality set of behavior policies can be obtained through evolution in much shorter time than trial and errors.

Future works

• Dynamic network topology• Service composition

– Multiple types of agent


Adaptability Measures• Adaptability is measured as

– Service Adaptation• Service Availability

– the number of agents• Quality of Service

– response time of agents for processing service requests from users

– Resource Adaptation• Resource availability

– the number of platforms that makes resources available for agents

• Resource efficiency– indicates how many service requests can be processed per

resource utilization of agents and platforms.


Regular Behaviors without GAInput:

Output:

Service availability (# of agents) and resource availability (# of platforms) change dynamically

0

100

200

300

400

0 2 4 6 8 10 12 14 16 18 20 22 24simulation time (hour)

The

num

ber o

f age

nts

0

10

20

30

40

50

60

The

num

ber o

f pla

tform

s# of agents# of platforms

0

2000

4000

6000

8000

10000

0 2 4 6 8 10 12 14 16 18 20 22 24Serv

ice

Req

uest

Rat

e(#

of r

eque

sts /

min

)


0

5

10

15

20

0 2 4 6 8 10 12 14 16 18 20 22 24Simulation time (hour)

0%

20%

40%

60%

80%

100%

Thro

ughp

ut (%

)Average response timeThroughput

Ave

rage

resp

onse

tim

e (s

ec)

The biological mechanisms in SymbioticSphere contribute for agents and platforms to collectively retain response time and throughput performance by adjusting their populations and locations.


R: regular behaviorsS: regular + symbiotic behaviorsG: genetic operations


Other Results• Adaptability GRIDNETS 05

Biologically-inspired mechanisms in SymbioticSphere contribute for agents and platform to adapt to various dynamic changes in network conditions (such as workload and resource availability); -- improve resource efficiency

• Scalability CIIT 05Biologically-inspired mechanisms in SymbioticSphere contribute for agents and platform to scale to large number of network hosts and user request rate.

• Power Saving and Load Balancing ICAS 06 SymbioticSphere saves nearly 50% power consumption at maximum, compared with traditional network systems

• Self Healing (Survivability) COMPSAC 06Biologically-inspired mechanisms in SymbioticSphere contribute for agents to survive network link failures (data center failures) and maintain high throughput for users.


Request Forwarding

• When a user requests a service – the user creates a request message and sends to the data center.

• When service request arrives a host. – The service daemon checks whether there is a platform and any agents working on its.

• If there is no platform, service daemon sends request msg to neighboring hosts.• If there is a platform and agents on the host

– Service request msg is placed in service request queue in the platform– A request message in the queue will be taken by an agent running on the

platform

Service daemon

Data center Network host

User access point

Platformrequest Q

agents


Migrate

Replicate

Die

Reproduce

Replicate

Die

Reproduce

Agent

Platform

Host

Agents and PlatformsAgent:- Agent ID- Energy level- Service name- Service- Behaviors- Behavior policies

Platform:- Platform ID- Energy level- Middleware services- Behaviors- Behavior policies

Agent/platforms behaviors

When an agent/platform invokes a behavior, it pays energy.

HostService daemon

platformagents SymbioticSphere service daemon

- runs on network host- handles

- platform reproduction requests- host resource availability requests

- forward service requests from users when there is no platform


Agents/Platforms Cooperation• Symbiotic behaviors are intended to augment the adaptability of agents and

platforms by allowing two species to cooperate for pursuing their mutual benefits

• Each symbiotic behavior is a sequence of regular behaviors that an agent and its underlying platform perform in order.

• There are two type of symbiotic behaviors:1) Agent-initiated symbiotic behaviors (A1 –A3)– An agent proposes the underlying platform to perform symbiotic behaviors. – The platform may accept the proposal and perform symbiotic behaviors.

2) Platform-initiated symbiotic behaviors (P1-P3)– A platform proposes the agents working on it to perform symbiotic behaviors. – The agent may accept the proposal and perform symbiotic behaviors.

• A symbiotic behavior policy is a behavior policy that each agent/platform possesses to determine whether it invokes a particular symbiotic behaviors.– when to propose/accept to perform symbiotic behaviors

[ ( Σ WSi FSi > threshold) and ( condition is true ) ]


A

Platform

An agent wants to migrate toward a user

Amigrate

Platform3

A platform replicated closer to a user

Propose

Agent-initiated symbiotic behaviors A1:

Energy for platform replication

replicate

21

4

A host close to a user

Low resource availability

- An agent wants to migrate to host that close to user but there is no platform on that host.

- A Platform has low resource availability

Condition:

Agent can migrate toward to user

-> Response time reduces

-> high chance to get energy

Platform increases resource avail.

-> reduce the chance to be crashed

1) Agent proposes to perform A1.

2) Agent gives destination host information and pays energy to let platform replicate.3) Platform replicates on the host.4) Agent migrates

Action:

Mutual Benefit:


Agent Behavior Policy

• Factors in agent migration behavior

1. Energy Level: ( the agent energy level )• encourages agents to move in response to higher energy level.

2. Service Request Ratio:• The ratio of # of incoming service requests on a remote platform to

the local platform• encourages agents to move towards users.

3. Resource Availability Ratio:• The ratio of resource availability (--CPU cycles, memory space,

etc.) on a remote host to the local host • encourages agents to move to platforms running on healthier hosts

4. Migration Interval: Time interval to perform migration• discourages agents to migrate too often


Genetic Operations• When an agent/platform invokes reproduction behavior;

it perform genetic operations (crossover and mutation)

Parent1F1

Parent2F2

d1 d2

d1/d2 = F2/f1

Offspring

Offspring

Normal distribution mutation

Symbioitc Sphere Bc Short Version

Education

agent energy level

network conditions

platforms agent

high energy level

agent behavior policy

network devices

network traffic

network host