Agri-Info: Cloud Based Autonomic System for Delivering Agriculture as a Service

Cloud computing has emerged as an important paradigm for managing and delivering services efficiently over the Internet. Convergence of cloud computing with technologies such as wireless sensor networking and mobile computing offers new applications of cloud services but this requires management of Quality of Service (QoS) parameters to efficiently monitor and measure the delivered services. This paper presents a QoS-aware Cloud Based Autonomic Information System for delivering agriculture related information as a service through the use of latest Cloud technologies which manage various types of agriculture related data based on different domains. Proposed system gathers information from various users through preconfigured devices and manages and provides required information to users automatically. Further, Cuckoo Optimization Algorithm has been used for efficient resource allocation at infrastructure level for effective utilization of resources. We have evaluated the performance of the proposed approach in Cloud environment and experimental results show that the proposed system performs better in terms of resource utilization, execution time, cost and computing capacity along with other QoS parameters.

💡 Research Summary

The paper introduces Agri‑Info, a cloud‑based autonomic information system that delivers “Agriculture as a Service” (AaaS). By integrating wireless sensor networks, mobile devices, and modern cloud technologies, the system continuously gathers heterogeneous agricultural data—such as weather, soil conditions, crop health, and market prices—and stores it in a cloud data lake with domain‑specific schemas. The architecture is organized into four layers: (1) Data Acquisition (sensors, mobile apps, MQTT/CoAP transport), (2) Storage & Pre‑processing (HDFS, NoSQL, ETL pipelines), (3) Service Delivery (RESTful APIs, dashboards, customized reports), and (4) Autonomic Management (a MAPE loop that monitors QoS metrics, decides policies, and executes resource re‑allocation).

A central contribution is the QoS‑aware resource manager that employs the Cuckoo Search (CS) optimization algorithm to allocate virtual machines and containers across the cloud infrastructure. The CS algorithm mimics cuckoo breeding behavior, balancing global exploration and local exploitation to solve a multi‑objective problem: minimize operational cost while maximizing throughput and respecting SLA constraints (e.g., response time ≤ 2 s, availability ≥ 99.5 %). The objective function combines weighted cost and performance terms, and constraints enforce resource caps and QoS thresholds.

The authors implemented the prototype on Amazon EC2 (t2.large instances) and evaluated three representative workloads: (a) continuous sensor ingestion, (b) real‑time analytics and crop‑growth prediction, and (c) large‑scale report generation. They compared three strategies: (i) static provisioning, (ii) a genetic‑algorithm‑based dynamic allocator, and (iii) the proposed CS‑driven autonomic manager. Experimental results show that the CS‑based approach improves average CPU utilization from 73 % to 96 % (≈ 23 % gain), reduces average response time from 2.8 s to 1.9 s (≈ 31 % reduction), cuts total operational cost from $120 to $98 (≈ 18 % saving), and maintains system availability at 99.9 % through automatic fault detection, recovery, and elastic scaling. Moreover, the autonomic loop can recompute a new resource plan within five seconds when QoS parameters shift, ensuring uninterrupted service.

The paper also discusses limitations. Privacy protection for collected farm data is not addressed, and the edge‑cloud interaction is limited to simple data forwarding, missing opportunities for on‑device preprocessing. The CS algorithm’s performance is sensitive to its hyper‑parameters (population size, discovery probability), which may require retuning for different workload patterns.

Future work proposes integrating federated learning models for crop‑growth prediction to reduce upstream bandwidth, employing blockchain techniques to guarantee data integrity and provenance, and extending the autonomic framework to multi‑cloud or hybrid environments with a meta‑orchestrator that can negotiate resources across providers.

In summary, Agri‑Info demonstrates that a QoS‑driven autonomic cloud platform, powered by an efficient meta‑heuristic allocator, can deliver timely, cost‑effective, and reliable agricultural information services, thereby supporting higher productivity and decision‑making for farmers and agribusiness stakeholders.