China 
Africa 
Explore chapters and articles related to this topic
Integration for Complex Consumer Robotic Systems: Case Studies and Analysis
Published in Shuzhi Sam Ge, Frank L. Lewis, Autonomous Mobile Robots, 2018
Mario E. Munich, James P. Ostrowski, Paolo Pirjanian
Dynamic reconfigurability. A resource must be located, instantiated, and activated before it becomes available to the system. After it is no longer needed, or the system shuts down, the resource must be released and its memory reallocated. For this purpose, we utilize a Resource Manager that is responsible for managing the system resources across their life cycle. The Resource Manager loads the resources based on the information provided by the resource configuration file. Resources specified in the resource configuration file are available on a need-to-use basis. If a particular portion of an application requires a set of resources at a certain point in time, the resources will be activated by the Resource Manager and provided to the application. Once the resources are not needed, the Resource Manager will deactivate them while keeping them in the list of available resources for future use. One drawback of the current implementation, however, is that dynamic and system-wide changes in the resource configuration file can only be effected by a complete shutdown and deallocation of resources, followed by a reload of the resource configuration file. Similarly, updates to the system require that the system be restarted — there is no infrastructure within ERSP for internally updating libraries.
Chip-Level Communication Services
Published in Hamidreza Ahmadian, Roman Obermaisser, Jon Perez, Distributed Real-Time Architecture for Mixed-Criticality Systems, 2018
M. Grammatikakis, H. Ahmadian, M. Coppola, S. Kavvadias, A. Mouzakitis, K. Papadimitriou, A. Papagrigoriou, P. Petrakis, V. Piperaki, M. Soulié, G. Tsamis
Memory and network bandwidth management policies can improve communication-intensive memory-bound applications running on distributed embedded multi-core systems-on-chip. In particular, memory bandwidth management schemes can allocate memory resources to applications in a fair manner, avoiding local saturation or monopoly phenomena, while network bandwidth regulation apply packet monitoring and control to avoid filling the network capacity and to utilize the available budget more efficiently. Moreover, by combining these policies with CPU bandwidth scheduling and the provided functionality by the Linux kernel, it is possible to develop a holistic approach for the system resource management.
Modeling Guidelines of FreeRTOS in Event-B
Published in Ibrahiem M. M. El Emary, Anna Brzozowska, Shaping the Future of ICT, 2017
Eman H. Alkhammash, Michael J. Butler, Corina Cristea
The components of most RTOSs are [20] Scheduler—Special algorithms that are used to schedule objects. Some of the commonly used scheduling algorithms are preemptive priority-based scheduling and round-robin scheduling. In preemptive priority-based scheduling, each task must be assigned a priority. At every clock tick, the scheduler runs the highest priority task that is ready to run. In round-robin scheduling, the tasks with equal priority get an equal share of processing time.Objects—Entities that are used by the developers to create applications for real-time embedded systems. Some object constructs are tasks, which are objects created by a developer to handle a distinct topic; queues which are used for task–task communication; and semaphores and mutexes, which are used for the synchronization between the tasks and the interrupts.Services—Operations performed by the kernels, such as task management, intertask communication and synchronization, interrupt handling, and resource management. The task management includes operations such as task creation, task deletion, task suspension, and changing task priority. Intertask communication and synchronization are mechanisms that enable information to be transmitted from one task to another such as message queues, pipes, semaphores, and mutexes. Interrupt handling are software routines used to handle interrupts; an interrupt is a signal to the microprocessor indicating that an event needs immediate attention. Resource management are kernel functions used to manage system resources such as the CPU, memory, and time.
Scheduling multimedia services in cloud computing environment
Published in Enterprise Information Systems, 2018
Yunchang Liu, Chunlin Li, Youlong Luo, Yanling Shao, Jing Zhang
Due to the increased functionality and complexity of the cloud computing system, resource failures are inevitable. Wang et al. (2014a) studied the performance of a cloud-based multimedia system using retrying for fault tolerance. The response time of the cloud-based multimedia system is modeled and the probability distribution of the response time is derived considering the effect imposed by retrying tasks in case of service failures happening. Javadi, Abawajy, and Buyya (2012) proposed a scalable hybrid Cloud infrastructure as well as resource provisioning policies to assure QoS targets of the users. The proposed policies take into account the workload model and the failure correlations to redirect users’ requests to the appropriate Cloud providers. Though the works consider the resource failure and provision reliable multimedia services for user, they ignore security or trust requirement in scheduling schema and decrease the efficiency of media task scheduling.