In many of the challenges faced by the modern world, from overcrowded transportation systems to overstretched healthcare systems, large benefits for society come about from small changes by very many individuals. We survey the problems and the cost they impose on society, and describe a framework for designing "nudge engines"---algorithms, incentives and technology for influencing human behavior. We present a model for analyzing their effectiveness and results from transportation pilots conducted in Bangalore, at Stanford and in Singapore, and a wellness program for the employees of Accenture-USA.

Datacenters are fascinating places, where the massive scale required to deliver on-line services like web search and cloud hosting turns minor issues into major challenges that must be addressed in the design of the physical infrastructure and the software platform. In this talk, I'll briefly overview the kinds of applications that run in mega-datacenters and the workloads they place on the infrastructure. I'll then describe a number of challenges seen in Microsoft's datacenters, with a goal of posing questions more than describing solutions. The audience will leave with a better understanding of how economic factors, technology issues, and software design interact when creating low-latency, low-cost, high availability services.

Interest has been growing in powering datacenters (at least partially) with renewable or "green" sources of energy, such as solar or wind. However, it is challenging to use these sources because, unlike the "brown" (carbon-intensive) energy drawn from the electrical grid, they are not always available. In this talk, I will first discuss the tradeoffs involved in leveraging green energy today and the prospects for the future. I will then discuss the main research challenges and questions involved in managing the use of green energy in datacenters. Next, I will describe some of the software and hardware that researchers are building to explore these challenges and questions. Specifically, I will overview systems that match a datacenter's computational workload to the green energy supply. I will also describe Parasol, the solar-powered micro-datacenter we have recently built at Rutgers University. Finally, I will discuss some potential avenues for future research on this topic.

In this talk we present a preview of the upcoming Springer monograph. We use the islands of Sao Miguel and Flores to illustrate an end-to-end IT framework for enabling deployment of new hardware technologies into the existing electric power systems at value. We explain how the proposed IT framework could evolve in synchrony with the existing utility control centers and their Supervisory Control and Data Acquisition (SCADA). We illustrate how such an IT approach could transform the islands into green islands in which expensive diesel generation is replaced by a mix of wind and solar power plants, and fleets of electric vehicles. In particular, we show how carefully architected IT enables electricity service at value and according to choice. This is done without damaging continuity of services defined according to terms between the service providers and users. We illustrate dynamic deployment of wind and solar power, responsive demand, including PHEVs, according to the value they bring to those needing them. Most importantly, the overall operations and planning process becomes much more manageable and simpler when enabled by the right IT.

Today, buildings account for nearly 75% of the electricity usage and 40% of the total energy usage in modern economies. Consequently, techniques for reducing the energy and carbon footprint of buildings has emerged as an important research topic. Demand side energy management refers to techniques employed by smart buildings or its occupants to modulate the energy usage for various energy- or grid-level optimizations. In this talk, I will argue that modeling and prediction of electrical loads is a key ingredient of any demand-side energy management technique. I will describe opportunities and challenges in modeling these loads and describe our recent work in empirically characterizing and modeling common residential loads. I will also describe how better modeling can result in more effective demand side energy management and better energy efficiency improvements.

In this talk, we present a holistic end-to-end management solution - Net-Zero Energy Data Center - for optimizing the design and operation of data centers to minimize the life time energy cost and carbon footprint. We discuss several key techniques that have been developed: (1) optimizing the design and size of data center energy infrastructure; (2) scheduling IT workloads based on (renewable) resource availability and SLAs; (3) dynamically provisioning IT and cooling resources according to needs and integrated management of IT and cooling resources; and (4) improving the effective utilization of servers by managing the collocation of critical (e.g., interactive apps.) and non-critical (e.g., batch jobs) workloads on virtualized multi-core servers. We describe a prototype implementation of Net-Zero energy data center that achieves Net-Zero grid energy use while meeting all critical performance criteria and incurring minimal capital infrastructure expense - lowering the total data center power costs by 30% and dependence on a larger power grid by more than 80%.