Ekhiotz Jon Vergara

When mice consume like elephants: instant messaging applications

A recent surge in the usage of instant messaging (IM) applications on mobile devices has brought the energy efficiency of these applications into focus of attention. Although IM applications are changing the message communication landscape, this work illustrates that the current versions of IM applications differ vastly in energy consumption when using the third generation (3G) cellular communication. This paper shows the interdependency between energy consumption and IM data patterns in this context. We analyse the user interaction pattern using a IM dataset, consisting of 1043370 messages collected from 51 mobile users. Based on the usage characteristics, we propose a message bundling technique that aggregates consecutive messages over time, reducing the energy consumption with a trade-off against latency. The results show that message bundling can save up to 43% in energy consumption while still maintaining the conversation function. Finally, the energy cost of a common functionality used in IM applications that informs that the user is currently typing a response, so called typing notification, is evaluated showing an energy increase ranging from 40-104%.

Kernel level energy-efficient 3G background traffic shaper for android smartphones

Reducing the energy consumption of wireless devices is paramount to a wide spread adoption of mobile applications. Cellular communication imposes high energy consumption on the mobile devices due to the radio resource allocation, which differs from other networks such as WiFi. Most applications are unaware of the energy consumption characteristics of third generation cellular communication (3G). This makes the background small data transfers of undisciplined applications an energy burden due to inefficient utilisation of resources. While several approaches exist to reduce the energy consumption of this best-effort background traffic by means of traffic shaping, we find that they are mostly evaluated with simulations and the actual energy overhead for the traffic shaper itself has not been studied. In order to cover this gap, our work realises an existing energy saving algorithm as a Kernel Level Shaper (KLS) within the Android platform, and measures its energy footprint. The total energy savings of our implementation range from 8% to 58% for emulated real background traffic, that is categorised as best-effort traffic. We further show the implications of running the KLS during live operation of applications as an exploratory study.

EnergyBox: A Trace-Driven Tool for Data Transmission Energy Consumption Studies

Although evolving mobile technologies bring millions of users closer to the vision of information anywhere-anytime, device battery depletions hamper the quality of experience to a great extent. We argue that the design of energy-efficient solutions starts by energy-awareness and propose EnergyBox, a tool that provides accurate and repeatable energy consumption studies for 3G and WiFi transmissions at the user end. We recognize that the energy consumption of data transmission is highly dependable on the traffic pattern, and provide the means for trace-based iterative packet-driven simulation to derive the operation states of wireless interfaces. The strength of EnergyBox is that it allows to modularly set the 3G network parameters specified at operator level, the adaptive power save mode mechanism for a WiFi device, and the different power levels of the operation states for different handheld devices. EnergyBox enables efficient energy consumption studies using real data, which complements the device-dependent laborious physical power measurements. Using real application transmission traces, we have validated EnergyBox showing an accuracy range of 94-99% for 3G and 93-99% for WiFi compared to the real measured energy consumption by a 3G modem and a smartphone with WiFi.

Energy-aware cross-layer burst buffering for wireless communication

The massive explosion of mobile applications with the ensuing data exchange over the cellular infrastructure is not only a blessing to the mobile user but also has a price in terms of regular discharging of the device battery. A big contributor to this energy consumption is the power hungry wireless network interface. We leverage a measurement kit to perform accurate physical energy consumption measurements in a third generation (3G) telecommunication modem thus isolating the energy footprint of data transfers as opposed to other mobile phone-based measurement studies. Using the measurement kit we show how the statically configured network parameters, i.e., channel switch timers, and buffer thresholds, in addition to the transfer data pattern and the radio coverage, impact the communication energy footprint. We then demonstrate that being aware of static network parameters creates room for energy savings. This is done by devising a set of algorithms that (a) infer the network parameters efficiently, and (b) use the parameters in a new packet scheduler in the device. The combined regime is shown to transfer background uplink data, from real world traces of Facebook and Skype, with significant energy saving compared to the state-of-the-art.

Resource Footprint of a Manycast Protocol Implementation on Multiple Mobile Platforms

Wireless communication is becoming the dominant form of communication and ad hoc wireless connections are posed to play a role in disaster area networks. However, research efforts on wireless ad hoc communication protocols do not pay enough attention to measurable and reproducible indications of the mobile footprint including power consumption. Protocols and applications are initially designed and studied in a simulation environment and are hard to test in in-field experiments. In this work we report a multi-platform implementation of Random-Walk Gossip, a many cast protocol designed for message dissemination in disaster areas. Our work is focused in studying the resource footprint and its impact on performance on commercially available devices. We show both how different aspects of the protocol contributes to the footprint and how this in turn affects the performance. The methodologies used here can be applied to other protocols and applications, aiding in future optimisations.

Software-related energy footprint of a wireless broadband module

Energy economy in mobile devices is becoming an increasingly important factor as the devices become more advanced and rich in features. A large part of the energy footprint of a mobile device comes from the wireless communication module, and even more so as the amount of traffic increases. In this paper we study the energy footprint of a mobile broadband hardware module, and how it is affected by software, by performing systematic power consumption measurements. We show that there are several cases where the software does not properly take into account the effect that data communication has on the power consumption. This opens up for potential energy savings by creating better applications that are aware of the energy characteristics of the communication layer.

Communication Energy Overhead of Mobiles Games

Although a significant proportion of the mobile apps are games there has been little attention paid to their specific characteristics with respect to communication energy. In this paper we select 20 mobile games among the top 100 free Android games, and study their data patterns and communication energy use over a total of 25 hours of playing. The analysis of the energy for communication over 3G networks indicates that there is a wide variation among the games, the largest footprint being 8 times higher than the lowest one. The results also indicates both app-specific and category-specific relations between data pattern and energy use, as well as variations in CPU utilisation.

Fairness and Incentive Considerations in Energy Apportionment Policies

The energy consumption of a system is determined by the system component usage patterns and interactions between the coexisting entities and resources. Energy accounting plays an essential role in revealing the contribution of each entity to the total consumption and for energy management. Unfortunately, energy accounting inherits the apportionment problem of accounting in general, which does not have a general single best solution. In this article, we leverage cooperative game theory, which is commonly used in cost allocation problems to study the energy apportionment problem, that is, the problem of prescribing the actual energy consumption of a system to the consuming entities (e.g., applications, processes, or users of the system). We identify five relevant fairness properties for energy apportionment and present a detailed categorisation and analysis of eight previously proposed energy apportionment policies from different fields in computer and communication systems. In addition, we propose two novel energy apportionment policies based on cooperative game theory that provide strong fairness notion and a rich incentive structure. Our comparative analysis in terms of the identified five fairness properties as well as information requirement and computational complexity shows that there is a tradeoff between fairness and the other evaluation criteria. We provide guidelines to select an energy apportionment policy depending on the purpose of the apportionment and the characteristics of the system.

Sharing the Cost of Lunch: Energy Apportionment Policies

Energy consumption has become a hot topic in computer and communication technologies pinpointing the need to carefully analyse system efficiency. The energy consumption of a system is determined by the usage patterns of system components and complex interactions between the coexisting entities and resources. Providing transparency of a systems consumption by breaking down the total consumption is vital to evaluate and provide energy-efficient design and operation. In this paper we survey the apportionment problem in different fields such as computer systems, wireless sensor networks, mobile devices and energy-efficient buildings. The challenge lies in how to attribute a share of the total energy consumption to the responsible entities (e.g., applications, processes or users of the system). Our analysis identifies that energy apportionment is a common problem in different fields and reviews five previously applied energy apportionment policies. Also, the work identifies relevant further research.

Mobile location sharing: an energy consumption study

The use of a mobile devices battery for frequent transmissions of position data in a location sharing application can be more expensive than the location retrieval itself. This is in part due to energy-agnostic application development and in part dependent on choice of protocols. This paper studies the lightweight Message Queuing Telemetry Transport protocol (MQTT) as an application layer protocol on top of the third generation cellular communication. The energy efficiency and amount of data generated by the public/subscribe MQTT protocol is experimentally compared against the Hypertext Transfer Protocol (HTTP), which is currently used in typical location sharing applications. The evaluation results indicate that MQTT is a good candidate as a protocol for location sharing. At comparable bandwidth and energy expenses MQTT offers better quality of user experience, since the subscribers are notified at once when the location of some interesting client has changed. Our measurements show that MQTT is more energy-efficient than HTTP in the idle state and when the number of other users with whom the client shares location is low. When the number of users increases beyond 3, HTTP becomes the preferred option in terms of energy efficiency at the cost of a higher notification delay.