Antonio Buonanno

Predictive models for building's energy consumption: An Artificial Neural Network (ANN) approach

Buildings energy demand is influenced by many factors, such as: weather conditions, building structure and characteristics, energy consumption of components (lighting and HVAC systems), level of occupancy and users behavior. As consequence of multi-variable impact on buildings energy consumption, theoretical models based on first principles are not able to forecast actual energy demand of a generic building. In this paper, an Artificial Neural Network (ANN) model applied to a real case consisting in a dataset of monthly historical building electric energy consumption is developed. Results show that accuracy of energy consumption forecast runs, in terms of RMSPE (root mean square percentage error), in the range 15.7% to 17.97% and varies slightly according to the prediction horizon (3 months, 6 months and 12 months).

A maker friendly mobile and social sensing approach to urban air quality monitoring

Novel model of citizenship calls for a new approach to the policy making, characterized by the wish to be part of the information building process. The citizen wants to become an active member of the smart city. This has its impact also on the air quality monitoring and control process. In this work, we try to answer to these needs by investigating a citizen centered air quality monitoring concept. The goal is to enable individuals to monitor their exposure to air pollution and simultaneously to contribute creating a map of the state of urban air quality through the sharing of data.

A SWE Architecture for Real Time Water Quality Monitoring Capabilities Within Smart Drinking Water and Wastewater Network Solutions

The world is facing a water quantity and quality crisis. These global concerns are addressing water sector operators to smart technological solutions that realize the so-called smart drinking water and wastewater networks. Water quality preservation is one of the essential services that smart water utilities have to guaranteed. The water quality monitoring systems include a variety of in situ sensors with several sensor protocols and interfaces. Sensor integration as well as real time sensor readings accessibility and interoperability across the interconnected layers of functionality needed for a comprehensive smart water network solution are the challenges should be tackled. The objective of this research work has been to develop a standardized OGC SWE (Sensor Web Enablement) architecture that enables the integration and real time access to the various continuous and networked sensors can be installed along drinking water and wastewater networks, and real time sensor data browsing, querying and analyzing capabilities across the components of a smart water network solution. Furthermore, a web based geo-console and a QGIS SOS client application have been developed ad hoc for supporting utilities to effectively manage their water treatment and optimize quality-testing processes.

An adaptive immune based anomaly detection algorithm for smart WSN deployments

The growing attention in smart WSN deployments for monitoring, security and optimization applications urges the design of new tools in order to recognize, as soon as a possible, anomalous states of systems whenever they occur. In order to develop an anomaly detection system enabling to discover unusual events in a non-stationary process, a scalable immune based strategy has been adopted. The algorithm works as an instance based 1-class classifier capable to un-supervisedly model the “normal” spatial-temporal variable behavior of the system identifying first order anomalies. Typical immune-like processes guarantee a slow adaptation of the set of local patterns to long term variation in the monitored system. The algorithm has been applied to a several real scenarios showing to be able to work on both on resource constrained WSN nodes and on dealing with large data streams in centralized data processing facilities.

Applying the SWE Framework in Smart Water Utilities Domain

Water leakage, water contamination, inability to detect water quality are some of the problems affecting the existing drinking water infrastructures. Unmanaged wastewater can be a source of pollution, a hazard for the health of human populations and the environment alike. The majority of wastewater infrastructures results in massive run-off and flooding of cities in case of extreme rainfall events. One of the ways to address these problems is by creating smart water utilities, equipping them of smart distributed sensing systems, integrated with advanced information systems. The integration of the diverse networked sensors involved in the water utilities management is not straightforward. The objective of this research work has been to develop a OGC SWE (Sensor Web Enablement) architecture across different applications in the smart water utilities domain, capable of integrating the various networks of in-situ sensors and processing sensor observations into decision support systems, realizing sensor related services and data delivery.

Tinynose, an Auxiliary Smart Gas Sensor for RFID Tag in Vegetables Ripening Monitoring During Refrigerated Cargo Transport

Current state of the art’s real time monitoring of fresh produce, provides only temperature and humidity information. The idea is to develop new sensors and transport service assisted by ICT platform to monitor fresh produce quality. The technology will be based on radio frequency (RF) wireless network, and will provide real-time and in-site data-logging, enabling active management of food products in storage and transit. The RF sensor network design, allows an auxiliary sensor node to be “plugged in”. In this contribution we present the commercial platform developed starting from o fork of open hardware on which we assemble an array of commercial sensors in an “open air” configuration. We developed for this Embedded Gas Sensor System Device (Tinynose) two set-up: the “Development set-up” that uses a star wireless network infrastructure to store all raw sensor output and associated measurement error in a server DB to define parameters in ripening mathematical model and the “TAG set-up” that performs ripening evaluation in ICT in-site platform.

Online Anomaly Detection on Rain Gauge Networks for Robust Alerting Services to Citizens at Risk from Flooding

The modern cities are addressing their innovation efforts for facing not just the common stresses cities accumulate daily, but also the sudden shocks can occur such as urban floods. Networked gauge stations are instrumental to robust floods alerts though they suffer from error and fault. For capturing the anomalous behavior of networked rain gauges, the use of an online anomaly detection methodology, based on the Support Vector Regression (SVR) technique, has here been investigated and developed. The specific anomaly case of incorrectly zero sensor readings has been efficiently addressed by a centralized architecture and a prior-knowledge free approach based on SVRs that simulate the normality profile of the networked rain gauges, on the basis of the spatial-temporal correlation existing among the observed rainfall data. Real data from the pilot rain gauge network deployed in Calabria (South Italy) have been used for simulating the anomalous sensor readings. As a result, we conclude that SVR-based anomaly detection on networked rain gauges is appropriate, detecting the eventual rain gauge fault effectively during the rainfall event and by passing through increased alert states (green, yellow, orange, red).

A Sensor Fusion Method Applied to Networked Rain Gauges for Defining Statistically Based Rainfall Thresholds for Landslide Triggering

Timely alerts provided to the communities at risk of landslides can prevent casualties and costly damages to people, buildings and infrastructures. The rainfalls are one of the primary triggering causes for landslides so that empirical approaches based on the correlation between landslides occurrence and rainfall characteristics, are considered effective for warning systems. This research work has intended to develop a landslide alerting system by using a Sensor Fusion method based on the SVC (Support Vector Classification) techniques. This method fuses rainfall data gathered in continuous by networked rain gauges and returns confidence degrees associated to the not occurrence of the landslide event as well as to the occurrence of one. By using a k-fold validation technique, an SVC-model, with AUC (Area Under the Curve) mean of 0,964733 and variance of 0,001243, has been defined. The proposed method has been tested on the regional rain gauges network, deployed in Calabria (Italy).

A Distributed Sensor Network for Waste Water Management Plant Protection

Waste water management process has a significant role in guarantee sea and surface water bodies water quality with direct impact on tourism based economy and public health. Protection of this critical infrastructure form illicit discharges is hence paramount for the whole society. Here, We propose a pervasive monitoring centered approach to the protection of wastewater management plant. An hybrid sensor network is actually deployed along the wastewater network including several different transducers. Incepted data are harmonized and processed with an integrated SWMM model and machine learning based approach in order to forecast water qualitative and quantitative aspects, detect and localize anomalies. An advanced WEBGIS-SOS based interface conveys relevant information to the management entity allowing it to take appropriate actions in a timely way, reducing and mitigating the impacts of illicit discharges.

An integrated infrastructure for distributed waste water quality monitoring and decision support

Waste water management plant protection is a major concern for water cycle management entities. The rapid identification and possible localization of anomalous or even malicious waste liquids immission may allow for undertaking pollution risk mitigation actions (e.g. using of ancillary basins) and reduce maintenance costs. Pervasive monitoring of the transport network is hence needed although economic and technical issues prevent its implementation. The SIMONA project is aimed to design, deploy and test an integrated, intelligent, pervasive monitoring infrastructure based on a network of low cost/low maintenance quali-quantitative multisensor nodes. A scalable data processing facility permit the ingestion and the processing of the data stream while a set of models provide for quali-quantitative forecasting increasing the manager situational awareness about the smart infrastructure. All the information is made available via a GIS based Web HCI.