Mobile Cloud Computing -II

Summary

Highlights

• Mobile devices have become omnipresent with advanced capabilities yet limited resources. 📱
• Cloud computing supports heavy computational tasks through offloading. 🌥
• Ensuring reliability and managing resource dependencies are key challenges. 🤔
• Security concerns arise when utilizing third-party cloud services. 🔐
• Dynamic partitioning helps optimize application execution for energy and time efficiency. 🕒
• Frameworks like MAUI and Comet facilitate effective task distribution. 🚀
• Cloudlets can drastically reduce network latency and improve efficiency. 📡
• Offloading must consider program partitioning and execution timing for effectiveness. 🧩
• Heterogeneous networks introduce complex challenges that need careful navigation. 🛤

Key Takeaways

• Mobile Cloud Computing enhances device performance by offloading tasks to the cloud! ☁️
• Security and reliability are major challenges in mobile cloud use. 🔒
• Dynamic task partitioning is essential for optimizing energy consumption and execution time. 🔄
• Innovations like cloudlets reduce latency and improve energy efficiency. ⚡️
• Understanding heterogeneity is crucial for seamless MCC integration. 🌐

Overview

Chapters

• 00:00 - 00:30: Introduction to Mobile Cloud Computing The chapter begins with a continuation of a discussion on mobile cloud computing. It addresses the prevalence of mobile devices in today's world, highlighting their omnipresence and the evolving landscape of cloud computing. The chapter sets the stage for understanding how mobile devices integrate with cloud technologies, foreshadowing more detailed explorations of this integration.
• 00:30 - 01:00: Capabilities and Challenges of Smart Mobile Devices The chapter discusses the widespread admiration for smart mobile devices, highlighting their ability to run numerous applications efficiently. With the advancement in technology, these devices have improved capabilities, allowing them to handle more complex and data-intensive applications. The chapter also touches on the growing demand for such applications as the capabilities of devices continue to expand.
• 01:00 - 01:30: Offloading Computations to the Cloud The chapter discusses the potential of offloading computations to the cloud for enhanced performance on mobile devices. It acknowledges improvements in mobile device resources but suggests that offloading to more powerful cloud computing services could optimize performance. The cloud could handle computations that are more demanding, creating a backend service for mobile applications. The chapter hints at several challenges associated with this approach but implies that cloud computing is a crucial component in leveraging more complex computing tasks off mobile devices.
• 01:30 - 02:00: Challenges in Data Transfer and Execution Time The chapter discusses the challenges associated with data transfer and execution time in technological processes. It highlights the costs involved in terms of execution time and points out that if there is a significant delay, the process becomes impractical. Additionally, the chapter touches upon the reliability issues that arise when an application is executed in a different location.
• 02:00 - 02:30: Security Issues in Mobile Cloud Computing This chapter discusses the various security issues associated with mobile cloud computing. Key points of concern include] dependency on intermediate networks such as wireless connections, resource availability at remote ends, potential failures either in the network, resources, or the mobile device itself. The text also highlights the complexities introduced by offloading tasks, emphasizing that security concerns extend from individual devices to the broader cloud-based system. The chapter underscores the heightened need for secure processing and data transmission when applications run across distributed cloud environments.
• 02:30 - 03:00: Popularity and Benefits of Mobile Cloud Computing Popularity and Benefits of Mobile Cloud Computing delves into the rising prominence of mobile cloud computing. It discusses the concern of privacy and security issues when data and processes are maintained on premises controlled by third parties. Despite these challenges, mobile cloud computing continues to gain popularity.
• 03:00 - 03:30: Interoperability and Internet of Devices In this chapter, the focus is on the rising popularity of interoperability and the Internet of Devices, driven by several factors. First, the capability to manage large applications via small devices is highlighted. Additionally, there is an emphasis on the shared use of data, where processes may utilize data controlled by others, and operations are carried out in locations where both data and processes exist. Moreover, the chapter discusses how mobile devices can function as data collectors, contributing to central repositories or supporting processes either on the device itself or elsewhere.
• 03:30 - 04:00: Optimization and Middleware in MCC This chapter discusses the concept of interoperability and data exchange issues in the context of mobile cloud computing. It explores how the evolution of the Internet of Devices brings cloud computing into a central management role. The chapter aims to delve into various aspects of mobile cloud computing.
• 04:00 - 05:00: Static and Dynamic Task Partitioning The chapter discusses the concept of task partitioning in mobile cloud computing. It refers to research works to provide a better understanding of the challenges and possible solutions in this field. Some of the key challenges include the need for dynamic partitioning in mobile cloud environments.
• 06:00 - 07:00: MAUI Framework in Mobile Cloud Computing The chapter discusses the use of the MAUI framework within the context of mobile cloud computing, particularly focusing on optimizing energy savings and execution time for applications. It highlights the necessity of balancing execution between local resources and cloud-based services. Key considerations include maintaining energy efficiency and ensuring timely task completion, alongside the role of middleware in determining which parts of an application should be executed locally.
• 07:00 - 08:00: COMET Framework and DSM Model The chapter discusses the COMET Framework and the DSM Model, focusing on optimization problems associated with executing applications partially on local systems and remotely or in the cloud. It explains how applications can be divided into different components where some can be run locally and others remotely. This distribution can be predetermined if there is prior knowledge or determined during execution.
• 08:00 - 10:00: Task Partitioning Problems and Solutions The chapter discusses the challenges and solutions associated with task partitioning, especially in contexts where it is not initially clear whether tasks should be executed locally or remotely. The decision primarily hinges on data dependency and related factors. Therefore, a dynamic approach is necessary, which involves synchronization, sense scheduling, and resource management. These elements are crucial, especially when dealing with specific devices.
• 10:00 - 10:30: Communication and Computation Issues The chapter discusses the complexity of infrastructure in communication and computation where different components are owned and maintained by various authorities. It highlights the intricacies that arise from mobile devices and cloud services being managed by different third-party providers, each with their own set of authorities. These overlapping domains create challenging issues that need to be addressed.
• 10:30 - 12:30: Code Offloading and Cloudlets This chapter discusses code offloading and cloudlets, focusing on mobile assistance using infrastructure as outlined in a specific research paper. It introduces MAUI, a system that enables programmers to initially partition their programs by marking each method as remoteable or not, determining whether methods should be executed remotely or locally. Native methods, however, cannot be marked as remoteable.
• 12:30 - 15:00: Energy Cost Analysis in Offloading This chapter discusses the decision-making framework for offloading tasks from a device to the cloud to optimize energy consumption and execution time. It highlights the MAU framework, which uses annotation to decide whether a method should be executed on the cloud server. Key considerations include the time required to execute the task on the cloud, the time to transfer process and data, and the cloud component known as the MAU server.
• 15:00 - 18:00: Cloud Computing Efficiency and Challenges The chapter discusses the architecture and interaction between the MAU client on the mobile side and the MAU server as a cloud component. It highlights the importance of having the necessary software modules within the framework to support the workflow. It explains a client-server type of architecture where synchronization is proposed between the components. Particular components such as the app, profiler, and solver profiler are mentioned, emphasizing their roles in profiling the application and server partitions.
• 18:00 - 20:00: Offloading and Execution Time Benefits This chapter discusses the concept of offloading and the associated benefits in terms of execution time. It describes the process by which applications can be executed both locally and remotely using RPC calls. The application can run in parts on the device known as the Smart Mobile Divider (SMD) and in part on the cloud, emphasizing the synchronous communication between the server and the application. The chapter also introduces the term 'comet quad code offloading' as part of the offloading process.
• 20:00 - 21:00: Conclusion and Overall Challenges in MCC The chapter discusses a concept where execution can be migrated transparently. This means that applications can work without modification and without the need for source code changes. The migration capability allows threads to move between machines based on workload demands. This is achieved by implementing a distributed shared memory (DSM) model in the runtime engine, which facilitates the movement of threads across different machines.

Mobile Cloud Computing -II Transcription

• 00:00 - 00:30 hello ah so we will continue our discussion on cloud computing ah rather we will continue our discussion on mobile cloud computing so what we are ah discussing about mobile cloud computing said that the mobile is a mobile devices ah these days are omnipresent right
• 00:30 - 01:00 there is a huge glorification of smart mobile devices ah which has fairly good capability of doing lot of a um applications or running lot of applications as as there is a as the capability increases the ah need for running more computational and data intensive applications also ah also there is a increase in the those type of applications
• 01:00 - 01:30 now in ah though there is a increase in this resources of the mobile devices but ah what we still feel that some of the cases ah ah had it been a background backend some more computing services that could have been better like ah we execute some part here some part offload some part of the computation or data on the on the backend devices where ah what we have seen that cloud may play a important role but there are ah several issues into
• 01:30 - 02:00 the things right that any any transfer of data and processes involves costing costing in terms of execution time ah specifically that if the delay is more than something it is ah it becomes ah ah um unviable also we see that is a question of reliability when once your ah application runs ah goes to another place to run
• 02:00 - 02:30 so if there is there are a lot of dependency involves like intermediate ah network or the wireless network the ah availability of the resources at the other end or failure or fault in the other end and of course the fault in the device at the a mobile device itself so whereas when you offload all those things come into play right then we have also seen there are issues of security right so far the application running your own device so you have someone on the process and the data over it right but whenever the application
• 02:30 - 03:00 running in some other premises or some other devices or cloud which is maintained and owned by some third party then your ah there is a ah there is a concerned about privacy and other security issues the regarding those ah data and a processes so this becomes pretty tricky issue and nevertheless ah mobile cloud computing is becoming pretty
• 03:00 - 03:30 popular because of several ah reasons first of all you can now have think of a ah large application running ah on or rather controlled by a small devices there can be things that the your process may be using somebody elses data so you run somewhere where the data is there and the process is there or the mobile device acts as a collection of data which is contributing to some central repository some process at this device or some other
• 03:30 - 04:00 device can do so there is ah there are issues of in exchanging of data interoperability issue and sharing of this sort of devices right or what what we see a a evolution of this that internet of devices come into play where cloud plays as a central ah role of managing the so right so we will we will look at a some of the aspects today ah regarding a mobile cloud computing in continuous in our with
• 04:00 - 04:30 our previous lecture of mobile cloud computing and ah rather we will try to refer some of the ah some of the research works ah which will ah give us a opportunity or give us a more ah better view of how what the what this ah what are the different challenges and how to handle them and so and so forth so we will look at a mobile cloud computing as we have seen some of the key challenges are that that requires dynamic partition of
• 04:30 - 05:00 a application to optimize energy saving execution side right so two things as we mentioned earlier also one is energy saving and ah to optimize the execution time right if the time is beyond a limit then there may be ah that then that process may not be viable to run on the things also requires software or something middleware that decides ah that the app launch which parts of the application will be executed locally and which part of the application
• 05:00 - 05:30 need to be executed on the externally or remotely or in the cloud right so so its a classic optimization problem right so ah ah we can do this ah sort of ah means dividing this application into different parts some of the parts or the component of the application need to be run locally and some of the remotely this can be done statically like i have a priori knowledge of this sort of things can be done or in some cases i may
• 05:30 - 06:00 not know the a priori that which need to be ah locally or locally or remotely primarily it is if it is dependent on the data and other type of things right so what will happen i need to have a dynamic these and all the things and as as we understand whenever we need this type of thing synchronize a sense scheduling ah and the resource management come into play in a big way right so all those things here and when you are specifically doing the devices
• 06:00 - 06:30 and say infrastructure which are owned and maintained by different ah um authorities then its a more tricky so like mobile devices is something and cloud is maintained by other third party intermediate you have service provider we are who are ah again have a different type of authority so all those things makes a very ah complicated issue need to be solved
• 06:30 - 07:00 so this is one of the work is ah as referred in the in this paper there is mobile assistance using infrastructure right so it is one form of mcc so maui enables the programmer to produce an initial partition of the program so programmer marks the each method as remoteable or not that means whether a remote or local native methods cannot be ah remoteable which are
• 07:00 - 07:30 need to be done ah on the um on the device itself mau framework uses the annotate to decide whether the method should be executed on cloud server to save energy and time to execute the thing right so there are a couple of times the time to execute on the cloud there is a time to transfer this ah process and data to the cloud and get back the data if as ah if the need demands and mau server ah is a ah is a cloud component
• 07:30 - 08:00 so there is a mau client which is on the mobile side there is a mau server which is a cloud component the framework has necessary software modules required for the workflow so that that there is a client server type of architecture where ah what they propose and can be able to synchronize so if you see so there is the app and there is a profiler and the solver profiler basically profiling of the application and profile along with the server partitions
• 08:00 - 08:30 the application these gates executed here and with ah rpc calls and then it ah in a two and four things lan server ah communicate to the profile as sync among itself when the apps run in a some part on the app and some part on the some part on the device and some or what we say smart mobile divider smd and some part on the cloud right so ah there is another work which is what is called comet ah quad code offloading by
• 08:30 - 09:00 migrating execution transparently right so works on unmodified application no source code required that is on the ah app app itself allows threads to migrate between the machine depending on workload they based on the things that threads can migrate it implement a distributed memory shared memory or dsm model to runtime engine right those who have ah gone through
• 09:00 - 09:30 computer architecture or advanced computer architecture and various type of things they understand that this ah dsm model a dsm allows transparently movement of the threads across machine in computer architecture dsm is a form of memory architecture where physically separate memories can address as one logically shared address space there is the core of the or there is what we say very ah quick view on the ah what what this dsm says
• 09:30 - 10:00 so ah likewise there is a phone os and remote os so it need to maintain this memory states and there is a ah distributed memory synchronization and the executed this processes other codes are executed ah or offloaded by migrating execution transparently so it is not that ah the neither ah neither the source code is required nor that has ah nor the a user end there is known that this things are going on at the backend so what it requires only
• 10:00 - 10:30 program binaries right execute multi thread programs correctly so it does not require source code only the binaries furthermore improvement on the data traffic during migration is also possible by sending only parts of the heap that has been modified so ah it is not transmitting the whole heap but the part of the heap which has been modified so what we see the key problem to address or solve is a at the at its core mcc framework
• 10:30 - 11:00 must solve how to partition a program right or execution on heterogeneous sources thus not only partitioning it need to be executed on heterogeneous ah resources right it one on the mobile ah device side which ah may be some mobile related os when you are running on the cloud side that is some other kind of ah environment so it is a heterogeneous environment how things need to be run need to be looked into
• 11:00 - 11:30 so its a task partitioning problem ah as we have seen in other ah computer architecture and organizations widely studied in processor scheduling as a job scheduling problem also right we do have this sort of challenges out here so need to be looked into from that angle so task partitioning problems ah so what we have typically in a task partitioning problem in mcc a call graph representing the applications method ah or call sequence right so ah its
• 11:30 - 12:00 a call graph attributes of each node in the graph in ah denotes a energy consumed to execute the method on the mobile device and energy consumed to transfer the program states to the remote server so one is the energy consumed in the mobile device and transferred the things what we are considering that the other end ah that is the cloud end the it its pretty
• 12:00 - 12:30 resourceful and efficient so the energy consumes in is in executing that in the cloud end is ah negligible in compared to the um energy consumption at the this end ah ah at the device end rather the device does not much clear about that but you need to clear about that executing its own locally the portion to be executed and the transfer cost of this ah the same memory state and processes and so and so forth as as things required right and
• 12:30 - 13:00 data memory state and so on so output what we get as a partition the methods into two sets one set of the matter executes at the mobile device and the second state ah say it goes to the execute on the cloud so go if we look at the goal and constraint energy consume must be minimized so ah i need to minimize the energy ah consumption there is a limit on the execution time of the application so it should it should within the threshold
• 13:00 - 13:30 say time capital t other constant could be ah some methods must executed on the mobile device total monetary cost etcetera so two we have couple of a constant that means we need to goal is to ah reduce the energy consumption time should be within that particular threshold value and there can be other ah constant like ah some of the um thing some of the application
• 13:30 - 14:00 ah some part of the application may need to be executed in the device itself like i may not be able to offload it and i may look at the total costing of the thing the total cost should not execute some something some some portion more than that so these things are ah necessary so if we look at that ah little mathematically so we have a execution graph right out of that what we say that these are v one v four v nine
• 14:00 - 14:30 in this case are ah native task that means needs to be executed in the device itself right i cannot offload it so there can be so highlighted ah nodes here must be executed device edges represent the sequence of execution that how the sequence of execution will be there any non highlighted node can be executed either locally or on the mobile device right
• 14:30 - 15:00 can be locally or on the ah mobile device so if it is offloaded ah to the local device this first four senses that how much energy it could have saved right or in other sense had it been ah worked on the local how much energy could have been taken so that has been saved if i offload it to the ah remote but ah i need to also look at that ah where the
• 15:00 - 15:30 costing of transfer this data right so there is a cost involved or there is a energy cost involved energy expenditure involved in transferring the data from the device to the remote device right that has to be incurred by the mobile device right so that are needs to be there so if we need to maximize this so if it is if this result is a positive or the maximum of the maximum ah if you can maximize then i have a substantial energy saved otherwise
• 15:30 - 16:00 ah cannot be ah cannot be ah there the there there is no benefit of doing that right and of course ah it should be within a total execution latency should be less than l right ah we should not have this ah whatever we do need to be ah less than ah less than the um particular latency ah l right so that it should be ah should be within that particular things and
• 16:00 - 16:30 i i need to look at that a dependency also like execution of one need to be executed if there is a dependency in the graph that need to be executed out here so ah as we are discussing there are two type of ah partitioning one is static and dynamic as we have seen static in case of a static when the application is launched the invoke a ilp solver and ah which tells where each method should be executed so it says that
• 16:30 - 17:00 statically says that when it is launched so there is ah there are also heuristic to find a solution first term that ah there are ah we can deploy a in case of a dynamic or adaptive partitioning what we do for a long running program environmental conditions may vary right if it is a executing for a long time environmental condition may vary like a requirement of the data and ah ah even the ah availability of the remote resources transferring bandwidth
• 17:00 - 17:30 all those things can vary depending on the input the energy consumption of a method may vary so that means in other sense i need to i need to take a call that which partition need to be executed locally and remotely ah because of that varying nature of the things there are hosting may ah go on changing right so that is that is ah another challenge out here so there are ah as we see there are ah when we do this type of partitioning
• 17:30 - 18:00 and transfer the job executes something locally something ah ah remotely or everything within a time limit ah a particular threshold values threshold time and ah we want to maximize the energy saving right so these are the different constraint and in in order to achieve this sort of ah issues so there are ah several challenges and issues need to be addressed so mobile communication issues that is low bandwidth one of the biggest
• 18:00 - 18:30 issue because of the radio resource of the wireless network is much more scarce than the wired networks so the ah it is the availability band availability of this bandwidth mobile bandwidth or wireless bandwidth at times is pretty less ah in compared to a wired type of things or so that so that is not only the less it also varies on if it is a long running execute executive means long running process then it may vary over time
• 18:30 - 19:00 so getting a guaranteed bandwidth is a is a challenge service availability mobile user may not be able to connect to the cloud to obtain a service due to traffic congestion network failure mobile signal strength and so and so forth issue of a heterogeneity handling wireless connectivity with highly heterogeneous network to satisfy mcc requirement always on a connectivity on demand scalability energy efficiency is a difficult problem so there
• 19:00 - 19:30 are heterogeneous ah heterogeneity involved in it and there are these are different challenges so these are more issues with the communication issues there are a few computation issues or computing offloading related issues one one of the this is one of the major feature of the things like you are able to offload it offloading it not always effective in saving energy as we have seen that if those parameters
• 19:30 - 20:00 are not made then it may not be that energy saving may not be ah um ah what we say ah within that quote unquote profitable margin right so it may be costly stuff ah it is critical to determine whether to offload and which portion of the source code to offload so its its a critical challenge especially as that there are different type of application with different type of requirement etcetera and its its a major challenge to decide that ah
• 20:00 - 20:30 where when to offload how much to offload and and so and so forth so there are other trials or other ah type of a initiative one is that ah code offloading using cloudlet right so um if you look at cloudlet its a trusted resource rich computer or cluster computers that is well connected to the internet and is available for use by
• 20:30 - 21:00 nearby mobile devices so its a what we say ah we can look at as a smaller version or of cloud ah but it is resource rich but it is more within the locality of the mobile ah mobile devices or nearby regions right so offloading a code to the remote server and executing it when you look at the court code offloading part so this architecture
• 21:00 - 21:30 decrease decreases latency by using single hop network and potentially lowers battery consumption using wi fi short range radio broadband wireless etcetera so what we try to see that ah first of all of offloading and secondly when we make multiple hops then the cost increases so what you try to see that whether i can have presence of smaller clouds which can take care of this ah this sort of application ah this sort of a executing this portion of the application and if a single hop then we can have something ah more or
• 21:30 - 22:00 what we say that we can have ah more ah um the better energy saving and better response time with with having ah those resources much closer to the device so cloud ah code offloading using ah um cloudlet ah so we have a ah mobile devices mobile networks
• 22:00 - 22:30 and the remote cloud and there are if you look at there are different small small different different set of systems or mobile cloudlet and cloudlet nodes which takes care of these devices right or what we say that goal is to reduce the latency ah in reaching the cloud service ah servers use a servers that are closer to the mobile devices that means going
• 22:30 - 23:00 for instead of the full place cloud we can have smaller version of the clouds or cloudlet a cloudlet is a new architectural element or ah that arises from the convergence of mobile computing and cloud computing right it represents a middle tire of a three tier architecture like mobile devices cloudlet and cloud so that in other sense what we are trying to do in order to reduce the latency and a better energy savings possible better
• 23:00 - 23:30 energy saving in one side the cloud is there one side a devices we made a we ah make a intermediate a thing what we say cloudlet right so which ah takes care of the things now when to offload is ah again a a serious question so if we look at a very ah straightforward formulation of the things ah so if we look at that equation that so what we say ah that
• 23:30 - 24:00 pc is the energy cost per second when the mobile phone is ah doing computing that means mobile phone is computing pi is that energy cause the mobile phone is idle ptr is the ah per second a cost per second when the mobile phone is transmitting data so a it a mobile device can be either computing or idle or transmitting data so this three
• 24:00 - 24:30 component are ah pc pi or um ptr or when um energy when transmitting data now if you consider c ah as the number of instruction and m is the speed of the mobile compute the c instruction so what we see that ah ah if we see that pc c by m if it is offloaded pc c by m minus
• 24:30 - 25:00 pi c by s so what is s the speed of cloud to compute the c instruction so if it is s is the p ah ps s is the speed of the cloud then i we can see that idle pi is the idle time c there is number of instruction by the speed so this ah p by c by s and the
• 25:00 - 25:30 transmitting ptrd by b d means the total data to transmit and b is the bandwidth available so if we offload so this is my overall ballmark figure right this should be a positive number so it says that i save energy right so this was my energy consumption if i offload this consumption are not there and then then this is ah this is save of the saving of the energy
• 25:30 - 26:00 or if i say the server or the cloud server is f time faster then i can look at s equal to f into m right so that means your speed of cloud to compute c instruction and m is the speed of mobile phone to compute c instruction if it is f times faster and we can see that s equal to ah f into m right or in other we can rewrite
• 26:00 - 26:30 the ah program or rewrite that particular formula or substitute this s equal to f by m into the formula ah um to look ah to ah to basically arrive this thing c by m pc pi by f minus ptr d by b this is a very ah simple arithmetic ah you just substitute and if you take appropriate common so we we come to a figure called in this sort of scenario right
• 26:30 - 27:00 c by m equal to pc minus pi pi by f and minus tr so what we see from here that energy is saved when formula produces a positive number definitely if it is a positive then only energy is saved the formula is positive if d by a d by b is sufficiently small compared to c by m right so one side is d by b should be sufficiently
• 27:00 - 27:30 small compared to c by m so that ah um i have a ah larger number on the left side so this is ah what we say that ah this is one of the condition cloud computing so what ah cloud computing can potentially save energy from the mobile devices note that ah all application in the energy efficient when migrated to the cloud are may not be energy efficient right
• 27:30 - 28:00 so ah from this formula already say that first of all d by b should be must lesser less than c by m and f should be sufficiently higher which makes sense right f is the how many times the cloud server is faster than the mobile device it is likely that the cloud server should be sufficiently higher ah otherwise there is no point in offloading and getting executed at externally right ah if it is ah you know so if that conditions are satisfied
• 28:00 - 28:30 then what we see that we get a positive number and it is ah it is obvious that all the applications may not be always ah beneficial when you offload cloud computing service should be significantly different from the cloud services for desktop because they must offer energy savings in this case the services should consider the energy overhead for privacy security reliability data communication etcetera which we have not directly considered in this cases so its a ideally it should take care of other type of features which ah in
• 28:30 - 29:00 while calculating the things so if we ah look into different ah other way of looking at us ah same a formulae formula is that offloading is beneficial when large amount of computation c are needed with relatively small amount of data communication right so we require large amount of computation right with relatively less transmission of
• 29:00 - 29:30 data right here also as we have seen that c should be sufficiently large with d should be sufficiently small keeping ah like f must be much faster and ah do we see that it is a a thinks and we can see that ah in different scenario how things will be there right so party computation overloading there are several approaches ah you can see several research
• 29:30 - 30:00 papers also partitioning a program based on estimation of energy consumption before execution so what we say that pre ah partition estimation of the thing optimal program partitioning for offloading is dynamically calculated based on trade off between communication and computational cost at the at run time offloading scheme based on profiling information about computation time data sharing at the level of procedure calls right so at the level of procedure calls we can do so a cost graph can be generated or constructed and branch
• 30:00 - 30:30 and bound algorithm to to applied to minimize the total energy consumption of computation and total data requirement so what we what we are looking at that ah it is it is not vanilla offloading some of the things to the things so there are a lot of the ah lot of ah calculation involved as as we come back to the our previous premise that one is that your ah um energy savings should be higher need to be maximized whereas ah your latency
• 30:30 - 31:00 should be ah preserved and oh and we see that there are several other ah aspects of the components are there like security reliability fault in the server system etcetera and ah there are issues which are not directly under not and may not be a directly under the control of the cloud neither on the mobile devices which is what we say that
• 31:00 - 31:30 intermediate wireless network that also plays a things so that is there are issues of heterogeneity need to be addressed and need to be looked into a ah in a in totality it is not that isolated i offload offload something get some executed and type of things need to be looked as a in totalities so that the user at the mobile end or the user get a seamless feeling
• 31:30 - 32:00 or better ah resource utilization or better ah energy savings at that things thank you