Unmanned aerial systems (UAS) are increasingly used in precision agriculture to collect crop health related data. UAS can capture data more often and more cost-effectively than sending human scouts into the field. However, in large crop fields, flight time, and hence data collection, is limited by battery life. In a conventional UAS approach, human operators are required to exchange depleted batteries many times, which can be costly and time consuming. In this study, we developed a novel, fully autonomous aerial scouting approach that preserves battery life by sampling sections of a field for sensing and predicting crop health for the whole field. Our approach uses reinforcement learning (RL) and convolutional neural networks (CNN) to accurately and autonomously sample the field. To develop and test the approach, we ran flight simulations on an aerial image dataset collected from an 80-acre corn field. The excess green vegetation Index was used as a proxy for crop health condition. Compared to the conventional UAS scouting approach, the proposed scouting approach sampled 40% of the field, predicted crop health with 89.8% accuracy, reduced labor cost by 4.8× and increased agricultural profits by 1.36×.

The growing carbon footprint of Web hosting centers contributes to climate change and could harm the public's perception of Web hosts and Internet services. A pioneering cadre of Web hosts, called green hosts, lower their footprints by cutting into their profit margins to buy carbon offsets. This paper argues that an adaptive approach to buying carbon offsets can increase a green host's total profit by exploiting daily, bursty patterns in Internet service workloads. We make the case in three steps. First, we present a realistic, geographically distributed service that meets strict SLAs while using green hosts to lower its carbon footprint. We show that the service routes requests between competing hosts differently depending on its request arrival rate and on how many carbon offsets each host provides. Second, we use empirical traces of request arrivals to compute how many carbon offsets a host should provide to maximize its profit. We find that diurnal fluctuations and bursty surges interrupted long contiguous periods where the best carbon offset policy held steady, leading us to propose a reactive approach. For certain hosts, our approach can triple the profit compared to a fixed approach used in practice. Third, we simulate 9 services with diverse carbon footprint goals that distribute their workloads across 11 Web hosts worldwide. We use real data on the location of Web hosts and their provided carbon offset policies to show that adaptive green hosting can increase profit by 152% for one of today's larger green hosts.

Real production applications ranging from enterprise applications to large e-commerce sites share a crucial but seldom-noted characteristic: The relative frequencies of transaction types in their workloads are nonstationary , i.e., the transaction mix changes over time. Accurately predicting application-level performance in business-critical production applications is an increasingly important problem. However, transaction mix nonstationarity casts doubt on the practical usefulness of prediction methods that ignore this phenomenon. This paper demonstrates that transaction mix nonstationarity enables a new approach to predicting application-level performance as a function of transaction mix. We exploit nonstationarity to circumvent the need for invasive instrumentation and controlled benchmarking during model calibration; our approach relies solely on lightweight passive measurements that are routinely collected in today's production environments. We evaluate predictive accuracy on two real business-critical production applications. The accuracy of our response time predictions ranges from 10% to 16% on these applications, and our models generalize well to workloads very different from those used for calibration. We apply our technique to the challenging problem of predicting the impact of application consolidation on transaction response times. We calibrate models of two testbed applications running on dedicated machines, then use the models to predict their performance when they run together on a shared machine and serve very different workloads. Our predictions are accurate to within 4% to 14%. Existing approaches to consolidation decision support predict post-consolidation resource utilizations . Our method allows application-level performance to guide consolidation decisions.

Fully autonomous aerial systems (FAAS) fly complex missions guided wholly by software. If users choose software, compute hardware and aircraft well, FAAS can complete missions faster and safer than unmanned aerial systems piloted by humans. On the other hand, poorly managed edge resources slow down missions, waste energy and inflate costs. This paper presents a model-driven approach to manage FAAS. We fly real FAAS missions, profile compute and aircraft resource usage and model expected demands. Naive profiling approaches use traces from previous flights to infer resource usage. However, edge resources can affect where FAAS fly and which data they sense. Usage profiles can diverge greatly across edge management policies. Instead of using traces, we characterize whole flight areas to accurately model resource usage for any flight path. We combine expected resource demands to model mission throughput, i.e., missions completed per fully charged battery. We validated our model by creating FAAS, measuring mission throughput across many system settings. Our FAAS benchmarks, released through our open source FAAS suite SoftwarePilot, execute realistic missions: autonomous photography, search and rescue, and agricultural scouting using well-known software. Our model predicted throughput with 4% error across mission, software and hardware settings. Competing approaches yielded 10--24% error. We used our SoftwarePilot benchmarks to study (1) GPU acceleration, scale up, and scale out, (2) onboard, edge and cloud computing, (3) energy and monetary budgets, and (4) software driven GPU management. We found that model-driven management can boost mission throughput by 10X and reduce costs by 87%.

Precision agriculture examines crop fields, gathers data, analyzes crop health and informs field management. This data driven approach can reduce fertilizer runoff, prevent crop disease and increase yield. Frequent data collection improves outcomes, but also increases operating costs. Fully autonomous aerial systems (FAAS) can capture detailed images of crop fields without human intervention. They can reduce operating costs significantly. However, FAAS software must embed agricultural expertise to decide where to fly, which images to capture and when to land. This paper explores fully autonomous precision agriculture where FAAS map crop fields frequently. We have designed hardware and software architecture. We use unmanned aerial systems, edge computing components and software driven by reinforcement learning and ensemble models. In early results, we have collected data from an Ohio cornfield. We use this data to simulate a FAAS modeling crop yield. Our results (1) show that our approach predicts yield well and (2) can quantify computational demand. Computational costs can be prohibitive. We discuss how research on adaptive systems can reduce costs and enable fully autonomous precision agriculture. We also provide our simulation tools and dataset as part of our open source FAAS middleware, SoftewarePilot.

Internet services replicate data to geo-diverse sites around the world, often via consistent hashing. Collectively, these sites span multiple power authorities that independently control carbon emissions at each site. Serving data from a carbon-heavy site increases the service's carbon footprint, but it is hard to place data at sites that will have low emission rates without replicating to too many sites. We present CADRE, a carbon-aware data replication approach. CADRE forecasts emission rates at each site and replicates data to sites that combine together to yield low carbon footprints. It makes replication decisions online, i.e., When data is created, and thus avoids emissions caused by moving data frequently in response to changing emission rates. CADRE uses the multiple-choice secretary algorithm to replicate objects with large footprints to low emission sites. It models carbon footprints for each object using the footprint-replication curve, a graph that maps replication factors to expected carbon footprints. CADRE also achieves availability goals, respects storage capacity limits and balances data across sites. Compared to consistent hashing, our approach reduces carbon footprints by 70%. It also supports and enhances the state-of-the-art green load balancing, reducing the carbon footprint by an additional 21%.