Average Network Research Articles

Fast and Accurate NoC Latency Estimation for Application-Specific Traffics via Machine Learning

Latency is one of the critical performance metrics for Networks-on-Chips (NoCs). When designing an NoC, the designers have to explore enormous design parameters and various traffic patterns, thus a fast and accurate latency estimator is essential to explore the large design space. In this paper, we present an ideal neural network-based methodology for latency estimation in NoCs, especially for application-specific traffics. By inputting the sequence of extracted traffic features and NoC parameters, the neural network model will infer the corresponding average network latency in a fast while accurate way. Instead of training one neural network model for each benchmark from scratch, we adopt transfer learning to train the network model for a new benchmark from another trained one. Experimental results on a set of widely used application-specific NoC benchmarks show that, our method can achieve an average estimation accuracy of 95%, and a 17.1X speedup for large NoCs compared to BookSim2 simulations. Our method can also achieve 20% to 70% improvement in accuracy over the other state-of-art machine learning-based works.

Maximizing wireless sensor network lifetime through energy-efficient routing

Wireless sensor networks (WSNs) are an emerging technology that has the potential to transform the way agricultural farms operate. However, deploying WSNs in agricultural farms presents a unique set of challenges. Limited coverage area, power source availability, data collection and processing, environmental factors, cost, and integration with existing systems are some of the potential problems that need to be addressed when deploying WSNs in agricultural farms. Hence, in this work, we have proposed a method for increasing the lifetime of the sensor network which will help also help to reduce the energy. The proposed method has been evaluated in terms of network lifetime of the sensor nodes, routing and communication overhead. The results have been compared with the existing M-LEACH method and the results show that there is an enhancement of 79.02% for average network lifetime. The results also show that the proposed method reduces the average routing and communication overhead by 49.17% and 38.37% respectively.

Predictive Modeling of Indoor Environmental Parameters for Assessing Comfort Conditions in a Kindergarten Setting.

People tend to spend the majority of their time indoors. Indoor air properties can significantly affect humans' comfort, health, and productivity. This study utilizes measurement data of indoor conditions in a kindergarten in Sofia, Bulgaria. Autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) recurrent neural network (RNN) models were developed to predict CO2 levels in the educational facility over the next hour based on 2.5 h of past data and allow for near real-time decision-making. The better-performing model, LSTM, is also used for temperature and relative humidity forecasting. Global comfort is then estimated based on threshold values for temperature, humidity, and CO2. The predicted R2 values ranged between 0.938 and 0.981 for the three parameters, while the prediction of global comfort conditions achieved a 91/100 accuracy.

A forecasting approach for hospital bed capacity planning using machine learning and deep learning with application to public hospitals

Hospital Bed Capacity (HBC) planning affects economic and social sustainability in healthcare through bed capacity efficiency and medical treatment accessibility. Conventionally, this problem is solved using programming or simulation models with assumptions and limits. Forecasting the HBC using time series data on bed occupancy has been considered but not with factors such as the Number of Hospitalized Patients (NHP) and patient’s length of stay (LOS). This study proposes a data-driven methodology to forecast the HBC using Machine Learning (ML) and Deep Learning (DL). The LOS classification is performed using several ML techniques, including the Bayesian network, K-nearest neighbor, support vector machine, decision tree, and Linear regression. Also, the seasonal autoregressive integrated moving average, linear regression and Long short-term memory neural network are applied for the NHP forecasting. The forecasting and descriptive analysis outputs based on LOS classes are directly applied to a simple mathematical model to predict the required bed capacity. This methodology is applied in a case study in a heart ward at a public hospital. The data set includes 51231 records, and ML and DL algorithms are developed in Python. Results show that the heart ward’s bed capacity must be raised from 45 to 137 by 2026. In addition, several managerial recommendations are formulated.

Tourists’ Perception and Influence Factors in Virtual Tourism Using Bayesian Sentimental Analysis Model in Vietnam Based on e WOM for Sustainable Development

Objective: The advancement of Internet technology brought up the tourism industry towards new development and opportunities. With application of the Internet technology tourism industry comprises a vast range of virtual communities such as Trip Advisor, Agoda, Travelocity and so on. Existing research concentrated on evaluating the factors influencing virtual communities’ behaviour with limited evaluation of tourist perception. This paper focused on examining the tourists' perception of a virtual tour through the sentimental analysis model based on eWOM for sustainable development. Method: The developed model comprises the group average Bayesian network with the computation of the polarity of the tourist perception. A Bayesian network is a data-driven method involved in estimating dependence among the variable with probabilistic computation. Results: The analysis is based on data collected from sample population in Vietnam with consideration of the 11 variables. Participation intensity, social identity, functional value, emotional value, sharing, interaction, and user satisfaction are among eleven primary variables that have been chosen. Conclusions: The analysis of the results expressed that the user satisfaction level is based on the user's experience and functional value. Additionally, the analysis stated that social value comprises the intermediary role in virtual tourism. This research adds to research methodologies of user engagement methods as well as serves as a reference for theoretical research and management practise in the virtual tourist community.

Robust Energy-Efficient Transmission for Cell-Free Massive MIMO Systems with Imperfect CSI

In this paper, we investigate a long-term power minimization problem of cell-free massive multiple-input multiple-output (MIMO) systems. To address this issue and to ensure the system queue stability, we formulate a dynamic optimization problem aiming to minimize the average total power cost in a time-varying system under imperfect channel conditions. The problem is then converted into a real-time weighted sum rate maximization problem for each time slot using the Lyapunov optimization technique. We employ approximation techniques to design robust sparse beamforming, which enables energy savings of the network and mitigates channel uncertainty. By applying direct fractional programming (DFP) and alternating optimization, we can obtain a locally optimal solution. Our DFP-based algorithm minimizes the average total power consumption of the network while satisfying the quality of service requirements for each user. Simulation results demonstrate the rapid convergence of the proposed algorithm and illustrate the tradeoff between average network power consumption and queue latency.

A Task-Oriented Hybrid Routing Approach based on Deep Deterministic Policy Gradient

With the development of communication and transmission technologies, the applications of Internet of Things (IoT) and telemedicine are increasingly sensitive to network latency. To meet this urgent demand, learning-based routing approaches emerge, with better performance and higher flexibility. These routing approaches can be divided into single-path and multipath, which have lower transmission delay and better load balancing respectively. However, the traffic scheduling policy is not only affected by the network states but also needs to consider the requirements for traffic tasks. We propose a Task-Oriented Hybrid Routing Approach (TOHRA) based on Deep Deterministic Policy Gradient (DDPG) in Software-Defined Networking (SDN). First, the hybrid routing optimization algorithm comprehensively considers the network states and task requirements, and outputs a task-oriented hybrid routing that combines the advantages of single-path and multipath. Moreover, we design a hop-by-hop traffic segmentation model based on DDPG to output the traffic segmentation ratio on hybrid routing to adapt to the changing transmission path. Experimental results show that TOHRA achieves the best performance of load balancing and network throughput. Especially in the case of Type C tasks in Germany topology, the average network throughput of THORA is increased by 32.86%, and the average variance of link load rate is reduced by 46.62%.

Research on Public Air Route Network Planning of Urban Low-Altitude Logistics Unmanned Aerial Vehicles

As urban populations continue to grow and road traffic congestion worsens, traditional ground logistics has become less efficient. This has led to longer logistics times and increased costs. Therefore, unmanned aerial vehicle (UAV) logistics has become increasingly popular. However, free-planned routes cannot meet the safety and efficiency requirements of urban airspace mobility. To address this issue, a public air route network for low-altitude logistics UAVs needs to be established in urban areas. This paper proposes a public route network planning method based on the obstacle-based Voronoi diagram and A* algorithm, as follows: Firstly, construct a city airspace grid model in which the characteristics of the airspace are mapped onto the grid map. Introduce an obstacle clustering algorithm based on DBSCAN to generate representative obstacle points as the Voronoi seed nodes. Utilize the Voronoi diagram to establish the initial route network. Then, conduct an improved path planning by employing the A* algorithm for obstacle avoidance in route edges that pass through obstacles. To ensure the safe operation of drones, set constraints on the route safety interval. This process will generate a low-altitude public air route network for urban areas. After considering the flight costs of logistics UAVs at different altitudes, the height for the route network layout is determined. Finally, the route network evaluation indicators are established. The simulation results demonstrate that compared with the city road network planning method and the central radial network planning method, the total route length is shortened by 7.1% and 9%, respectively, the airspace coverage is increased by 9.8% and 35%, respectively, the average network degree is reduced by 52.6% and 212%, respectively, and the average flight time is reduced by 19.4s and 3.7s, respectively. In addition, by solving the network model using the Dijkstra algorithm, when the energy cost and risk cost weights are 0.6 and 0.4, respectively, and the safety interval is taken as 15 m, the total path cost value of the planned trajectory is minimized.

An improved reconfiguration algorithm for handling 1-point NoC failures

In today’s world, the demands for high-performance computing necessitate faster on-chip communication. Current chips with a large number of on-chip elements need an efficient alternative such as network-on-chip (NoC) for on-chip communication. As technology down scales toward the deep sub-micron, process variability makes the transistors more unreliable. Hence, on-chip elements including NoC can suffer from permanent/transient failures. In an NoC, 1-link/1-router failure can disrupt overall connectivity. The paper presents an improved routing reconfiguration algorithm for handling all 1-point permanent failures in 2D mesh NoC. By 1-point failure, we mean a failure can be occurred on any network link/router. State-of-the-art approaches either require a large number of reconfiguration cycles or provide partial support for 1-point failures, i.e., cover only 1-link failures. Proposed approach performs partial reconfiguration of routing function implemented using logic-bits instead of costly routing tables, thus reducing hardware overheads for larger networks as well. In terms of performance, the average flit latency cycles are reduced up to 31% and the average network throughput is improved up to 14.5% for 1-router failure in 8 × 8 2D mesh NoC. For 2-router failures, the improvements are 20% and 13% in terms of average flit latency cycles and average network throughput, respectively.

FlexDATE: Flexible and Disturbance-Aware Traffic Engineering With Reinforcement Learning in Software-Defined Networks

Traffic Engineering (TE) is an important network operation that routes/reroutes flows based on network topology and traffic demands to optimize network performance. Recently, new emerging applications pose challenges to TE with dynamic network conditions, where frequent routing updates are required to maintain good network performance with Software-Defined Networking (SDN). However, flow rerouting operations could lead to considerable Quality of Service (QoS) degradation and service disruption, which is often neglected by existing TE solutions. In this paper, we apply a new QoS metric named network disturbance to measure the negative impact of flow rerouting operations performed by TE. To achieve near-optimal load balancing performance and mitigate network disturbance together in dynamic network scenarios, we propose a flexible and disturbance-aware TE solution called that combines Reinforcement Learning (RL) and Linear Programming (LP). Specifically, leverages RL to intelligently identify flexible numbers of critical flows for each traffic matrix and reroutes these critical flows based on LP optimization to improve network performance with low disturbance. Empowered by a customized actor-critic architecture coupled with Graph Neural Networks (GNNs), can generalize well to unseen traffic scenarios and remain resilient to single link failures. Extensive simulations are conducted on five real-world network topologies to evaluate with real and synthetic traffic traces. The results show that can achieve the performance target (i.e., 90% of optimal performance) in 99% of network scenarios and effectively mitigate the average and maximum network disturbance by up to 9.1% and 38.6%, respectively, compared to state-of-the-art TE solutions.

Making Home: The Role of Social Networks on Identity, Health, and Quality of Life Among Rural Lesbian and Gay Older Adults.

Gay and lesbian older persons face a host of health inequalities related to their identity as they age. Challenges to health access and appropriate social support may be even more exacerbated for those living in rural environments; this may be due to the lack of supportive and affirming social connections. This project aimed to explore and describe the social networks and the relationship of these social networks to identity, health, and quality of life of gay and lesbian individuals in rural communities. Social network data on network type, size, and social capital were collected and supplemented by quantitative questionnaires relating to health, quality of life, marginalization, and identity. Participants (N = 25) were recruited from three states. Thirteen participants self-identified as gay and 12 as lesbian. All but one identified as non-Hispanic White. The average age of all participants was 60.32 years. Findings indicate that rural gay and lesbian individuals develop networks with little consideration for network members' acceptance of their identity. Participants reported an average network size of 9.32 individuals. Gay men reported higher perceptual affinity (.69) than lesbian participants (.62). Lesbian networks showed significantly (p = .0262) greater demographic similarity (.58) than aging gay men's networks (.55). Aging gay men (.89) reported statistically stronger (p = .0078) network ties than aging lesbian females (.78). Among participants in this study, network size is not correlated with the health and quality of life of rural aging lesbian and gay individuals. Still, personal identity congruence does appear to relate to health and quality of life. The findings highlight the collective need to continue research into sexual minority aging and rural sexual minority aging, particularly employing novel methods.

Analisa Perfoma Jaringan Wifi Berbasis Smartphone Sebagai Tethering dan Smartphone Sebagai Modem dengan Metode Perbandingan

At this time smartphones sound familiar to the public. Smartphones are included in the auxiliary tools in the continuity of human life equipped with various features that have the same capabilities as computers, so it is no stranger to the ears of the community with it because it provides convenience for users. One of the features given to smartphones is the tathering feature, Tethering makes it easy for users to share internet connections in a way that is easy to use in every age group of society in general. This research uses an experimental method by analyzing two objects. Based on the test results, the test was carried out using the speed test application 10 times within 1 day and obtained an average on both objects that showed a comparison of the results obtained and showed the superiority of using a smartphone as a modem compared to a tethering smartphone. In this test, get the average value of the router download: 15.66 and upload: 18.207 then the average value of tethering download: 10,815 and upload: 16,271 from the beginning of the average network used download: 20.782 and upload: 20,51. With the average comparison above, it can be concluded that the use of a smartphone as a modem has a superior network sharing average using MBps as a measure.

Tetra Optimization Based Hybrid Parameters for OFDM Modulated Wireless Sensor Network

Orthogonal frequency-division multiplexing [OFDM] is an information transfer technique in which a single data flow is divided between several closely spaced narrowband subchannel frequency range rather than a single Wideband channel frequency. The information is sent to the relay node there is a delay and some data is lost in the relay node is the major issue in the existing system. To overcome these challenges, The objective of this study is to minimize the overall energy consumption and to maximize the network lifetime. In this paper, a novel Five Input Hybrid Optimization Relay Node Selection and Energy Efficient Routing (FIHORNSEER) technique has been proposed for choosing the best relay based on noises. Ant Lion Optimization (ALO) is initially utilized to select the relay node's elite position. Secondly, the Crow Search Optimization (CSO) Algorithm is used for the phenomenon of position and memory of each relay. Finally, the Memetic Algorithm (MA) was generated by integrating the Ant Lion and Crow search optimization algorithm for the best relay node selection. The proposed framework is compared with previous techniques like FRNSEER, LMMSE, and HABO-OFDM Methods in terms of performance analysis, such as average utility, Energy Consumption, and Network Life Time. The result shows that the proposed FIHORNSEER improves the energy consumption better than 22.01%, 16.4%, and 12.2% FRNSEER, LMMSE, and HABO-OFDM, respectively.

Image Splicing Compression Algorithm Based on the Extended Kalman Filter for Unmanned Aerial Vehicles Communication

The technology of unmanned aerial vehicles (UAVs) is extensively utilized across various domains due to its exceptional mobility, cost-effectiveness, rapid deployment, and flexible configuration. However, its limited storage space and the contradiction between the large amount of image data returned and the limited bandwidth in emergency scenarios necessitate the development of a suitable UAVs image compression technology. In this research, we propose an image splicing compression algorithm based on the extended Kalman filter for UAV communication (SEKF-UC). Firstly, we introduce the concept of image splicing to enhance the compression ratio while ensuring image quality, leveraging the characteristics of deep learning-based compression, which are relatively unaffected by the size of the compressed data. Secondly, to address the issue of slow processing speed of deep neural networks (DNN) caused by the substantial volume of data involved in image splicing, we incorporate an extended Kalman filter module to expedite the process. Simulation experiments show that our proposed algorithm outperforms existing methods in multiple ways, achieving a significant compression ratio improvement, from 2:1 to 25:1, with a marginal reduction of 6.5% in structural similarity (SSIM) compared to the non-spliced approach. Moreover, for deep neural networks (DNN), our method incorporating the extended Kalman filter module achieves the same error level with only 30 iterations—a significant reduction compared to the traditional BP algorithm’s requirement of over 4000 iterations—while improving the average network operation speed by an impressive 89.76%. Additionally, our algorithm excels in image quality, with peak signal-to-noise ratio (PSNR) improving by 92.7% and SSIM by 42.1%, at most, compared to other algorithms. These results establish our algorithm as a highly efficient and effective solution, suitable for various image processing and data compression applications.

Methodology for calculating standards for process losses of heat energy and heat carrier, and consumption of electricity during transmission

A logical and sequential model of calculation of standards of process losses of heat energy and heat carrier, as well as electricity costs during transmission of heat energy in heating networks has been developed and built using MS Excel. The model constitutes a group of files interconnected by links, which allows perceiving the whole group of files as a single program. All the user needs to do is enter the source parameters of the heat network sections, such as length, diameter, year of installation, temperature curve, network operation time, pumping equipment characteristics, network operation temperature schedule, ambient temperature norms in accordance with the region of calculation, and the output will be a ready detailed calculation of all the normal rates. In the process of successive calculation, such normative values as heat energy losses, heat carrier costs, hourly heat energy losses under average annual network operating conditions, annual heat energy losses are determined. Besides, hourly and annual losses of heat carrier with leaks are determined. Power consumption is calculated on the basis of factory and operating parameters of pumping equipment operation. The results of standard calculations are summarized in a consolidated table, where both monthly and annual figures are shown. The procedure makes it possible to considerably decrease the time spent on calculations of normal rates, to make a forecast for heat energy balance, to analyze the dynamics of actual and estimated values. The methodology has been successfully proven, with multiple approvals of standards of process losses of heat energy, heat carrier, and electricity consumption during transmission by the Ministry of Energy of the Russian Federation.

Pattern formation and bifurcation analysis of delay induced fractional-order epidemic spreading on networks

The spontaneous emergence of ordered structures, known as Turing patterns, in complex networks is a phenomenon that holds potential applications across diverse scientific fields, including biology, chemistry, and physics. Here, we present a novel delayed fractional-order susceptible–infected–recovered–susceptible (SIRS) reaction–diffusion model functioning on a network, which is typically used to simulate disease transmission but can also model rumor propagation in social contexts. Our theoretical analysis establishes the Turing instability resulting from delay, and we support our conclusions through numerical experiments. We identify the unique impacts of delay, average network degree, and diffusion rate on pattern formation. The primary outcomes of our study are: (i) Delays cause system instability, mainly evidenced by periodic temporal fluctuations; (ii) The average network degree produces periodic oscillatory states in uneven spatial distributions; (iii) The combined influence of diffusion rate and delay results in irregular oscillations in both time and space. However, we also find that fractional-order can suppress the formation of spatiotemporal patterns. These findings are crucial for comprehending the impact of network structure on the dynamics of fractional-order systems.

Energized people in prominent places: Political support networks, relational energy, and employee innovation implementation

SummaryAlthough affect is a factor likely to impact the success of innovation, little research has been done on the relationship between affect and innovation implementation performance (i.e., an employee's ability to successfully implement innovative ideas and practices). We address this oversight by adopting a social network approach to examine relational energy (i.e., how energized one person is when interacting with another) as a form of high‐activation positive affect likely to influence innovation implementation. We test our hypotheses using a sample of employees in a pharmaceutical research firm (Study 1). Our results indicate that the number of people an employee goes to for political support who report being energized by that employee is positively related to innovation implementation performance. In contrast, the number of people an employee seeks out for political support who are not energized by that employee has negative implications for innovation implementation performance. The average network centrality of an individual's energized network contacts also relates to implementation performance, with this effect being stronger for employees not in a managerial position. A scenario‐based experiment (Study 2) provides support for the causal linkage between feeling energized by a co‐worker and one's willingness to provide instrumental help to the co‐worker.

A Machine Learning-Aided Network Contention-Aware Link Lifetime- and Delay-Based Hybrid Routing Framework for Software-Defined Vehicular Networks

The functionality of Vehicular Ad Hoc Networks (VANETs) is improved by the Software-Defined Vehicular Network (SDVN) paradigm. Routing is challenging in vehicular networks due to the dynamic network topology resulting from the high mobility of nodes. Existing approaches for routing in SDVN do not exploit both link lifetimes and link delays in finding routes, nor do they exploit the heterogeneity that exists in links in the vehicular network. Furthermore, most of the existing approaches compute parameters at the controller entirely using heuristic approaches, which are computationally inefficient and can increase the latency of SDVN as the network size grows. In this paper, we propose a novel hybrid algorithm for routing in SDVNs with two modes: the highest stable least delay mode and the highest stable shortest path mode, in which the mode is selected by estimating the network contention. We distinctly identify two communication channels in the vehicular network as wired and wireless, where network link entropy is formulated accordingly and is used in combination with pending transmissions to estimate collision probability and average network contention. We use the prospect of machine learning to predict the wireless link lifetimes and one-hop channel delays, which yield very low Root Mean Square Errors (RMSEs), depicting their very high accuracy, and the wireless link lifetime prediction using deep learning yields a much lower average computational time compared to an optimization-based approach. The proposed novel algorithm selects only stable links by comparing them with a link lifetime threshold whose optimum value is decided experimentally. We propose this routing framework to be compatible with the OpenFlow protocol, where we modify the flow table architecture to incorporate a route valid time and send a packet_in message to the controller when the route’s lifetime expires, requesting new flow rules. We further propose a flow table update algorithm to map computed routes to flow table entries, where we propose to incorporate an adaptive approach for route finding and flow rule updating upon reception of a packet_in message in order to minimize the computational burden at the controller and minimize communication overhead associated with control plane communication. This research contributes a novel hybrid routing framework for the existing SDVN paradigm, scrutinizing machine learning to predict the lifetime and delay of heterogeneity links, which can be readily integrated with the OpenFlow protocol for better routing applications, improving the performance of the SDVN. We performed realistic vehicular network simulations using the network simulator 3 by obtaining vehicular mobility traces using the Simulation of Urban Mobility (SUMO) tool, where we collected data sets for training the machine learning models using the simulated environment in order to test models in terms of RMSE and computational complexity. The proposed routing framework was comparatively assessed against existing routing techniques by evaluating the communication cost, latency, channel utilization, and packet delivery ratio. According to the results, the proposed routing framework results in the lowest communication cost, the highest packet delivery ratio, the least latency, and moderate channel utilization, on average, compared to routing in VANET using Ad Hoc On-demand Distance Vector (AODV) and routing in SDVN using Dijkstra; thus, the proposed routing framework improves routing in SDVN. Furthermore, results show that the proposed routing framework is enhanced with increasing routing frequency and network size, as well as at low vehicular speeds.

Spatial Network and Driving Factors of Agricultural Green Total Factor Productivity in China

Agricultural green total factor productivity (AGTFP) is an important indicator to reflect the sustainability level of agriculture. The AGTFP network reflects the spatial correlations of the AGTFP among regions; thus, exploring its network structure and influencing factors can provide targeted policy guidance to the coordinated development of the agriculture sector. This study builds an epsilon-based measurement data envelopment analysis (EBM-DEA) model to calculate 31 provincial AGTFPs in China from 2002 to 2020. Then, social network analysis (SNA) was utilized to explore the characteristics of the AGTFP network, and the quadratic assignment procedure (QAP) was applied to find its external influencing factors. We reached four central conclusions: (1) Overall, there was a gradual upward trend of AGTFP in China during 2002~2020, and the average value rose from 0.75 in 2002 to 0.90 in 2020, but there were some differences among regions. (2) There is a complex and stable network characteristic of AGTFP; the average network density is 0.3753, and the average network efficiency is 0.4714. Meanwhile, some eastern and central areas, such as Henan, Anhui, Hubei, Hebei, Jiangsu, etc., have relatively high centrality and are a bridge in the entire network. (3) The AGTFP network can be divided into eight blocks, including two net beneficial blocks (the central-eastern provinces with high centrality); two net spillover blocks, including the provinces located in the developed urban areas (Beijing, Tianjin, Shanghai, and Jilin), the underdeveloped northwest regions (Ningxia, Qinghai, Xinjiang, and Tibet). The other areas are two-way spillover blocks. (4) Transportation development gap, technological progress gap, and the similarities of the agricultural industry structure are critical factors influencing the AGTFP network. Hence, improving the efficiency of the logistics and transportation industry, promoting technology transfer from developed areas to underdeveloped areas, and developing characteristic agriculture are all conducive to promoting the whole region’s AGTFP. Our research provides policy implications for sustainable agricultural development in China and other developing countries.

Modeling and Forecasting of Milk Production in the Western Zone of Tamil Nadu

Background: In India, the dairy business is expanding dramatically. Tamil Nadu milk cooperatives significantly contribute to the growth of the dairy sector in the state. In terms of delivering economic income for dairy smallholders and satisfying customer demand, the identification of milk production is one of the primary financial operations made in India. Considering this, it is crucial to understand future production to enhance and sustain the sector’s growth and development. Methods: The present investigation attempts to predict and forecast milk production in Tamil Nadu using time series models. Yearly milk data from 1976 to 2020 was taken. The study considered Auto-Regressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN) to select the appropriate stochastic model for forecasting milk production in Tamil Nadu. Further statistical modeling procedures employed for milk production reveal that the selection of a suitable time series model will always depend on the nature of the data. Result: Results revealed that the ARIMA model is selected as the best model despite ANN, even if it is considered the most powerful model. The CAGR for forecasted milk production from 2020-2025 was 0.02%. Model adequacy criteria like RMSE, MAPE and MAE are used. Based on observation ARIMA model (1, 1, 2) is chosen as the best model over the ANN model.