Consider directed acyclic graph (DAG) scheduling for a large heterogeneous system, which consists of processors with varying processing capabilities and network links with varying bandwidths. The search space of possible task schedules for this problem is immense. One possible approach for this optimization problem, which is NP-hard, is to start with the best task schedule found by a fast deterministic task scheduling algorithm and then iteratively attempt to improve the task schedule by employing a general random guided search method. However, such an approach can lead to extremely long search times, and the solutions found are sometimes not significantly better than those found by the original deterministic task scheduling algorithm. In this paper, we propose an alternative strategy, termed Push-Pull, which starts with the best task schedule found by a fast deterministic task scheduling algorithm and then iteratively attempts to improve the current best solution using a deterministic guided search method. Our simulation results show that given similar runtimes, the Push-Pull algorithm performs well, achieving results similar to or better than all of the other algorithms being compared.

In this paper, we propose a novel QoS guaranteed algorithm for real-time applications in IEEE 802.15.4 protocol. The IEEE 802.15.4 standard provides a Guaranteed Time Slot (GTS) mechanism to allocate a specific duration within a superframe structure for time-critical transmissions. However, there are many weak points to support real-time applications. We suggest a new slot allocation algorithm that enables guaranteed services to be more efficient. The proposed algorithm also allocates a new guaranteed time slot dynamically to support real-time applications which have periodic messages. We evaluate the delay bounds and the throughput of the proposed scheme compared with original protocol. We then show that our proposal improves the bandwidth utilization and guarantees real-time features more strictly.

In general IP networks, addresses can be assigned to hosts manually by a network administrator or automatically by a DHCP server. Mobile ad-hoc network (MANET), which is a self-configuring network, is the union of mobile hosts that form an arbitrary topology. Most research related to the MANET assumes that host's IP address is configured, prior to the node joining the MANET. However, it is impossible that a network administrator or DHCP server configures host IP addresses in MANETs because there is no infra-structure. For this reason, a dynamic address management protocol is essential in MANETs. Thus, this paper proposes a novel self-configuring address management protocol, referred to as DAP (distributed address pool), in which IP addresses can be dynamically allocated to a newly-joined host in MANETs with no network infra-structure. In DAP, every host in a MANET has a unique IP address pool (a set of unused addresses that will be used for new joined hosts in MANETs) and address assignments are performed locally in the host. The advantage of this method is that it does not generate any broadcasting messages and, in turn, address allocation time can be significantly reduced. From our simulations, DAP showed a superior performance to a random address allocation scheme (RADA) in terms of both address allocation time and message exchange overhead.

This paper presents a hierarchical dispatcher architecture designed to efficiently schedule the execution of multiple deep neural networks (DNNs) on edge devices with heterogeneous processing units (PUs). The proposed architecture is applicable to systems where PUs are either integrated on a single edge device or distributed across multiple devices. We separate the dispatcher and scheduling policy. The dispatcher in our framework acts as a mechanism for allocating, executing, and managing subgraphs of DNNs across various PUs, and the scheduling policy generates optimized scheduling sequences. We formalize a hierarchical structure consisting of high-level and low-level dispatchers, which together provide scalable and flexible scheduling support for diverse DNN workloads. The high-level dispatcher oversees the partitioning and distribution of subgraphs, while the low-level dispatcher handles the execution and coordination of subgraphs on allocated PUs. This separation of responsibilities allows the architecture to efficiently manage workloads in both homogeneous and heterogeneous environments. Through case studies on edge devices, we demonstrate the practicality of the proposed architecture. By integrating appropriate scheduling policies, our approach achieves an average performance improvement of 51.6%, providing a scalable and adaptable solution for deploying deep learning models on heterogeneous edge systems.