Patent Application
20140081998
The subject matter disclosed herein relates to utility management systems and, more particularly, to methods and systems for utility management using social network data.
Utility outages can be very expensive both to consumers and the utility companies that serve them. As such, it is in the utility companies' best interests to locate and repair such outages as quickly and as economically as possible. Utility companies may also be interested in other information relating to the utility network, such as suspicious activity or utility damages and hazards. Conventionally, utility outages, such as power outages, and other damages or hazards are identified by landline telephone calls from customers in an affected area. Younger customers, however, are increasingly likely not to have landline telephone service. It may be more difficult to identify the location of a customer using a non-landline telephone, such as a cellular or Voice Over Internet Protocol (VOIP) telephone. Other techniques for identifying utility outages and other hazards have been developed that do not rely on landline telephone calls. Many of these techniques may involve sensors placed throughout the utility service area. These sensors, however, may be a very expensive investment for many utility companies.
Certain embodiments commensurate in scope with the originally claimed invention are summarized below. These embodiments are not intended to limit the scope of the claimed invention, but rather these embodiments are intended only to provide a brief summary of possible forms of the invention. Indeed, the invention may encompass a variety of forms that may be similar to or different from the embodiments set forth below.
In a first embodiment, a system includes a storage configured to store instructions that can be executed on a processor. Additionally, the system includes a processor to execute instructions for filtering social media posts from a variety of social media networks to ascertain social media posts relevant to a utility network. The instructions also associate the relevant social media posts with locations on the utility network.
In a second embodiment, a method using a processor comprises filtering social media posts of a social media network to ascertain social media posts relevant to a utility network. The method also includes determining that a utility network event has occurred based at least in part on the relevant social media posts.
In a third embodiment, a system includes a storage configured to store instructions executable by a processor, and a processor to execute the instructions. The instructions include instructions to determine a geographic location of a social media post that is relevant to a utility network. Additionally, the instructions include instructions to overlay the relevant social media post onto a network model representing the utility network or map of an area of the utility network, or both, at the determined geographic location.
These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:
One or more specific embodiments of the present invention will be described below. In an effort to provide a concise description of these embodiments, all features of an actual implementation may not be described in the specification. It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another. Moreover, it should be appreciated that such a development effort might be complex and time consuming, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure.
When introducing elements of various embodiments of the present invention, the articles “a,” “an,” “the,” and “said” are intended to mean that there are one or more of the elements. The terms “comprising,” “including,” and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements.
Present embodiments relate to a utility management system configured to take advantage of existing social network services. Among other things, the utility management system may help detect and locate utility network events. As used herein, the term “utility network event” refers to any occurrence that may impact utility management or service, such as utility outages, suspicious activity, utility hazards, or other utility-related information without the expensive investment of time and money in sensor technology. Some embodiments may provide utility companies (e.g., electrical utilities, water and sewer utilities, gas delivery utilities, and/or telephone and data) with an outage detection, location and analysis tool at a fraction of the cost of sensor-based systems. Particularly, the utility management system described below uses a social mining engine to obtain and filter data from a variety of social networking services. The social mining engine may query and filter the social networking data looking for items that may be relevant to the utility. Geographical data may also be supplied by the social networking service.
In the context of outage detection, the social networking data may be analyzed with data supplied by an outage management system in an outage analysis engine. This data is compared to a model of the network to determine the location of a fault, the blacked-out area caused by a fault, and the possible causes of a fault. The information generated by the outage analysis engine may be summarized and presented immediately in a suitable format to operators, dispatch crews and other interested parties. The analysis engine also may identify the individual sources of the social networking data used for the analysis. The source information may be used to provide incentives to the utility users that provided the information.
With the foregoing in mind, it may be useful to describe an embodiment of a utility management system that uses social media, here shown in the context of outage detection, such as illustrated in
The power generated by the power generation stations 16, 18, 20, and 22 may be transmitted through a power transmission grid 24. The power transmission grid 24 may cover a broad geographic region or regions, such as one or more municipalities, states, or countries. The transmission grid 24 may also be a single phase alternating current (AC) system, but most generally may be a three-phase AC current system. As depicted, the power transmission grid 24 may include a series of towers to support a series of overhead electrical conductors in various configurations. For example, extreme high voltage (EHV) conductors may be arranged in a three conductor bundle, having a conductor for each of three phases. The power transmission grid 24 may support nominal system voltages in the ranges of 110 kilovolts (kV) to 765 kilovolts (kV). In the depicted embodiment, the power transmission grid 24 may be electrically coupled to a power distribution substation and grid 26. The power distribution substation and grid 26 may include transformers to transform the voltage of the incoming power from a transmission voltage (e.g., 765 kV, 500 kV, 345 kV, or 138 kV) to primary (e.g., 13.8 kV or 4160V) and secondary (e.g., 480V, 240V, or 120V) distribution voltages. For example, industrial electric power consumers (e.g., production plants) may use a primary distribution voltage of 13.8 kV, while power delivered to commercial and residential consumers may be in the secondary distribution voltage range of 120V to 480V.
As again depicted in
As mentioned above, in certain embodiments, a disruption may cause an outage 38, effectively causing power loss to a group of residences 34. Upon losing power, a group of residents may send posts 40 out on social networking sites that include text 41 or other forms of data to indicate their power is out. Data that may indicate a power outage may include keywords, specific textual tags (e.g. #outage, @powerout, etc.), photos or videos of an area affected by an outage, voice messages describing a power outage, and so forth. The social networking sites may include, for example, Twitter, Facebook, Google+, app.net, blogs, or other sources of public information such as traffic information or local news sites. A power grid social media analysis system 42 may use public or private social network posts such as these to identify an outage, as discussed further below. The power grid social media analysis system 42 may use a processor 44 with instructions stored in a memory 46 coupled to the processor 44. The instructions may configure the processor 44 to mine the social data networks for posts relevant to the utility network 10. Upon processing the data of the social networking post 40, the processor 44 may determine the data is relevant to the utility network 10 and may store the message 40 in storage 48.
In certain embodiments of the present disclosure, associating a utility customer's social media account with a utility customer account may improve the reliability of the social media detection system. Accordingly,
In contrast to
Referring back to
In some embodiments, the processor 44 may request certain social network data by way of an application programming interface (API). For example, the processor 44 may request only social network data posted within a geographic area served by the utility power transmission grid 24 and within some recent amount of time. To provide a few examples, the processor 44 may request only social network data posted within the previous 30 seconds, 1 minute, 2 minutes, 5 minutes, 10 minutes, 20 minutes, 30 minutes, 1 hour, 2 hours, or any other suitable amount of time.
The processor 44 may process the social network data, filtering the social network data for data that may indicate a power outage, as represented by block 84. Data that may indicate a power outage may include keywords, specific textual tags (e.g. #outage, @powerout, etc.), or may involve more sophisticated text analysis, voice analysis, photo analysis, and/or video analysis. For each piece of social networking data, the processor 44 may decide if the data is relevant to a power outage or not, as represented by block 86. If an item is not relevant, the processor 44 may discard the piece of data and continue searching social network data 82. If an item is deemed relevant to a power outage, the processor 44 may acquire additional data from the post, if available, that may determine the geographic location of the original data post, as represented by block 88. The processor 44 may use the geographical data to determine a likely area of outage, as represented by block 90. The processor 44 may also determine the location and cause of a fault that caused the area of outage, as will be described below.
Turning now to
A social mining engine 116 may search and process data from the Internet 112 for data in social media posts 104 that would indicate a power outage. The social mining engine 116 may also search the Internet 112 for data in social media posts 104 periodically over a range of times. The range of times may include searching the social networking sites every 30 seconds, 1 minute, 2 minutes, 5 minutes, 10 minutes, 20 minutes, or any other suitable amount of time. The social mining engine 116 may also employ a threshold to limit how far back in time the data in social media posts 104 is considered relevant. The threshold may extend back 30 seconds, 1 minute, 2 minutes, 5 minutes, 10 minutes, 20 minutes, 30 minutes, 1 hour, 2 hours, or any other suitable amount of time. Depending on the social networking service 108, the data may be streamed to the social mining engine 116 (e.g., if the service supports streaming of queries), or it may be actively retrieved by a spider-like system (e.g., in the case of graph-based social networks). The social mining engine 116 may use social media APIs to search posts from specific geographical locations. Any data that may be deemed relevant to a power outage by the social mining engine 116 may be stored in the social event store 118. Data that may be deemed relevant to a power outage may include the use of specific textual tags (e.g., #outage, @powerout, etc.), or it may involve more sophisticated linguistic text analysis (for text analysis), voice analysis (for audio posts), or video analysis (for pictures and video posts). The social mining engine may store social media posts 104 that include geographical data. The geographical data may include the location of where customers are providing feedback 102 about a power outage. If geographical data is available for a given social media post 104, the geographical data may be stored with the social network data in the social event store 118.
An outage detection component 120 may receive data from both the outage management system 114 and the social event store 118 to determine the occurrence of a power outage. Data from the outage management system 114 and the social event store 118 may be determined to be related to the same outage event, and may cause the outage detection component 120 to invoke an outage analysis engine 122. The outage analysis engine 104 may extract all records from the social event store 118 deemed to belong to the same outage. The outage analysis engine may analyze the records from the social event store against a network model 124 to determine the location of the fault on the network, a blacked-out area caused by the fault, and possible causes of the fault. Possible causes of the fault may be determined from the linguistic analysis of text/voice data, or by photo/video posts.
In the present embodiment, the outage analysis engine may store the outage data in a real time outage store 128. The outage analysis engine may display outage data to a user experience interaction interface 130 and present the outage data in a suitable format to an outage event management group 132. The suitable format for the outage data may include but not be limited to a mobile application, text message, or web application. The outage event management group 132 may include operators, dispatch crews, or other interested parties.
The outage analysis engine 122 may identify the individual sources of the social networking data and provide the identity of the sources to a customer incentive component 134. The customer incentive component may use the customer identity data to provide incentives (e.g. discounts) to utility users or use the customer identity data in other ways. In some embodiments, the customer incentive component 134 may send a relevant reply to the social media posts made by utility users.
The example of
Like
Turning to
The social media analysis system 42 may be utilized to detect damage to the utility network or suspicious activity around the utility network as well as detecting power outages.
As mentioned, the social media analysis system may detect suspicious activity relating to the utility network.
Technical effects of embodiments include improved utility management using social network information. For instance, a power outage detection system may use social network mining to quickly and efficiently detect and respond to power outage events. Particularly, the system may include a social mining engine to acquire and filter through data from social networking sites. A series of outage detection components and outage analysis engines may analyze and process the data retrieved by the social mining engine to detect outage events, and in the case of an outage event, determine the location of a utility fault, an area affected by the fault, and a possible cause of the fault. This data may allow response teams to respond quickly and accurately to a power outage event.
This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the invention is defined by the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements with insubstantial differences from the literal language of the claims.
