An Optimal Resource Allocation in 5G Environment Using Novel Deep Learning Approach

Optimal container resource allocation in cloud architecture: A new hybrid model

We study the problem of admission control and resource (subcarriers, power and bit-loading) allocation in a heterogeneous OFDMA wireless network serving both QoS-constrained high-priority users and best-effort users. By clustering subcarriers, efficient algorithms for cluster and power allocation have been proposed. Our strategy maximizes the total network utility of the best-effort users while satisfying the QoS request for maximum number of high-priority users. We approximate best-effort user utility function as a piece-wise linear function and propose a linear programming based cluster allocation algorithm. The feasibility of the resource allocation problem depends on the number of HP users in the network. Since a large number of demanding HP users would render the resource allocation problem infeasible, a joint admission control and resource allocation scheme could be an efficient way of tackling both problems with less overhead. By incorporating admission control, we propose an efficient and optimal joint admission control and resource allocation algorithm.

The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former’s capabilities and battery lives. In a multiuser system, the joint allocation of communication-and-computation (C2) resources (i.e., scheduling and bandwidth allocation) is made challenging by adopting efficient inference techniques, batching and early exiting, and further complicated by the heterogeneity in users’ requirements on accuracy and latency. Batching groups multiple tasks into a single batch for parallel processing to reduce time-consuming memory access and thereby boosts the throughput (i.e., completed task per second). On the other hand, early exiting allows a task to exit from a deep-neural network without traversing the whole network, thereby supporting a tradeoff between accuracy and latency. In this work, we study optimal C2 resource allocation with batching and early exiting, which is an NP-complete integer programming problem. A set of efficient algorithms are designed under the criterion of maximum throughput by tackling the challenge. First, consider the case with batching but without early exiting. The target problem is solved optimally using a proposed best-shelf-packing algorithm that nests a threshold-based scheme, which selects users with the best channels and meeting the computation-time constraints, in a sequential search for the maximum batch size. Next, consider the general case with batching and early exiting. A low-complexity sub-optimal algorithm for C2 resource allocation is developed by modifying the preceding algorithm to exploit early exiting for latency reduction. On the other hand, the optimal approach is developed based on nesting a depth-first tree-search with intelligent online pruning into a sequential search for the maximum batch size. The key idea is to derive pruning criteria based on the simple greedy solution for the target problem without a bandwidth constraint and apply the result to designing an intelligent online pruning scheme. Experimental results demonstrate that both optimal and sub-optimal C2 resource allocation algorithms can leverage integrated batching and early exiting to double the inference throughput compared with conventional schemes.

Implementing the dynamic couple of searching paths and resource allocation becomes increasingly important in the research of Quality of Service (QoS) routing. In this paper, we formulate the problem of dynamic QoS routing with resource allocation based on Worst-case Fair Weighted Fair Queuing (WF2Q) packet scheduling style. We propose an algorithm using the proved results -- the optimal path resource allocation algorithm (OPRA2), which can allow intelligent choice of the maximized reliability and minimized delay path according to the types of applications and adapt QoS parameters and allocated resources related to WF2Q in process of routing. It can find an optimal path which satisfies different QoS requirements and compute the amount of bandwidth and buffer resources needed at each node. We provide the simulation results to illustrate the effect of buffers and bandwidths according to the values of control parameters.

The crowd-creation space is a manifestation of the development of innovation theory to a certain stage. With the creation of the crowd-creation space, the problem of optimizing the resource allocation of the crowd-creation space has become a research hotspot. The emergence of cloud computing provides a new idea for solving the problem of resource allocation. Common cloud computing resource allocation algorithms include genetic algorithms, simulated annealing algorithms, and ant colony algorithms. These algorithms have their obvious shortcomings, which are not conducive to solving the problem of optimal resource allocation for crowd-creation space computing. Based on this, this paper proposes an In the cloud computing environment, the algorithm for optimizing resource allocation for crowd-creation space computing adopts a combination of genetic algorithm and ant colony algorithm and optimizes it by citing some mechanisms of simulated annealing algorithm. The algorithm in this paper is an improved genetic ant colony algorithm (HGAACO). In this paper, the feasibility of the algorithm is verified through experiments. The experimental results show that with 20 tasks, the ant colony algorithm task allocation time is 93ms, the genetic ant colony algorithm time is 90ms, and the improved algorithm task allocation time proposed in this paper is 74ms, obviously superior. The algorithm proposed in this paper has a certain reference value for solving the creative space computing optimization resource allocation.

Optimal resource allocation across related channels

We present a novel hybrid algorithm for optimal resource allocation for scheduling tasks that satisfy a variety of diverse constraints. The problem is pitched in geometrical domain and has direct application to several areas including, and not limited to physical resource allocation, crowd sourcing and distributed/cloud computing. The fundamental problem is to complete a set of N tasks at geographically separate locations in a two-dimensional plane where each task takes a fixed duration, requires certain number resources and must be completed within a specified time window. The goal is to maximize the profit by efficient utilization of resources and reducing the cost of movement between locations and waiting at each location. In this paper, we propose multiple strategies with each one progressively better than the previous. The main contribution of the paper is the novel hybrid algorithm that combines the traditional greedy approach with chunk allocation and random tie-breaking scheme to achieve maximal profit by efficient resource allocation.

Fog Computing (FC) paradigm offers significant potential for hosting diverse delay-sensitive Internet of Things (IoT) applications. However, the limited resources of fog devices pose significant challenges for deploying multiple applications, particularly in heterogeneous and dynamic IoT scenarios, due to the absence of effective mechanisms for resource estimation and discovery. An efficient resource allocation strategy is crucial for meeting the Quality of Service (QoS) requirements of IoT applications while enhancing overall system performance. Identifying the optimal allocation strategy for IoT applications with multiple QoS parameters is a complex and computationally intensive challenge, classified as an NP-complete problem. This paper proposes a Multi-Objective Optimization Algorithm (MOOA) for optimal resource allocation using the Osprey Optimization Algorithm (OOA) to efficiently allocate available resources. The proposed algorithm was evaluated against existing approaches, including the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), under varying task loads ranging from 100 to 500 tasks. The simulation results demonstrate significant performance improvements, including an average reduction in execution time by 12.45% compared to PSO and 22.97% compared to GA, response time by 32.57% compared to GA and 24.45% compared to PSO, and completion time by 44.39% compared to GA and 33.23% compared to PSO. These findings highlight the proposed algorithm’s ability to efficiently handle task allocation in dynamic FC environments and its potential to address complex QoS requirements in real-world IoT applications.

In this paper, we consider the saturation problem in the 3GPP LTE cellular system caused by the expected huge number of machine‐type communication (MTC) devices, leading to a significant impact on both machine‐to‐machine (M2M) and human‐to‐machine H2H traffic. M2M communications are expected to dominate traffic in LTE and beyond cellular networks. In order to address this problem, we proposed an advanced architecture designed for 5G LTE networks to enable the coexistence of H2H/M2M traffic, supported by different priority strategies to meet QoS for each traffic. The queuing strategy is implemented with an M2M gateway that manages four queues allocated to different types of MTC traffic. The optimal radio resource allocation method in LTE and beyond cellular networks was developed. This method is based on adaptive selection of channel bandwidth depending on the QoS requirements and priority traffic aggregation in the M2M gateway. Additionally, a new simulation model is proposed which can help in studying and analyzing the mutual impact between M2M and H2H traffic coexistence in 5G networks while considering high and low priority traffics for both M2M and H2H devices. This simulator automates the proposed method of optimal radio resource allocation between the M2M and H2H traffic to ensure the required QoS. Our simulation results proved that the proposed method improved the efficiency of radio resource utilization to 13% by optimizing the LTE frame formation process.

As one of the most important communication scenarios in the coming fifth generation (5G) cellular networks, ultrareliable and low-latency communication (URLLC) is promising to enable real-time wireless control systems. However, one of the biggest challenges is that how to integrate URLLC and control performance together to maximize the overall system performance. In this paper, we investigate the resource allocation for URLLC uplink in real-time wireless control systems. Specifically, we first discuss the relationship between communication and control performance. Based on that, we convert the hybrid co-design problem into a regular wireless resource allocation problem. Then, we propose an iteration algorithm to obtain the optimal wireless resource allocation. Simulation results indicate the performance of our method.

Teaching resources in higher education are an important part of the talent cultivation system of higher education institutions. Dynamic management and optimal allocation of teaching resources are the focus of the construction of each school, which reflects the teaching, research, and management level of the school to a certain extent. In this paper, after combining the current situation and management problems of teaching resources in six schools in City A and putting forward constructive opinions, we further use data envelopment analysis to study the efficiency of teaching resource allocation in School H in City A and put forward the method of resource optimization.The input redundancy rate of School X1 in School H during the three years of 2021-2023 is 30.25%, 44.15%, and 55.26%, respectively. The data shows that the school has an excess of teacher inputs and there is a shortage of resources for teachers. For the current dynamic management and resource allocation problems of teaching resources in A city school, this paper argues that the management of school teaching resources is a long-term and complex organic whole, and needs to be reformed in terms of structure, resource integration and management, and to construct a high-quality and efficient management model. In terms of resource optimization and allocation, schools can optimize the talent resource allocation mechanism and other aspects to promote the full allocation of teaching resources in higher education.

Cooperative dynamic free-space optical (FSO) networks exploit the fact that atmospheric losses are distance dependent to enhance the performance of FSO networks. This enhancement is achieved by sharing the resources of shorter links among different nodes in the network. In this paper, two joint transceiver placement and resource allocation schemes are proposed to optimally place FSO redundant transceivers based on optimal resource allocation in cooperative dynamic FSO networks. Specifically, one scheme increases reliability and capacity, while the other increases reliability and fairness of cooperative dynamic FSO networks during severe weather conditions. The schemes are formulated as multi-objective and bi-level integer linear programming problems and solved using an exhaustive search to obtain optimal solutions. The numerical results reveal that higher reliabilities can be achieved with enhanced capacities and fairness using the first and second schemes, respectively. Furthermore, these improvements are achieved by using many fewer numbers of FSO redundant transceivers than those of random placement.

Sparse resource allocation to shape a network dynamical process is studied. Specifically, we consider allocating limited distributed control resources among a subset of a network's nodes, to minimize the dominant eigenvalue of a linear dynamical spread process associated with the network. Structural characterizations of the closed-loop dynamics at the optimum are obtained. These results are then used to 1) develop constructive algorithms for optimal resource allocation, 2) identify limits on the control performance, and 3) understand the relationship between the network's graph and the optimal resource profile. While the focus here is on a simplified linear model, an exploratory study of the design's applicability to realistic stochastic and nonlinear spread processes is undertaken, via simulation examples. As a whole, this study advances a research thrust on disease spread control in networks, toward the realistic paradigm that control resources can only be allocated at a subset of network locations.

One of the drawbacks of an orthogonal frequency division multiplexing (OFDM) system is the larger peak to averaged power ratio (PAPR). The PAPR reduction scheme is a complicated problem, especially when a resource allocation is considered jointly. In this paper, a joint algorithm for determining an optimal resource allocation with PAPR awareness is proposed. Firstly, an adaptive tone reservation assignment is performed by optimally choosing a group of subcarriers, whose channel gains are sufficiently high, to be the data subcarriers and the remaining subcarriers will be used as the reserved tones for reducing PAPR to the desired level. Secondly, an adaptive power adjustment for PAPR reduction technique is introduced for determining the allocated power of data subcarriers by using the water-filling approach with the joint PAPR and capacity constraints. By using the proposed joint algorithm, the PAPR threshold level is satisfied while the desired capacity could be achieved. From the results, the proposed algorithm achieves the better results comparing with a conventional partial transmit sequence (PTS) technique and the tone reservation (TR) technique in terms of PAPR, and probability of error performances, in which the side information is not required, in contrast with the other techniques.

Multiple-input multiple-output (MIMO) wireless communication systems in combination with orthogonal frequency division multiple access and space division multiple access are flexible, spectrally efficient and of high capacity. These systems can allocate frequency, time, and space resources adaptively among mobile stations. Optimal resource allocation (RA) for maximizing the sum rate is usually too complex for practical applications, hence suboptimal algorithms are required. The performance of RA algorithms are degraded due to imperfections in channel state information at transmitter (CSIT). Thus, techniques that make the RA algorithm, robust against CSIT errors are favorable. In this paper, two novel suboptimal grouping algorithms are introduced that are shown to achieve better sum rate-complexity and fairness-complexity performances. A novel index is proposed to measure the efficiency of RA algorithms, which takes into account sum rate and complexity simultaneously. Moreover, the effect of erroneous CSIT on sum rate is investigated and it is shown that performance of the proposed RA algorithms with erroneous CSIT are superior to the existing schemes. Finally, fairness performance of the proposed RA algorithms are evaluated, which are shown to be the same if not superior to other existing algorithms.