Workload Patterns Research Articles

Advanced Analysis of Scalability and Mobility in Cloud Servers using Logistic Regression Models.

With the rapid expansion of cloud computing, efficiently managing scalability and mobility has become paramount. This paper presents an in-depth examination of how logistic regression models can predict and optimize these two critical aspects of cloud infrastructure. By analyzing various cloud configurations, workload patterns, and system performance data, the logistic regression framework forecasts resource needs and identifies potential bottlenecks. The study incorporates real-world applications and case studies to demonstrate the practical benefits of logistic regression in enhancing cloud performance. Additionally, the paper compares logistic regression with other predictive models and explores future advancements in cloud optimization through AI-driven automation and real-time machine learning. The findings underscore the importance of predictive analytics in maintaining seamless cloud operations and provide actionable insights for cloud architects aiming to design more resilient and efficient cloud systems.

Adaptive and Scalable Database Management with Machine Learning Integration: A PostgreSQL Case Study

The increasing complexity of managing modern database systems, particularly in terms of optimizing query performance for large datasets, presents significant challenges that traditional methods often fail to address. This paper proposes a comprehensive framework for integrating advanced machine learning (ML) models within the architecture of a database management system (DBMS), with a specific focus on PostgreSQL. Our approach leverages a combination of supervised and unsupervised learning techniques to predict query execution times, optimize performance, and dynamically manage workloads. Unlike existing solutions that address specific optimization tasks in isolation, our framework provides a unified platform that supports real-time model inference and automatic database configuration adjustments based on workload patterns. A key contribution of our work is the integration of ML capabilities directly into the DBMS engine, enabling seamless interaction between the ML models and the query optimization process. This integration allows for the automatic retraining of models and dynamic workload management, resulting in substantial improvements in both query response times and overall system throughput. Our evaluations using the Transaction Processing Performance Council Decision Support (TPC-DS) benchmark dataset at scale factors of 100 GB, 1 TB, and 10 TB demonstrate a reduction of up to 42% in query execution times and a 74% improvement in throughput compared with traditional approaches. Additionally, we address challenges such as potential conflicts in tuning recommendations and the performance overhead associated with ML integration, providing insights for future research directions. This study is motivated by the need for autonomous tuning mechanisms to manage large-scale, heterogeneous workloads while answering key research questions, such as the following: (1) How can machine learning models be integrated into a DBMS to improve query optimization and workload management? (2) What performance improvements can be achieved through dynamic configuration tuning based on real-time workload patterns? Our results suggest that the proposed framework significantly reduces the need for manual database administration while effectively adapting to evolving workloads, offering a robust solution for modern large-scale data environments.

Efficient resource allocation in cloud computing environments using AI-driven predictive analytics

This paper proposes an innovative AI-driven approach for efficient resource allocation in cloud computing environments using predictive analytics. The study addresses the critical challenge of optimizing resource utilization while maintaining high quality of service in dynamic cloud infrastructures. A hybrid predictive model combining XGBoost and LSTM networks is developed to forecast workload patterns across various time horizons. The model leverages historical data from a large-scale cloud environment, encompassing 1000 servers and over 52 million data points. A dynamic resource scaling algorithm is introduced, which integrates the predictive model outputs with real-time system state information to make proactive allocation decisions. The proposed framework incorporates advanced techniques such as workload consolidation, resource oversubscription, and elastic resource pools to maximize utilization efficiency. Experimental results demonstrate significant improvements in key performance indicators, including increasing resource utilization from 65% to 83%, reducing SLA violation rates from 2.5% to 0.8%, and enhancing energy efficiency, with PUE improving from 1.4 to 1.18. Comparative analysis shows that the proposed model outperforms existing prediction accuracy and resource allocation efficiency methods. The study contributes to the field by presenting a comprehensive, AI-driven solution that addresses the complexities of modern cloud environments and paves the way for more intelligent and autonomous cloud resource management systems.

HRMF-DRP: A next-generation solution for overcoming provisioning challenges in cloud environments

The cloud computing infrastructure is a distributed environment and the existing research works have some provisioning problems such as suboptimal resource utilization and high execution time. The Heterogeneity Resource Management Framework for Dynamic Resource Provisioning (HRMF-DRP) is proposed for focusing on task scheduling and workload management. This framework incorporates advanced algorithms for dataset preprocessing, task clustering, workload prediction, and dynamic resource provisioning. For data preprocessing, the real-world workload traces were captured from the Planet Lab dataset that are taken as input for the preprocessing stage. The data preprocessing is responsible for ensuring data quality and reliability by using different models like missing data handling, outlier detection and removal as well as standardization and normalization. In this paper, the tasks are grouped into clusters by utilizing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) model and this model categorizes the data points into border points, core points and noise points based on their density. The temporal dependencies are captured for the workload prediction by using Long Short-Term Memory (LSTM) neural network model. A Gaussian Mixture Model (GMM) model is responsible for estimating the number of Virtual machines (VMs) present in the workload prediction process. The Self-Adaptive Genetic Algorithm (SAGA) is implemented for task mapping that adjusts the parameters to change workload patterns for contributing adaptability and robustness. The different experimental evaluations are conducted based on the task completion time, workload balance index, resource utilization efficiency and workload prediction accuracy. The proposed model achieved the workload prediction accuracy of 98.5%, cost of $89.6, execution time of 125ms, Task Completion Time (TCT) of 40ms, Workload Balance Index (WBI) of 0.96 and Resource Utilization Efficiency (RUE) of 0.93. The quantitative results collectively position HRMF-DRP as a practical and efficient solution, promising advancements in dynamic resource provisioning for cloud computing, particularly within the Infrastructure as a Service (IaaS) cloud model.

Classification of gait variation under mental workload in big five personalities

BackgroundHuman behavior patterns involve mutual interactions among psychology, physiology, and stress, which are all associated with gait at different grades. Research questionsThe study aims to reveal the interrelationship among personality, mental workload, and gait patterns by capturing gait variations using inertial sensors. It also assesses individual personality traits and simulates stress to construct a gait classification model. MethodsSixty participants were instructed to perform regular, low, and high mental workload walking on the corridor to simulate a natural setting walking. Meanwhile inertial measurement units (IMUs) were placed on eight body parts. Mental workload was induced using the auditory n-back task, and their Big Five personality traits were evaluated. Gait data from IMUs were categorized into nine classifications of average, low, and high Big Five Inventory scores with three levels of mental workload walking. Subsequently, the segmentation gait data were used as input features for classifications in deep learning models, employing a sliding window long short-term memory network for nine classifications for different personality dimensions. ResultsThe results indicated average accuracies of nine classifications were 83.6 % for Openness, 84.4 % for Conscientiousness, 82.0 % for Extraversion, 85.2 % for Agreeableness, and 84.5 % for Neuroticism across all IMU placements. Remarkably, gait data from the lower back IMU achieved the highest model performance, with an average accuracy of 92.7 %, in classifying the different levels of personality and mental workload walking. In contrast, the left wrist and chest showed several misclassifications among regular, low, and high mental workload walking across personality traits. SignificanceSuccessful classification can help monitor an individual's mental state in real time and analyze personality dimensions, providing feedback and suggestions. The present study demonstrated that gait characteristics can contribute to more profound and personalized health information.

Extracting the explore‐exploit intelligence of Physarum to manage the sustainability of an enterprise network

AbstractIn this work, we enhance the sustainability of an enterprise network (EN) by complementing it with an expert system that apprehends the explore‐exploit behavioural intelligence of Physarum to survive against the attractive‐adversarial nutritional environment. EN sustainability is dynamic since it depends on how well EN can react to an adversarial environment. We capture a reverse analogy to characterize EN's workload‐environment with Physarum's nutritive‐environment, where the high volume of workloads at the backbone network corresponds to a poor‐nutrient environment. The expert system explores EN to find out how to manage the workloads as Physarum handles its survivability, and exploits the users' workload patterns by grouping the highly communicating users together to redesign the network structure as Physarum's intelligence to exploit energy from rich‐ and poor‐nutrient food sources through redesigned tubular structures. We define two factors, such as nutrient‐intensity and chemo‐attractant to aid the redesign process. EN evolves through a set of redesigned clusters with an objective function to maximize its sustainability for a given set of explored workloads by minimizing the workloads through the backbone. EN evolution terminates when there is no change in the backbone utilization, resembling the organism's stay in a dormant state until it experiences a favourable environment. Our experimental results on an EN with a higher volume of workloads at the backbone producing 14.26 kWh energy consumption demonstrated that the developed expert system reduced the energy consumption to 11.27 kWh, thus enhanced the sustainability from 21% to 61%.

A novel framework for generic Spark workload characterization and similar pattern recognition using machine learning

Comprehensive workload characterization plays a pivotal role in comprehending Spark applications, as it enables the analysis of diverse aspects and behaviors. This understanding is indispensable for devising downstream tuning objectives, such as performance improvement. To address this pivotal issue, our work introduces a novel and scalable framework for generic Spark workload characterization, complemented by consistent geometric measurements. The presented approach aims to build robust workload descriptors by profiling only quantitative metrics at the application task-level, in a non-intrusive manner. We expand our framework for downstream workload pattern recognition by incorporating unsupervised machine learning techniques: clustering algorithms and feature selection. These techniques significantly improve the process of grouping similar workloads without relying on predefined labels. We effectively recognize 24 representative Spark workloads from diverse domains, including SQL, machine learning, web search, graph, and micro-benchmarks, available in HiBench. Our framework achieves a high accuracy F-Measure score of up to 90.9% and a Normalized Mutual Information of up to 94.5% in similar workload pattern recognition. These scores significantly outperform the results obtained in a comparative analysis with an established workload characterization approach in the literature.

“I Didn't See That Coming!” A daily investigation of the effects of as‐expected and un‐expected workload levels

AbstractWorkload is a ubiquitous feature of the workplace and an exemplar occupational stressor. In contrast to other such experiences, workload represents a necessary aspect of employment that cannot be alleviated or removed. It also has both aversive and beneficial aspects; research, therefore, has aimed to examine the circumstances under which its negative effects can be alleviated while still maintaining its potential benefits for individuals and organizations. Such efforts, however, have had mixed success. In this paper, we propose a new way forward by examining the extent to which the concordance of individual expectations about daily workload and actually experienced workload is associated with aversive affective responses (with ultimate impacts of the latter for cross‐day functioning). We test these propositions in two daily studies and find that when experienced workload levels do not align with expectations, individuals experience higher levels of anxiety. Importantly, these effects of unexpected workload are overall stronger in magnitude than the effects of high but expected workload; furthermore, they operate through their impact on individuals’ sense of control. These workload patterns are further indirectly associated with next‐day functioning through sense of control and anxiety. Implications for theory and practice are discussed, together with directions for future research.

A Comparative Study of Deep Neural Networks and Support Vector Machines for Unsupervised Anomaly Detection in Cloud Computing Environments

Abstract: Cloud computing is now ubiquitous and provides convenient access to computing resources on demand. Cloud environments are complex and prone to faults, which can have a negative impact on service quality. Cloud providers must be able to detect issues in a proactive manner using unsupervised anomaly detection. This does not require labeled data. This paper presents a comparison of deep neural networks and support vector machine (SVMs), both used for unsupervised anomaly identification in cloud environments. On benchmark datasets provided by cloud providers, we evaluate the performance Autoencoders with LSTM models, One Class SVMs, and Isolation Forests. Our results show that shallow Autoencoders do not capture workload patterns well, but LSTMs or Convolutional Autoencoders can. SVMs are as good or better than Autoencoders. One-Class SVMs show robust performance in all workloads. Isolation Forests perform poorly on cloud data that is seasonal. One-Class SVMs are the most accurate and low latency option for anomaly detection. Our findings offer cloud providers guidance on how to select suitable unsupervised models based upon their performance, interpretability, and computational overhead. The results and comparative methodology will be used to inform future research into adapting unsupervised-learning for cloud anomaly detection.

Optimizing Resource Management for Shared Microservices: A Scalable System Design

A common approach to improving resource utilization in data centers is to adaptively provision resources based on the actual workload. One fundamental challenge of doing this in microservice management frameworks, however, is that different components of a service can exhibit significant differences in their impact on end-to-end performance. To make resource management more challenging, a single microservice can be shared by multiple online services that have diverse workload patterns and SLA requirements. We present an efficient resource management system, namely Erms, for guaranteeing SLAs with high probability in shared microservice environments. Erms profiles microservice latency as a piece-wise linear function of the workload, resource usage, and interference. Based on this profiling, Erms builds resource scaling models to optimally determine latency targets for microservices with complex dependencies. Erms also designs new scheduling policies at shared microservices to further enhance resource efficiency. Experiments across microservice benchmarks as well as trace-driven simulations demonstrate that Erms can reduce SLA violation probability by 5× and more importantly, lead to a reduction in resource usage by 1.6×, compared to state-of-the-art approaches.

How flight experience impacts pilots’ decision-making and visual scanning pattern in low-visibility approaches: preliminary evidence from eye tracking

The visual approach is the most accident-prone phase of a flight, especially in low-visibility conditions. This preliminary study aimed to examine the effects of flight experience on pilots’ decision-making and visual scanning pattern in low-visibility approaches. Twenty pilots were separated into two groups based on their flight experience and completed the high- and low-visibility approaches in balanced order using a high-fidelity flight simulator. Pilots’ mental workload and visual scanning patterns were recorded via an eye tracker. The results showed that, compared to less flight-experienced pilots (20%, 3/15), experienced pilots (80%, 4/5) were more likely to make go-around decisions in the low-visibility approaches. Furthermore, they exhibited a more flexible and adaptable visual scanning pattern by quickly shifting their attention, as evidenced by decreased fixations and increased saccades. These findings suggest that the integration of visual scanning strategy and training solution with a marginally meteorological approach may enhance decision-making safety for novice pilots.

Green Computing with Deep Learning for Data Centers

Due to development in cloud services, lots of data is transferred between users and servers of the cloud. This transmission of data consumes huge amounts of energy. This energy consumption occurs during the operation of network infrastructure, the conversion of electrical to optical signals to travel long distances, and signal amplification. As Green computing is the use of computing devices in an environmentally friendly way, i.e., using electrical energy efficiently as Data centers require a significant amount of electricity to operate and cool the servers, leading to carbon emissions from the burning of fossil fuels. Green computing in cloud services is about optimizing energy consumption and by incorporating deep learning algorithms, we can enhance the energy efficiency of cloud infrastructure. These algorithms can analyze real-time data from sensors, optimize resource allocation, and dynamically adjust power usage. Through intelligent workload scheduling, server consolidation, and power management, deep learning enables the reduction of energy waste and carbon emissions. The integration of deep learning in cloud services not only improves energy efficiency but also enhances performance and cost-effectiveness. Here we are using a deep learning model which can be used for workload prediction and resource provisioning. By analyzing historical workload patterns and user behavior, deep learning algorithmscan predict future resource demands and allocate resources accordingly, leading to more efficient resource utilization and energy savings

Machine learning-driven task scheduling with dynamic K-means based clustering algorithm using fuzzy logic in FOG environment

Fog Computing has emerged as a pivotal technology for enabling low-latency, context-aware, and efficient computing at the edge of the network. Effective task scheduling plays a vital role in optimizing the performance of fog computing systems. Traditional task scheduling algorithms, primarily designed for centralized cloud environments, often fail to cater to the dynamic, heterogeneous, and resource-constrained nature of Fog nodes. To overcome these limitations, we introduce a sophisticated machine learning-driven methodology that adapts task allocation to the ever-changing Fog environment's conditions. Our approach amalgamates K-Means clustering algorithm enhanced with fuzzy logic, a robust unsupervised learning technique, to efficiently group Fog nodes based on their resource characteristics and workload patterns. The proposed method combines the clustering capabilities of K-means with the adaptability of fuzzy logic to dynamically allocate tasks to fog nodes. By leveraging machine learning techniques, we demonstrate how tasks can be intelligently allocated to fog nodes, resulting in reducing execution time, response time and network usage. Through extensive experiments, we showcase the effectiveness and adaptability of our proposed approach in dynamic fog environments. Clustering proves to be a time-effective method for identifying groups of jobs per virtual machine (VM) efficiently. To model and evaluate our proposed approach, we have utilized iFogSim. The simulation results affirm the effectiveness of our scheduling technique, showcasing significant enhancements in execution time reduction, minimized network utilization, and improved response time when compared to existing machine learning and non-machine learning based scheduling methods within the iFogSim framework.

PLATON: Top-down R-tree Packing with Learned Partition Policy

The exponential growth of spatial data poses new challenges to the performance of spatial databases. Spatial indexes like R-tree greatly accelerate the query performance and can be effectively constructed through packing, i.e., loading all data into the index at once. However, existing R-tree packing methods rely on a set of fixed heuristic rules, which may not be suitable for different data distributions and workload patterns. To address the limitations of existing R-tree packing methods, we propose PLATON, a top-down R-tree packing method with learned partition policy that explicitly optimizes the query performance with regard to the given data and workload instance. We develop a learned partition policy based on Monte Carlo Tree Search and carefully make design choices for the MCTS exploration strategy and simulation strategy to improve algorithm convergence. We propose a divide and conquer strategy and two optimization techniques, early termination and level-wise sampling, to drastically reduce the MCTS algorithm's time complexity and make it a linear-time algorithm. Experiments on both synthetic and real-world datasets demonstrate the superior performance of PLATON over existing R-tree variants and recently proposed learned/workload-aware spatial indexes.

On-Call Workload Differences in Neurosurgery: Resident Call "Weather" and a Departure from Colored Cloud Labels.

Labeling residents as "black" or "white" clouds based on perceived or presumed workloads is a timeworn custom across medical training and practice. Previous studies examining whether such perceptions align with objective workload patterns have offered conflicting results. We assessed whether such peer-assigned labels were associated with between-resident differences in objective, on-call workload metrics in three classes of neurosurgery junior residents. In doing so, we introduce more inclusive terminology for perceived differences in workload metrics. Residents were instructed to complete surveys to identify "sunny", "neutral", and "stormy" residents, reflecting least to greatest perceived workloads, of their respective classes. We retrospectively reviewed department and electronic medical records to record volume of on-call work over the first 4 months of each resident's 2nd postgraduate academic year. Inter-rater agreement of survey responses was measured using Fleiss' kappa. All statistical analyses were performed with a significance threshold of P < .05. Across all classes, there was strong inter-rater agreement in the identification of stormy and sunny residents (Kappa = 1.000, P = .003). While differences in on-call workload measures existed within each class, "weather" designations did not consistently reflect these differences. There were significant intraclass differences in per shift consult volume in two classes ( P = .035 and P = .009); however, consult volume corresponded to a resident's weather designations in only one class. Stormy residents generally saw more emergencies and, in 2 classes, performed more bedside procedures than their peers. Significant differences in objective on-call experience exist between junior neurosurgery residents. Self- and peer-assigned weather labels did not consistently align with a pattern of these differences, suggesting that other factors contribute to such labels.

Barriers to hand hygiene compliance in intensive care units to prevent the spread of healthcare-associated infections

Abstract Background: Healthcare-associated infections cause significant challenges to the provision of health care. This is due to the strain on individuals, their families, and health services. Hand hygiene measures are cost-effective to reduce the spread of healthcare-associated infections and effectively prevent the transmission of microorganisms during patient care. The hands of healthcare workers have been proven to be the main route of transmission of healthcare-associated infections. Maintaining proper hand hygiene is a straightforward method for averting healthcare-associated infections. Despite its significance, evidence suggests a need for enhanced compliance among healthcare workers concerning hand hygiene practices. Multiple factors influence hand hygiene adherence. Hence, this study sought to elucidate healthcare workers’ encounters with obstacles impeding hand hygiene compliance within intensive care units (ICUs). Materials and Methods: Conducted via purposive sampling, this qualitative study involved 50 professionals, including doctors, anesthesiologists, nurses, physiotherapists, and attendants employed in ICUs. The study utilized semi-structured individual interviews to collect data, whereas data analysis was carried out using the Lundman and Graneheim method. Results: In this study, the primary theme of “obstacles hindering hand hygiene adherence” is segmented into three principal categories: 1.barriers linked to healthcare providers encompass subcategories, such as workload, inadequate knowledge, inappropriate attitudes, and incorrect behavioral patterns; 2.barriers associated with management are delineated through subcategories involving inadequate planning and training and improper departmental physical space design; and 3.barriers related to equipment and facilities, consisting of subcategories centered on insufficient availability of equipment and equipment of subpar quality. Conclusion: The outcomes of this study offer valuable insights that can assist relevant authorities in implementing effective strategies to eliminate obstacles in hand hygiene practices. These findings aim to encourage the cultivation of the correct attitudes and behaviors among healthcare workers.

EagerCC: An ultra-low latency congestion control mechanism in datacenter networks

With the rapid development of cloud applications, the workload pattern of datacenters presents the characteristics of mixed long and short flows and frequent micro-burst traffic, which puts forward new requirements for network transmission performance, including ultra-low latency, high throughput, and strong stability. At the same time, datacenters begin to deploy the low-diameter topology to accommodate these new requirements, and the high-performance datacenter (HPDC) comes into being. However, due to the complexity of the load, existing congestion control mechanisms cannot control dynamic delay in the network well, which significantly restricts the development of the HPDC. Therefore, it is necessary to deploy the congestion control mechanism for the HPDC. So we propose EagerCC, an ultra-low latency, low-overhead, and accurate congestion control mechanism based on In-Network-Telemetry (INT) information for various datacenter scenarios, especially for HPDCs. EagerCC uses switch-feedback, ACK-padding, ACK-first to reduce feedback delay and uses switch-calculation, probabilistic ACK-padding to reduce the overhead of congestion signals. We conduct a lot of experiments and the result shows that EagerCC performs well in various datacenter scenarios, especially for HPDCs. Specifically, EagerCC reduces the 99th-FCT and avg-FCT by 52.3% and 13.3% for the HPC workload NPB-CG compared to HPCC in Dragonfly. In addition, EagerCC significantly reduces the network’s feedback delay and queue occupancy.

Real-Time Workload Pattern Analysis for Large-Scale Cloud Databases

Hosting database services on cloud systems has become a common practice. This has led to the increasing volume of database workloads, which provides the opportunity for pattern analysis. Discovering workload patterns from a business logic perspective is conducive to better understanding the trends and characteristics of the database system. However, existing workload pattern discovery systems are not suitable for large-scale cloud databases which are commonly employed by the industry. This is because the workload patterns of large-scale cloud databases are generally far more complicated than those of ordinary databases. In this paper, we propose Alibaba Workload Miner (AWM), a real-time system for discovering workload patterns in complicated large-scale workloads. AW M encodes and discovers the SQL query patterns logged from user requests and optimizes the querying processing based on the discovered patterns. First, Data Collection &amp; Preprocessing Module collects streaming query logs and encodes them into high-dimensional feature embeddings with rich semantic contexts and execution features. Next, Online Workload Mining Module separates encoded query by business groups and discovers the workload patterns for each group. Meanwhile, Offline Training Module collects labels and trains the classification model using the labels. Finally, Pattern-based Optimizing Module optimizes query processing in cloud databases by exploiting discovered patterns. Extensive experimental results on one synthetic dataset and two real-life datasets (extracted from Alibaba Cloud databases) show that AW M enhances the accuracy of pattern discovery by 66% and reduce the latency of online inference by 22%, compared with the state-of-the-arts.

CluMP: Clustered Markov Chain for Storage I/O Prefetch

Due to advancements in CPU and storage technologies, the processing speed of tasks has been increasing. However, there has been a relative slowdown in the data transfer speeds between disks and memory. Consequently, the issue of I/O processing speed has become a significant concern in I/O-intensive tasks. This research paper proposes CluMP, which predicts the next block to be requested within a process using a clustered Markov chain. Compared to the simple read-ahead approach commonly used in Linux systems, CluMP can predict prefetching more accurately and requires less memory for the prediction process. CluMP demonstrated a maximum memory hit ratio improvement of 191.41% in the KVM workload compared to read-ahead, as well as a maximum improvement of 130.81% in the Linux kernel build workload. Additionally, CluMP provides the advantage of adaptability to user objectives and utilized workloads by incorporating several parameters, thereby allowing for optimal performance across various workload patterns.

Sex inequality driven by dispersal

Inequality between the sexes is pervasive both outside and inside the home. One contributing factor could be the dispersal of one sex at marriage that sets up sex-specific differences in relatedness to the group. Here we exploit the ecological diversity and different social structures found in southwest China to investigate the role of sex-biased dispersal on inequality in the sexual division of labor. We use a wearable fitness tracker and validated readings by confirming that participants' daily "steps" were positively correlated with time spent in high-energy activities, such as agriculture and animal husbandry work, and negatively correlated with low-energy activities, such as leisure and relaxation. We applied multilevel comparative approaches to examine the relative workload pattern between the sexes under different dispersal states. Our results reveal two characteristics that lead to an unfavorable division of workload: being female and dispersing at marriage. This is consistent with the hypothesis that males have increased bargaining power when remaining in their natal home, leading to inequality in workload.