SlideShare a Scribd company logo
HTENG 432
Communications Network and Design
R215817B Nyamuchengwe Kudzwai C
R213120H Mtema Ken W R
Introduction to system and performance Evaluation
System performance and evaluation in communications network design refers to
the process of assessing how effectively the system operates based on predefined
criteria and performance metrics. The goal in system and performance evaluation is
to provide the highest performance at the lowest cost. This ensures the network
meets user demands and service level agreements (SLAs).
Computer system users, network administrators, web developers and
communications network designers all take part in system performance and
evaluation. System and Performance evaluations has important role in the selection
of network and computer systems, design of systems and applications and the
analysis of existing systems.
Objectives of Performance Evaluation
- Evaluating design alternatives
- Comparing two or more systems(system selection)
- Determining the optimal value of a parameter(system tuning)
- Finding the performance bottleneck (bottleneck identification)
- Characterizing the load on the system(workload characterization)
- Determining the number of and sizes of components ( capacity planning)
- Predicting the performance of future loads (forecasting)
- System: Any Collection of hardware, software and network
- Metrics: Criteria used to analyze the performance of the system or components
- Workloads: The request made by the users of the systems
- Performance: how well a machine does a piece of work or complete an assigned task.
- Evaluations: the process of calculating the quality, importance, amount, or value of a
system.
- Modelling: the process of creating an abstract representation of a network system to
analyze, predict, and optimize its performance without needing to build or test the system
physically.
Definition of basic terms
System Performance
• System performance describes how well a network functions, typically measured using
quantitative indicators. In communication networks, this includes:
• Throughput – Actual data transmission rate.
• Latency (Delay) – Time taken for a data packet to travel from source to destination.
• Jitter – Variation in latency over time (important in voice/video).
• Packet Loss – Percentage of data packets lost during transmission.
• Error Rates – Bit Error Rate (BER) or Frame Error Rate (FER).
• Availability – Network uptime or reliability.
• Scalability – Ability to handle increasing users or data volume without degradation.
System Performance Evaluation
System evaluation is the process of testing and analyzing these performance
metrics to determine if the design goals are met.
Performance Evaluation Process
- Performance evaluation of a system can be done at different stages of systems
development.
- Systems in planning and design stage use high level models to obtain performance estimates
for alternative system configurations and alternative designs
- When system is operational the system is measured with a view to improve the
performance. Develop a validated model that can be used for performance prediction and capacity
planning.
Stages in evaluation process
- Define objectives: What are you testing for (e.g., latency under load)?
- Set benchmarks or standards: Define expected performance.
- Select evaluation method: Simulation, testing, or monitoring.
- Measure metrics: Collect data on KPIs.
- Analyze and interpret results: Identify bottlenecks or issues.
- Refine and optimize : Adjust network design or parameters
Communication nertwork and network design
Techniques for performance evaluation
Performance Measurement
This involves the measurement of data by observing the events and activities on an
existing system. The performance is measured directly on a system. There is also need to
characterize the workload placed on a system during measurement. This generally
provides the most valid results however this techniques is not very flexible. It may also
be very difficult to vary some work parameters.
Performance modelling
Key principles
Model: An abstract of the system obtained by making a set of assumptions about
how the systems work. It captures the essential characteristics of a system.
Reasons for using models: experimenting with real the real system may be too
costly, risky and disruptive to the real system operation.
Workload characterization: Captures the resources demands and intensity of the
load bought by the system.
Types of performance models
- Analytical modelling
- Simulation modelling
- Stochastic models
- Queuing models
Analytical Modeling
Analytical modelling refers to the process of using mathematical techniques and logical reasoning
to represent, analyze, and predict the behavior or performance of a system, process.
Generally mathematical methods are used to obtain solutions on the performance of a system.
Numerical results are easy to compute if a simple analytic solution is available. Analytical
modelling is useful when rough estimates are needed whereas solutions to complex models may be
difficult to obtain.
Simulation Modeling
Simulation modelling is the process of creating a computerized model of a real or hypothetical
system and then experimenting with that model to observe system behavior over time. Uses
algorithms and computational power to imitate how a system evolves. A system can be studied at an
arbitrary level of detail. However the simulation may be costly to develop and run the program.
Stochastic Modelling
Stochastic modelling design involves using probabilistic methods to represent
and analyze the behavior of networks where elements such as traffic load,
packet arrivals, delays, and failures exhibit random behavior. Output is also
random and provide probability distributions of the performance measures of
interest.
Queuing Model
A queuing model is a mathematical representation of a system where
"customers" (like data packets, processes, or users) wait in line (a queue) to
receive a service (e.g., CPU time, router forwarding, or server response).
Queuing models are widely used in computer networks to analyze and predict
system performance especially in routers, switches, servers, or entire
communication networks where delays and congestion can occur.
It the most commonly used model to analyze the performance of computer
systems and network. Single queue models a component of the overall
system such as CPU, disk or communication channel.
Network of queues models system components and their interactions.
Metrics of Performance Evaluation
In communication systems design, performance metrics are crucial to evaluate the
effectiveness, efficiency, and reliability of the system. Here are the key performance
metrics typically used:
1.Bit Error Rate (BER)
 Definition: Ratio of incorrectly received bits to total transmitted bits.
 Importance: Measures the reliability and quality of the transmission.
2.Signal-to-Noise Ratio (SNR)
 Definition: Ratio of signal power to noise power (usually in dB).
 Importance: Indicates how well the signal can be distinguished from noise.
3.Throughput
 Definition: Actual rate of successful data transmission over a channel (bps).
 Importance: Reflects the system's data handling capacity.
6. Jitter
• Definition: Variability in packet arrival time.
• Importance: Affects voice and video quality in packet-switched networks.
7.Spectral Efficiency
 Definition: Measure of data rate per unit bandwidth (bits/s/Hz).
 Importance: Key for comparing modulation and multiplexing schemes.
5.Latency / Delay
 Definition: Time taken for data to travel from sender to receiver.
 Importance: Critical for real-time communications (e.g., voice/video).
4. Bandwidth Efficiency
 Definition: Throughput per Hz of bandwidth (bps/Hz).
Importance: Indicates how effectively bandwidth is utilized
8.Power Efficiency
 Definition: Data rate achieved per unit power consumed.
 Importance: Crucial for battery-operated or energy-limited systems.
9.Packet Loss Rate
 Definition: Percentage of packets lost during transmission.
 Importance: Affects the reliability of data delivery.
10.Coverage Area / Range
 Definition: Maximum distance over which communication remains
effective.
 Importance: Important in cellular and wireless network design.
THE END

More Related Content

DOC
Cloud data management
PPT
techniques.ppt
PPTX
module 1.pptx
PDF
Lesson02 - Network Design & LAN
PDF
Lesson - 02 Network Design and Management
PDF
CS-438 COMPUTER SYSTEMS MODELING WK1LEC1-2.pdf
PPT
An Overview of Performance Evaluation & Simulation
PDF
Performance Evaluation of a Network Using Simulation Tools or Packet Tracer
Cloud data management
techniques.ppt
module 1.pptx
Lesson02 - Network Design & LAN
Lesson - 02 Network Design and Management
CS-438 COMPUTER SYSTEMS MODELING WK1LEC1-2.pdf
An Overview of Performance Evaluation & Simulation
Performance Evaluation of a Network Using Simulation Tools or Packet Tracer

Similar to Communication nertwork and network design (20)

PPTX
9. Evaluation methodology.pptx
DOCX
16 & 2 marks in i unit for PG PAWSN
PPT
PPTX
Cp7101 design and management of computer networks -network
PPT
Ch14
PPT
Cp7101 design and management of computer networks-requirements analysis 2
DOCX
Modeling & simulation in projects
PDF
Introduction to modeling_and_simulation
PDF
Introduction to modeling_and_simulation
PPT
service methodology, service description, service characteristics, performanc...
PPTX
Simulation-System Modeling and Simulation
PDF
HIGH SPEED NETWORKS
PPTX
Traffic behavior of local area network based on
PPT
Network analysis and design unite_-i.ppt
DOCX
DOTNET 2013 IEEE MOBILECOMPUTING PROJECT Model based analysis of wireless sys...
PPS
Network Design and Management
DOCX
B.Tech. Summer Training Report
PPT
Chapter 2 - Analyzing Technical Goals and Tradeoffs.ppt
PPTX
chpater 4 FOR Information techonogy students
PPT
9. Evaluation methodology.pptx
16 & 2 marks in i unit for PG PAWSN
Cp7101 design and management of computer networks -network
Ch14
Cp7101 design and management of computer networks-requirements analysis 2
Modeling & simulation in projects
Introduction to modeling_and_simulation
Introduction to modeling_and_simulation
service methodology, service description, service characteristics, performanc...
Simulation-System Modeling and Simulation
HIGH SPEED NETWORKS
Traffic behavior of local area network based on
Network analysis and design unite_-i.ppt
DOTNET 2013 IEEE MOBILECOMPUTING PROJECT Model based analysis of wireless sys...
Network Design and Management
B.Tech. Summer Training Report
Chapter 2 - Analyzing Technical Goals and Tradeoffs.ppt
chpater 4 FOR Information techonogy students
Ad

Recently uploaded (20)

PDF
Human-AI Collaboration: Balancing Agentic AI and Autonomy in Hybrid Systems
PDF
Exploratory_Data_Analysis_Fundamentals.pdf
PDF
A SYSTEMATIC REVIEW OF APPLICATIONS IN FRAUD DETECTION
PDF
Soil Improvement Techniques Note - Rabbi
PDF
Categorization of Factors Affecting Classification Algorithms Selection
PDF
R24 SURVEYING LAB MANUAL for civil enggi
PDF
III.4.1.2_The_Space_Environment.p pdffdf
PPTX
CURRICULAM DESIGN engineering FOR CSE 2025.pptx
PPTX
introduction to high performance computing
PDF
Level 2 – IBM Data and AI Fundamentals (1)_v1.1.PDF
PDF
Analyzing Impact of Pakistan Economic Corridor on Import and Export in Pakist...
PDF
Integrating Fractal Dimension and Time Series Analysis for Optimized Hyperspe...
PDF
Automation-in-Manufacturing-Chapter-Introduction.pdf
PPTX
UNIT 4 Total Quality Management .pptx
PDF
COURSE DESCRIPTOR OF SURVEYING R24 SYLLABUS
PPTX
communication and presentation skills 01
PPTX
Current and future trends in Computer Vision.pptx
PPT
introduction to datamining and warehousing
PDF
The CXO Playbook 2025 – Future-Ready Strategies for C-Suite Leaders Cerebrai...
PDF
PREDICTION OF DIABETES FROM ELECTRONIC HEALTH RECORDS
Human-AI Collaboration: Balancing Agentic AI and Autonomy in Hybrid Systems
Exploratory_Data_Analysis_Fundamentals.pdf
A SYSTEMATIC REVIEW OF APPLICATIONS IN FRAUD DETECTION
Soil Improvement Techniques Note - Rabbi
Categorization of Factors Affecting Classification Algorithms Selection
R24 SURVEYING LAB MANUAL for civil enggi
III.4.1.2_The_Space_Environment.p pdffdf
CURRICULAM DESIGN engineering FOR CSE 2025.pptx
introduction to high performance computing
Level 2 – IBM Data and AI Fundamentals (1)_v1.1.PDF
Analyzing Impact of Pakistan Economic Corridor on Import and Export in Pakist...
Integrating Fractal Dimension and Time Series Analysis for Optimized Hyperspe...
Automation-in-Manufacturing-Chapter-Introduction.pdf
UNIT 4 Total Quality Management .pptx
COURSE DESCRIPTOR OF SURVEYING R24 SYLLABUS
communication and presentation skills 01
Current and future trends in Computer Vision.pptx
introduction to datamining and warehousing
The CXO Playbook 2025 – Future-Ready Strategies for C-Suite Leaders Cerebrai...
PREDICTION OF DIABETES FROM ELECTRONIC HEALTH RECORDS
Ad

Communication nertwork and network design

  • 1. HTENG 432 Communications Network and Design R215817B Nyamuchengwe Kudzwai C R213120H Mtema Ken W R
  • 2. Introduction to system and performance Evaluation System performance and evaluation in communications network design refers to the process of assessing how effectively the system operates based on predefined criteria and performance metrics. The goal in system and performance evaluation is to provide the highest performance at the lowest cost. This ensures the network meets user demands and service level agreements (SLAs). Computer system users, network administrators, web developers and communications network designers all take part in system performance and evaluation. System and Performance evaluations has important role in the selection of network and computer systems, design of systems and applications and the analysis of existing systems.
  • 3. Objectives of Performance Evaluation - Evaluating design alternatives - Comparing two or more systems(system selection) - Determining the optimal value of a parameter(system tuning) - Finding the performance bottleneck (bottleneck identification) - Characterizing the load on the system(workload characterization) - Determining the number of and sizes of components ( capacity planning) - Predicting the performance of future loads (forecasting)
  • 4. - System: Any Collection of hardware, software and network - Metrics: Criteria used to analyze the performance of the system or components - Workloads: The request made by the users of the systems - Performance: how well a machine does a piece of work or complete an assigned task. - Evaluations: the process of calculating the quality, importance, amount, or value of a system. - Modelling: the process of creating an abstract representation of a network system to analyze, predict, and optimize its performance without needing to build or test the system physically. Definition of basic terms
  • 5. System Performance • System performance describes how well a network functions, typically measured using quantitative indicators. In communication networks, this includes: • Throughput – Actual data transmission rate. • Latency (Delay) – Time taken for a data packet to travel from source to destination. • Jitter – Variation in latency over time (important in voice/video). • Packet Loss – Percentage of data packets lost during transmission. • Error Rates – Bit Error Rate (BER) or Frame Error Rate (FER). • Availability – Network uptime or reliability. • Scalability – Ability to handle increasing users or data volume without degradation.
  • 6. System Performance Evaluation System evaluation is the process of testing and analyzing these performance metrics to determine if the design goals are met. Performance Evaluation Process - Performance evaluation of a system can be done at different stages of systems development. - Systems in planning and design stage use high level models to obtain performance estimates for alternative system configurations and alternative designs - When system is operational the system is measured with a view to improve the performance. Develop a validated model that can be used for performance prediction and capacity planning.
  • 7. Stages in evaluation process - Define objectives: What are you testing for (e.g., latency under load)? - Set benchmarks or standards: Define expected performance. - Select evaluation method: Simulation, testing, or monitoring. - Measure metrics: Collect data on KPIs. - Analyze and interpret results: Identify bottlenecks or issues. - Refine and optimize : Adjust network design or parameters
  • 9. Techniques for performance evaluation Performance Measurement This involves the measurement of data by observing the events and activities on an existing system. The performance is measured directly on a system. There is also need to characterize the workload placed on a system during measurement. This generally provides the most valid results however this techniques is not very flexible. It may also be very difficult to vary some work parameters.
  • 10. Performance modelling Key principles Model: An abstract of the system obtained by making a set of assumptions about how the systems work. It captures the essential characteristics of a system. Reasons for using models: experimenting with real the real system may be too costly, risky and disruptive to the real system operation. Workload characterization: Captures the resources demands and intensity of the load bought by the system. Types of performance models - Analytical modelling - Simulation modelling - Stochastic models - Queuing models
  • 11. Analytical Modeling Analytical modelling refers to the process of using mathematical techniques and logical reasoning to represent, analyze, and predict the behavior or performance of a system, process. Generally mathematical methods are used to obtain solutions on the performance of a system. Numerical results are easy to compute if a simple analytic solution is available. Analytical modelling is useful when rough estimates are needed whereas solutions to complex models may be difficult to obtain. Simulation Modeling Simulation modelling is the process of creating a computerized model of a real or hypothetical system and then experimenting with that model to observe system behavior over time. Uses algorithms and computational power to imitate how a system evolves. A system can be studied at an arbitrary level of detail. However the simulation may be costly to develop and run the program.
  • 12. Stochastic Modelling Stochastic modelling design involves using probabilistic methods to represent and analyze the behavior of networks where elements such as traffic load, packet arrivals, delays, and failures exhibit random behavior. Output is also random and provide probability distributions of the performance measures of interest. Queuing Model A queuing model is a mathematical representation of a system where "customers" (like data packets, processes, or users) wait in line (a queue) to receive a service (e.g., CPU time, router forwarding, or server response). Queuing models are widely used in computer networks to analyze and predict system performance especially in routers, switches, servers, or entire communication networks where delays and congestion can occur. It the most commonly used model to analyze the performance of computer systems and network. Single queue models a component of the overall system such as CPU, disk or communication channel. Network of queues models system components and their interactions.
  • 13. Metrics of Performance Evaluation In communication systems design, performance metrics are crucial to evaluate the effectiveness, efficiency, and reliability of the system. Here are the key performance metrics typically used: 1.Bit Error Rate (BER)  Definition: Ratio of incorrectly received bits to total transmitted bits.  Importance: Measures the reliability and quality of the transmission. 2.Signal-to-Noise Ratio (SNR)  Definition: Ratio of signal power to noise power (usually in dB).  Importance: Indicates how well the signal can be distinguished from noise. 3.Throughput  Definition: Actual rate of successful data transmission over a channel (bps).  Importance: Reflects the system's data handling capacity.
  • 14. 6. Jitter • Definition: Variability in packet arrival time. • Importance: Affects voice and video quality in packet-switched networks. 7.Spectral Efficiency  Definition: Measure of data rate per unit bandwidth (bits/s/Hz).  Importance: Key for comparing modulation and multiplexing schemes. 5.Latency / Delay  Definition: Time taken for data to travel from sender to receiver.  Importance: Critical for real-time communications (e.g., voice/video). 4. Bandwidth Efficiency  Definition: Throughput per Hz of bandwidth (bps/Hz). Importance: Indicates how effectively bandwidth is utilized
  • 15. 8.Power Efficiency  Definition: Data rate achieved per unit power consumed.  Importance: Crucial for battery-operated or energy-limited systems. 9.Packet Loss Rate  Definition: Percentage of packets lost during transmission.  Importance: Affects the reliability of data delivery. 10.Coverage Area / Range  Definition: Maximum distance over which communication remains effective.  Importance: Important in cellular and wireless network design. THE END