Radio Frequency Identification (RFID) techniques are considered relevant building blocks for the Internet of Things. The interoperability across different RFID software and hardware infrastructures is a key requirement for achieving effective and wide-scale Internet of Thing deployments. The EPC Information Service (EPCIS) is a set of standard specifications for sharing RFID-related data (i.e., EPC events) both within and across enterprises. Although the EPCIS specifies a set of HTTP and Web Service interfaces for querying and adding EPC events, interoperability and easiness of use is hindered by the fact that client applications should be aware of the repositories that are authoritative for one or more given queries and links among relates events are not explicitly represented in response messages. We argue that, by leveraging emerging REST and Linked Data paradigms, EPC events can be handled as a graph of globally-addressable information resources that can be navigated, queried, and aggregated through a uniform interface and seamlessly across organization domains. To validate this approach, we have developed a prototype that exposes the EPCIS interfaces as a set of REST APIs. The prototype implementation exploits the information modeling and management capabilities provided by a framework, called InterDataNet (IDN), that we conceived and developed to ease the realization of the Web of Data and Linked Data applications.
We aim at exploiting Web-derived paradigms for enabling EPCIS data sharing across enterprises exploiting both REST and Linked Data principles. REST and Linked Data are two recent paradigms and while both have roots on the Web their mutual relation is a matter of study. Though REST and Linked Data show similarities (e.g., the resource abstraction, the use of URIs for resource identification, and the need of representing relations between resources), they have different scopes: REST defines an API for programming applications based on the HATEOAS (Hypermedia as the Engine of Application State) constraint, while Linked Data focuses on the definition of a distributed data model. These scopes could complement each other in the design of domain-driven applications: on one side Linked Data proposes principles for defining a shared representation of data in a given application domain, on the other side REST defines a lightweight API for accessing, modifying and publishing such data according to the given application domain purposes.
By exploiting both paradigms, EPC events can be handled as a graph of globally-addressable information resources that can be navigated, queried, and aggregated through a uniform interface and seamlessly across organization domains.
The EPC scenario is a challenging data consumption and production environment. For each tagged item, vast amount of information is entered into the system in the form of events. Events describe the relevant actions related to an EPC at a certain time. The EPCIS specification defines four types of events: 1) an Object Event is a general event related to an object. 2) An Aggregation Event describes the aggregation of more EPCs together inside a parent EPC container. For example, the actions of gathering a number of RFID tagged cases and loading them onto a pallet produce an Aggregation Event. 3) A Quantity Event describes an event pertaining to a number of elements of an object class where the individual instances are not identified. This type of event can be used to report inventory levels of a product. Finally, 4) a Transaction Event describes the association or disassociation of an object to a specific transaction.
Events establish relations between objects, contexts and sets of master data. For example an event can describe the loading phase of a pallet of microwave ovens on the currier truck occurred in a certain location. If the location is the factory facility, it will be likely to find it replicated in many other events. Due to their nature, master data are eligible to be frequently reused. This scenario could considerably benefit a graph data structure reflecting the abstract information relations. Therefore, the location of the previous example could be represented as a graph node the other entities (for example, events) connect with.
These considerations led us to propose the IDN approach to manage EPCIS information. Our intent is to build a browsable graph of individually addressable EPCIS data to support information reuse and efficient exploitation.
To this purpose, this web application has been designed and implemented. The application is called EPCWeb and is focused on two key assets: