The transition from 5G to 6G networks is driving an unprecedented densification of Radio Access Networks (RANs), resulting in increased energy demand and operational costs. Open RAN (O-RAN) architectures, which disaggregate baseband processing across commercial off-the-shelf (COTS) servers, further amplify these challenges due to the power sensitivity of the Distributed Unit (O-DU) to traffic load variations. This paper develops a nonlinear O-DU power model that captures load-dependent efficiency effects and integrates it into a dynamic core management framework, which activates or deactivates CPU cores based on instantaneous traffic demand. The effectiveness of the proposed dynamic core management framework is investigated in multi-RU O-RAN scenarios, comparing the proposed dynamic approach with a static baseline. Simulation results show that the dynamic scheme reduces energy consumption by up to 59.42% on average under light traffic, with instantaneous savings exceeding 70% during off-peak periods, while maintaining performance. These findings demonstrate that workload-aware core provisioning can deliver substantial energy efficiency gains in O-RAN deployments, particularly in lightly to moderately loaded networks.

The rapid deployment of 5 G and the anticipated evolution to 6 G have intensified the need for energy-efficient radio access networks, driven by rapidly growing power demands, rising energy costs, and environmental concerns. Open Radio Access Networks (O-RAN) offer a flexible and scalable architecture; however, their disaggregated nature requires accurate power modelling to optimise energy consumption. This paper proposes enhanced power consumption models for O-RAN that account for power efficiency gains from resource sharing across multiple radio units (O-RUs) and the offloading of highly parallel baseband processing tasks to specialised energy-efficient hardware accelerators such as ASICs, FPGAs, or GPUs. The models are used to analyse the scaling behavior of O-RUs, distributed units (O-DUs), and centralized units (O-CUs) under varying deployment scenarios. Results show that O-RUs dominate the total network power budget, while O-DUs benefit from sublinear growth due to statistical multiplexing, and O-CUs scale the slowest owing to centralised control-plane sharing. Furthermore, the study identifies optimal ranges of RU-to-DU aggregation and accelerator utilization for maximising energy efficiency in largescale $\mathbf{5 G} / \mathbf{6 G}$ O-RAN deployments.

The growing demands of$\mathbf{5 G}$and emerging$\mathbf{6 G}$mobile networks-driven by the proliferation of IoT devices, immersive applications, and high-throughput services-necessitate more efficient and scalable fronthaul solutions. Open Radio Access Networks and cloud-RAN architectures offer promising frameworks by decoupling hardware and software and enabling centralised processing. However, the fronthaul segment still faces challenges related to bandwidth inefficiency, signalling overhead, and relatively high energy consumption, particularly due to the transmission of vast numbers of small packets. Packet aggregation emerges as a viable strategy to mitigate these challenges by grouping multiple small packets into larger payloads, thereby reducing protocol overhead, improving throughput efficiency, and lowering energy consumption in the network as a whole. This paper investigates the impact of packet aggregation on both quality of service (QoS) and energy efficiency in the fronthaul of$\mathbf{5 G} / \mathbf{6 G}$mobile networks. While prior studies have examined its effects on throughput and latency, the implications for energy consumption remain underexplored. We evaluate how aggregation design parameters-such as time thresholds, size thresholds, and traffic intensity-influence performance metrics such as throughput and latency. We also propose ways to achieve an optimal trade-off between QoS and energy efficiency. Our findings offer insights into the design of energy-aware, delay-sensitive packet aggregation schemes tailored for next-generation mobile network architectures.

We address the problem of a Network Operator (NO) owning limited resources at the network edge. The NO wishes to enable advanced services, by virtualizing and allocating such resources among multiple tenants, i.e., third-party Service Providers, co-existing at the edge, with different Quality of Service (QoS) constraints. The NO applies a resource allocation policy with the objective of minimizing energy consumption via switching off non-used resources while guaranteeing tenants QoS requirements. We propose a resource allocation policy based on Markov Decision Processes (MDP). In simulation we show that our policy is able to reduce energy consumption, by turning off unused resources, while meeting heterogeneous SP requirements. Our code is available as open source.

Current architecture of many computer systems relies on dynamic allocation of a pool of resources according to workload conditions to meet specific performance objectives while minimizing cost (e.g., energy or billing). In such systems, different levels of operation may be defined, and switching between operating levels occurs at certain thresholds of system congestion. To avoid rapid oscillations between levels of service, “hysteresis” is introduced by using different thresholds for increasing and decreasing workload levels, respectively. We propose a model of such systems with general arrivals, arbitrary number of servers and operating levels where each higher operating level may correspond to an arbitrary number of additional servers and soft (i.e., non-deterministic) thresholds to account for “inertia” in switching between operating levels. In our model, request service times are assumed to be memoryless and server processing rates may be a function of the current operating level and of the number of requests (users) in the system. Additionally, we allow for delays in the activation of additional operating levels. We use simple mathematics to obtain a semi-numerical solution of our model. We illustrate the versatility of our model using several case study examples inspired by features of real systems. In particular, we explore optimal thresholds as a tradeoff between performance and energy consumption.

Cloud providers need to size their systems to determine the right amount of resources to allocate as a function of customer's needs so as to meet their SLAs (Service Level Agreement), while at the same time minimizing their costs and energy use. Queueing theory based tools are a natural choice when dealing with performance aspects of the QoS (Quality of Service) part of the SLA and forecasting resource utilization. The characteristics of a cloud center lead to a queueing system with multiple servers (nodes) in which there is potentially a very large number of servers and both the arrival and service process can exhibit high variability. We propose to use a G/G/c-like model to represent a cloud system and assess expected performance indices. Given the potentially high number of servers in a cloud system, we present an efficient, fast and easy-to-implement approximate solution. We have extensively validated our approximation against discrete-event simulation for several QoS performance metrics such as task response time and blocking probability with excellent results. We apply our approach to examples of system sizing and our examples clearly demonstrate the importance of taking into account the variability of the tasks arrivals and thus expose the risk of under- or over-provisioning if one relies on a model with Poisson assumptions.

Taxi GPS traces provide us with rich information about the human mobility pattern in modern cities. Instead of designing the bus route based on inaccurate human survey regarding people's mobility pattern, we intend to address the night-bus route planning issue by leveraging taxi GPS traces. In this paper, we propose a two-phase approach based on the crowd-sourced GPS data for night-bus route planning. In the first phase, we develop a process to cluster “hot” areas with dense passenger pick-up/drop-off, and then propose effective methods to split big “hot” areas into clusters and identify a location in each cluster as a candidate bus stop. In the second phase, given the bus route origin, destination, candidate bus stops as well as bus operation time constraints, we derive several effective rules to build bus routing graph and prune the invalid stops and edges iteratively. We further develop two heuristic algorithms to automatically generate candidate bus routes, and finally we select the best route which expects the maximum number of passengers under the given conditions. To validate the effectiveness of the proposed approach, extensive empirical studies are performed on a real-world taxi GPS data set which contains more than 1.57 million passenger delivery trips, generated by 7,600 taxis for a month in Hangzhou, China.

This study is about a prediction approach for our previous dynamic bandwidth allocation algorithm for Ethernet Passive Optical Networks (EPON). Our previous work (hcDBA) is based on half cycle timing for bandwidth allocation. That can be handled as a middle way between online and offline bandwidth allocation schemes. In PONs, prediction is used for bandwidth allocation to grant loaded nodes with early responses. However, due to the versatile nature of data traffic, prediction algorithms have a handicap to provide a better solution in classical approaches. In this study, a novel prediction approach integrated with hcDBA algorithm described. Performance comparison of hcDBA with & without prediction and IPACT algorithm is given. According to the simulation results, prediction on hcDBA seems to give some performance improvements in terms of access-delay.

Metropolitan ring networks are usually used to connect the high speed backbone networks with access networks. Until now, the metropolitan network and the access network are gained much attention of researchers. However they have been investigated in separate ways. There is no work in which the end-to-end performance from end-users of the access network to metropolitan network is evaluated. How to simulate a complete end-to-end network while keeping basic characteristics of access and metro traffic is an emergence problem to evaluate the end-to-end performance. In reality, a complete end-to-end network in which hundreds of Ethernet Passive Optical Network (EPON) are connected to metro ring networks cannot be simulated because of the huge amount of traffic generated from the access network side. In this paper, we aim to obtain trace files of incoming traffic at the entrance of Optical Line Terminal (OLT) by running simulations of an EPON network which implements Interleaved Polling with Adaptive Cycle Time (IPACT). Then, the generated traffic pattern will be characterized in order to find corresponding traffic model among well known traffic models and this model will be used as output traffic of OLTs. After, we can use this traffic model without simulating a complete EPON network. Through various simulations, we observe that the generated traffic that comes to OLT is similar to the traffic obtained with Poisson sources.

In this paper, we investigate performance analysis on queuing delay and queue length distribution of a slotted bus-based optical metropolitan area network (MAN) using fixed length packet format and a single wavelength. The studied network is a unidirectional bus on which many access nodes are connected to transmit fixed length packets to a centralized Hub node over a single wavelength. Each access node is modeled by an embedded discrete time Markov chain (EDTMC). The solution of this EDTMC allows computing the approximate probability that the next downstream access node on the bus sees the slot free. By using the recurrent analysis technique, we outline an approximate queue-length distribution as well as an approximate mean waiting time for each access node. The analytical results are finally compared with the simulation results. We have seen that the results strongly depend on the typical number of access nodes in the network. Both simulation and analytic models capture the expected behavior of mean waiting time and queue-length distribution but the difference between two models becomes more important as the transmission priority of ring node decreases.

A major challenge in the optical networking in the metropolitan area is the design of a robust and simple access scheme for building a flexible metro network. In this regard, we consider the bus-based approach of the Passive Optical Networks (PON) with the asynchronous CSMA/CA protocol. We present an enhancement of the CSMA/CA scheme, called LOCOMOTIVE, which takes benefit from the transparent nodes and unidirectional transmission of data signal on optical channel. Idea of the LOCOMOTIVE consists in creating trains of packets, where packets are glued one after another. As illustrated in this paper on simulation based results, the LOCOMOTIVE increases substantially the access protocol performance and achieves efficient utilization of network resources by minimizing the bandwidth fragmentation phenomenon. Index Terms-- Asynchronous optical CSMA/CA, variable length packet, shared bus, bandwidth fragmentation performance.

This paper presents a new access protocol addressing the problem of inefficient utilization of bandwidth and the fairness issue in metropolitan optical packet switching ring (OPSR) networks. This protocol, called Dynamic Intelligent - Medium Access Control (DI-MAC) protocol, greatly improves the performance of the OPSR network that usually employs the optical Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) protocol. The principle of DI-MAC is to intelligently space out the transmission of local packets at upstream nodes to avoid inefficient bandwidth fragmentation and, as a result, to release more bandwidth for downstream nodes. The key feature of DI-MAC is that it automatically and dynamically adjusts the gap between successive transmission of local packets, according to the change of network state (i.e., bandwidth availability, traffic variation, etc.), in order to favor the transmission of downstream nodes, and at the same time, to satisfy requirements of local clients in terms of quality of service. Our experiments shown that DI-MAC effectively simplifies the network management and optimizes the network performance; thus it promises to be a new cost-efficient access protocol for future metropolitan optical ring networks. In this paper, we explain in detail this protocol and analyze its impact on the network performance.

In this paper, we focus on the performance of asynchronous carrier sense multiple access with collision avoidance (CSMA/CA) protocol with variable packet sizes. We examine the fairness issue arising between ring nodes sharing a common data channel and show that the asynchronous CSMA/CA protocol suffers from bandwidth fragmentation and positional priority fairness problems. The paper proves that the phenomenon of bandwidth fragmentation represents the most important issue on asynchronous CSMA/CA protocol because it leads to bandwidth waste and thus increases unfairness for certain ring nodes. In this regard we explore limitations of a previous proposed solution, the so called traffic control architecture using remote descriptors (TCARD). Afterwards, we present an algorithm called Smart PACEd Transmission (SPACES) which deals with the aforementioned fairness problems. The desired scheme is based on a statistical and fully distributed mechanism to grant fair access to shared resources. As illustrated in this article SPACES alleviates performance degradation and resources underutilized while achieving fairness among ring nodes

The IP networks are faced today with difficult task of satisfying the needs of connections requiring different QoS by sharing the same physical resources, e.g. bandwidth and buffers. Buffers are a key component of packet-switched network, as they absorb burst arrivals of packets and hence reduce losses. Larger buffers can absorb larger bursts but they tend to build up high load and increase queueing delays. The traditional technique for managing delay is to set a maximum length for each buffer queue, accept packets in the queue until the maximum length is reached. Distributed computational grids depend on TCP to ensure reliable end-to-end communication between nodes across the wide area network (WAN). In the core of network (routers), it is believed that random early detection (RED) will alleviate problems related to synchronization of flows and also provide some notion of QoS by intelligent dropping. In this paper we develop simple Markovian model for the RED buffer management schemes, and use these models to quantify the benefits brought about by RED. In particular we examine the impact of RED on the loss rate and the mean delay. We analyse the transient and stationary states, using Markovian model. We show that the loss probability is the same for TCP and UDP traffics if RED algorithm is used. This loss rate of a flow going through a RED router does not depend of the burstiness of this flow, but only on the load it generates.

The sliding window (SW) mechanism is widely used for policing schemes in the frame relay network. Many performance studies have already been performed. All of them have considered the algorithmic description, the only one available till now for the SW. A queueing model is given for the SW mechanism. Its conformity to the algorithmic behaviour is proved through simulation. A diffusion approximation method is then used to resolve the queueing model. The aim of this approximation is to build up analytical equations describing the behaviour of the SW mechanism with a general input process.

An approximate method is developed to obtain the performance metrics of a flexible manufacturing system consisting of a circular conveyor and workstations placed around the conveyor. Each workstation consists of a single machine subject to breakdowns. The service, failure, and repair times are assumed to be exponentially distributed. The authors validate the results obtained by the approximate method with simulation.>