Today a smart phone has a processing power of about 200 megaflops, a laptop is offering some tenth of gigaflops, a PlayStation hundreds of gigaflops. Imagine to find the way for orchestrating millions of said Users’ devices, harnessing their idle processing and storage power: we can achieve bigger capacity than a supercomputer, like Titan (today number one, capable of 18 petaflops).

This distributed platform of edge devices can indeed create a sort of processing and storage fabric that can be used to execute any network function and to provide any sort of ICT services and applications. The components of this fabric can be seen as: CPU/GPU, SSD (Solid State Drive), HDD (Hard Disk Drive) and link (and this is perfectly in line with the “disaggregation of resources” targeted by the Open Compute Project).

One may imagine these components aggregating dynamically in an application-driven “flocking”. And, in the same way as birds with simple local behaviors are optimizing the aerodynamics of the flock (which is solving a “constraints optimization problems” by using very simple local rules), the flocking of component can follow dynamically application-driven network optimizations.

The problem is finding these local rules. Not only, but also the optimal way to allocate and dynamically migrate Virtual Machines and data (which are representing also states). Let me make an example, a very simple model. Imagine, just for didactical reasons,  to consider the equivalence between the time of one CPU cycle and the time of a step in a walk. The latency in accessing a SSM (e.g., DRAMs) can be estimated as around tenths of CPU cycle, tenths of steps in our example. But if you wish estimating the latency in accessing the HDD, i.e. the stored data (also including the latency of the network links, RTT), then overall it results the time to make a walk of about 10 000 km.

I’m sure that solving this constraints optimization problem…will mean allocating processing and storing data as closer as possible to the Users!

Open Compute Project (OCP) is an initiative started (on April 2011) at Facebook with the goal of developing “one of the most efficient computing infrastructures at the lowest possible cost”. The project is pursuing an open hardware approach, to “develop servers and data centers following the model traditionally associated with open source software projects”. In other words, the project is aiming at disaggregating the servers of data centers into elementary sub-systems that can be swapped out depending on applications’ needs. Memory, network, and storage resources would be disaggregated and shared across the rack and fast interconnects (e.g., 100 Gbps) will provide the binding of these elementary sub-systems.

And next target of OCP appears to be “disaggregating the network”. Basic idea is developing network switches that will look like more disaggregated open servers. Then, instead of having a vendor-specific network OS, one may want to load with any trusted software provided by developers. This OS-agnostic disaggregated switch is expected to enable a faster innovation in the development of networking hardware as well as costs drops in infrastructures exploitations; industries like Intel, Broadcom, VMware are already moving in this direction, also in the context of other similar initiatives.

Technology advances exploited in initiatives like this are concrete milestone in the ICT Fabrics vision we’ve elaborate some posts ago and this paper: imagine disaggregating (from a functional viewpoint) processing, storage and networking at more granular component and then composing, orchestrating them (beyond the borders between date centers and networks) through fast optical interconnections.

As Roberto mentioned in the post Telecommunications as a gigantic supercomputer this is not just a speculation, but it is likely to become a real medium-long term r-evolution capable of enable new networks and new services. The edges (around the Users) will look like virtual Data Centers morphing dynamically in space and time and capable of storing big data and information and the “flocking” of resources component will be “application-driven” without any networks-DCs borders.

As I pointed out in the previous two posts, as human beings we need much more bandwidth than the one we get today in most parts of the world. From a technical point of view, even the lowest capacity infrastructure we can deploy today (it is already being deployed) is more than enough to meet our needs. Unfortunately the problem is not lack of technology but lack of money and lack of culture.

Credit: FCC

In some parts of the world there is confidence that ultra broadband, over the 100 Mbps (and I would like to set the need at 500 Mbps downstream and 200 mbps Upstream) is already a defined roadmap, as shown by the graph here forecasting UBB penetration in the US.

In many parts of the world bringing that much bandwidth will be a dream for at least two decades if we think about using optical fibre (as it is the case in the US depicted in the graph). Developing economies have seen an amazing progress in terms of telecommunication penetration (not just China and India, also Africa is moving towards a 100% penetration of cell phones) but the bandwidth provided is clearly limited.

A bandwidth of a few Mbps is within reach almost everywhere using wireless communications (it may take this all decade to get there) but moving from a few Mbps (even with FRA – Future Radio Access) to hundreds of Mbps made available to all homes is beyond the economical possibility of most Countries. That sort of bandwidth requires pervasive fibre infrastructure (with radio drops in cells that are no more than 100 m, possibly smaller).

Alternatively, it requires completely different paradigms that today are just a matter of speculation.

In a number of Countries, like most of Western Europe, a pervasive fibre infrastructure is economically possible, but it is not able to generate that kind of ROI (Return Over Investment) that stimulates private investment. Private Public Partnership in these cases is almost mandatory. However, even a PPP is not enough unless there is a commitment to leverage the UBB, by re-engineering the Society processes (eGovernment, eHealth, eEducation, eLogistics, eProduction….).
UBB can increase the efficiency at Country level, estimates are in the order of 5-8% corresponding to a huge return of investment at Country level, able to recoup the investment in ONE YEAR! However, the destruction of “inefficiencies” results in destruction of jobs, and companies that are today living out of this inefficiency. And the corresponding creation of new jobs is not in synch with the destruction…

Hence, the risk is that the PPP investment does not result in an increased efficiency but in an further burden on the Society, increasing the cost.

Having seen the theoretical bandwidth consumption capability of our senses (using grossly simplified measures but that is ok for the point I want to make…) we have to realize that our senses do not consume bits…. they consume images, sounds, fragrances, acceleration and so on… Hence we need to convert bits carried by the network into these images, sounds…

A GPON infrastructure can sustain the bandwidth matching our sense’s resolution

Since we have seen that what gets the lion’s share, in terms of bandwidth, are the eyes we can focus our attention on them.And the translators that we use to convert bits into images are called… “screens”. Today we have HD screens (HDTV) that can display 2 Mpixels and require 10 Mbps bandwidth. The first 4k screens are becoming available, although we can expect them in full swing by 2015; they have 8 Mpixel resolution (like our eyes) and require 70 Mbps bandwidth. By the end of this decade we might see the first mass market 8k screens with a resolution of 32 Mpixels, exceeding our “brain” vision capability and providing a full immersion sensation: that will require a bandwidth of 150 Mbps.

Of course that goes for a single user. In a home you have several users although it is likely that the shift towards higher resolution screens will be gradual: only one 4k screen in the home for a while and then, some 5-7 years later only one 8k screen. Actually, 8k screens are not likely to become pervasive in the home, there will be probably just one, since it only makes sense if it is really big (over 80″, better over 100″) and you don’t have that much space in a normal home. You are likely to have, as it is common today, several screens but they will be HD or lower resolution, a few (2-3?) 4k and one 8k. Hence, it makes sense to assume as an upper boundary for bandwidth requirement at home something like 300 Mbps.

Of course, in other ambient, the bandwidth demand can and will be greater but in terms of economics the mass market is the one leading (for both cost and revenues).

What we can see is the the lowest bandwidth fibre infrastructure, the GPON is and will be providing more capacity than what is demanded. Hence it is a future proof infrastructure.

As LTE, the Long Term Evolution, is being deployed offering a theoretical data speed of up to 75 Mbps (it is very very theoretical, a few tens of Mbps are already problematic…) researchers are busy looking ways to increase the wireless data speed in what will come after the LTE, the so called FRA, Future Radio Access.

Fast Array: Samsung’s ultrafast wireless transmitter and receiver includes 128 antenna elements – 64 for transmitting and 64 for receiving data.
Credits: MIT Technology Review

Researches at Samsung have just announced the success of an experiment to transmit at 256 Mbps error free data stream using 28GHz as a carrier at a distance of up to 200m. They have also managed to transmit up to 512 Mbps with negligible error rate.

Actually, they performed a successful experiment few weeks ago (and information was leaked out to the press…)  but at that time the high bit rate transmission took place with a stationary receiver (and sender of course). Now, they have performed the experiment with the sending antenna placed on the wall of a building and the receiving device was moving at a jogging pace, 8km/h. So this time it really means much more.

They also demonstrated that transmission can be sustained even if part of the building is blocking the line of sight (at least a bit…).

As you know, the problem with wireless high data rate transmission (not just wireless, actually) is that you need to have a broad spectrum at your disposal and the current wireless space is already very crowded. So if you want more spectrum you need to you much higher bearer frequencies (like the 28GHz used by Samsung researchers). The problem is that the higher the frequency the more issue you have of propagation and absorption…

Moreover, you have to manage noise, multiple path and you name it… (and this are more specific in wireless communications, with optical fibre you do not have this kind of headache).

In LTE several techniques are used to decrease the impact of noise and multiple paths, like MIMO, Multiple Input Multiple Output. Basically rather than using a single antenna engineers are using 2 or 4 antennas, both in the receiver and in the sender part. By comparing the signals captured by each antenna with the ones captured by the other they are able to cancel out noise and multiple path, up to a certain extent.

Well, in this experiment Samsung researchers have been using 64+64 antennas (for the receiving and sending part respectively). Of course, comparing the various signals received by so many antennas requires a good deal of processing power  and in turns this is going to drain the battery. But we know that given sufficient time the progress of electronics will bring the power consumption down and increase the performances so there is a reasonable hope that it will become possible, at least in this respect.

The transmission distance will remain a crucial limitation. Here they managed to send over a 200m range, and that might be increased a bit (in the previous announced experiment they spoke of distance up to 1km and 1Gbps bit rate) but as bit rate increases a balance will have to be achieved between power, interference, spectrum and bit rate and this will tend to limit the distance of transmission.

Hence, as we are progressing towards a wireless world with bit rates that compare to the ones offered by fixed lines we are going to need plenty of fibre to sustain a pervasive backhauling.

The tiny KL02 microcontroller, made by Freescale, was created to enable swallowable wireless computers, and contains an energy efficient processor, memory, and RAM.
Credits: Technology Review

Freescale has announced the availability of a micro chip, basically a computer with integrated radio part for transmission that can be considered a midget cell phone. It is less than 2mm*2mm, as you can see in the photo on the left if you look close at the tiny bit on the top of a keyboard key.

It contains a processor, a storage and a wifi communication port plus a tiny battery that can be charged in different ways depending on the application.

You can get the details in an article on Technology Review.

Notice that Freescale is targeting this chip to the pharmaceutical market with the idea of inserting it in every pill that you swallow. So the header of this post is not just to catch your eye…

Indeed, in the near future we can expect to see more and more pervasive electronics embedded or pigging back on any object. The low power requirement of these micro chips (indeed it is correct to call them micro!) makes it possible to use scavenging as source of power.

There are a number of promising ways to scavenge ambient power, from using the HCl in our stomach for swallowed pills, to harvesting glucose energy for chips embedded under the skin to systems converting vibration or temperature differential for chips disseminated in the ambient.

Once the issue of powering is solved we will see plenty of electronics pervading our ambient, our body and becoming a seamless presence in our life…

Optical transmission operates in the THz range and photons do not interact with each other nor with atoms aggregated in a specific way like the ones forming an optical fibre. On the contrary, electrical transmission operates up to a few GHz and electrons interact with one another and with the ones in the medium -copper wires. A fibre doesn’t get warm when you use it, a copper wire does!

The “beamer” transmitting at 200-280 GHz to a receiver on the skyscraper in the background, achieving 40Gbps bit rate.

Radio waves are a bit in between. The waves that can be conveniently used in transmission are in the range of MHz up to a few GHz and do not interact one another, but can be absorbed by atoms (that’s the way you cook the chicken in the microwave oven, operating at 1.2GHz). The problem with waves is that it gets difficult to separate one from the other (interference) and from the background radiation (noise). Another -general- problem is that you can only cram as many bit per Hz and no more (Shannon Theorem) and therefore if you want to transmit more bits per unit of time you need a broader spectrum and this is scarce on radio waves.

Well, researchers of the Fraunhofer Institute of Applied Solid State Physics and the Karlsruhe Institute for Technology have found a way to use radio waves in the hundreds of GHz and more precisely the spectrum between 200 and 280GHz to transmit information. That 80GHz of spectrum allows for a 40 Gbps transmission (and if they were to be used at the same efficiency level we have reached today in cell phone networks they could sustain up to 160 Gbps!), a capacity that compares to the one provided by an optical fibre with a single “channel”.

This kind of capacity has been sustained over a 1km link and given the frequency used the transmission is less sensitive to atmospheric conditions (as it is the case in optical communication over air – fibre over air- that suffers from fog and rain). Actually, researchers expect to be able to extend the range, and the capacity, over the next few years.

This kind of transmission is “point to point”, it is therefore quite different from a radio cell that covers a broad area. It can be used as a replacement for an optical fibre, getting rid of deployment cost. One application can be to serve rural areas. The receiving point will have to create a radio cell to provide access over a broad area.

The high frequency chip only measures 4 x 1.5 mm², as the size of electronic devices scales with frequency / wavelength. Photo: Sandra Iselin / Fraunhofer IAF

The results of the Fraunhofer researchers represent the new record for radio transmission capacity so far.

The researchers have  created a chip able to sustain this high capacity transmission. Given the high frequency being used the size of the antenna can be very small (the rule of thumb for the antenna dimension os half the wavelength and that for a frequency of 200 GHz is 1.5mm) and indeed the chip, shown in the photo on the left, is very tiny.

I guess that in the future we are going to see many more applications of very high radio frequency to connect objects in a small ambient.

The Human Brain Project, HBP, has entered into its first phase (after a 2 year preparation work) and within 18 months should deliver a first prototype of a brain simulator based on reverse engineering of brain connections (connectomics).

The project is funded with a 1 billion € by the EU over a period of seven years. According to Henry Markram, the project leader, the brain simulator will be able to peer into 600 brain disorders and help in their tackling. He also “feels” that such a simulator may be implanted in a robot providing it (him?) the capability of thinking and being sentient.

Blue Brain Project: speed vs. memory (credit: Henry Markram)

As shown in the diagram sketched by Markram, given sufficient processing power and storage capacity it is possible to simulate a brain, the more capacity available, the more complex brains can be simulated.

We have now the processing power and storage capacity to simulate a cellular mesocircuit. Indeed that simulation was achieved in the preparation phase of the HBP. It simulated 100 neocortical columns for a total of 1 million neurones. And we are close to be able to simulate a rat brain: this is planned in 2014. For the human brain, whose complexity is estimated as 1,000 times a rat brain, we need to wait for the next decade, ten years from now.

The jury is still out in the definition (and acceptance) of what thinking and being sentient really means. In general we, humans, have a strong un-easiness in believing that a robot one day might become a thinking-sentient being, as we have believed for millennia that only human beings are “sentient” and self aware (have a soul…). In the last decades we have had experimental proof that even some insect have a certain degree of self awareness and that in general it is impossible to draw a dividing line between sentient, thinking self aware beings and those who are not.

As we are learning more and more about the physical underpinning of being sentient we are also entering an unchartered space where we will (might) encounter sentient being that we are creating.

In the last few days I stumbled onto some amazing news concerning Quantum Computing, Storage and Communications.

Google, together with NASA and the Universities Space Research Association, have launched an initiative to study if and how quantum computing might determine breakthroughs in machine learning. They will use the D-Wave Two quantum computer (see also this post) which will be  installed at the NASA Advanced Supercomputing Facility at the NASA Ames Research Center in Mountain View, California.

The chip at the heart of one of D-Wave’s computers (credit: D-Wave)

Let’s see the motivations. Learning algorithms normally operates by searching for a function fitting a set of data. This search can be formulated in terms of  minimizing an objective function, a very hard mathematical problem. Whilst classical computing normally uses what’s called a ‘gradient descent’ approach (i.e., moving towards a local optimal solution by slowly moving down on a curve), Quantum Computing could exploit the “tunnel effect” in finding better optimal solutions, and in by far shorter time !

Almost contemporary  an amazing scientific result , achieved in collaboration between the ARC Centre of Excellence for Quantum Computation and Communication Technology based at UNSW, the Australian National University and the University of Melbourne, has been published in the journal Nature. The achievement concerns a way to detected the spin, which is a quantum state, of a single atom using a combined optical and electrical approach. Indeed, a potential milestone for a developing networks of Quantum Computers.

Eventually, this third piece of news claims the world’s first quantum memory capable of storing the shape and structure of single photons. Researchers at the University of Science and Technology of China in Hefei have created a single photon with a spatial structure, stored that photon in a cloud of rubidium atoms and then released up to 400 nanoseconds later. In this post, Roberto already mentioned that at the University of Michigan, Ann Arbor, they have found a way to create a single photon emitter using technology that is industrially available, the one of silicon.

Another piece of news in that the Optical and Quantum Communications Group at MIT’s Research Laboratory of Electronics (RLE) have experimentally demonstrated a new quantum communication protocol for achieving practical quantum encryption.

Well, in view of these big efforts, and tangible results (which are becoming even industrially available) I’m wondering if the Quantum Singularity is really that far as one normally think…

Technology progresses constitute the fueling force of innovation. And they are in some way predictable. We’ve mentioned several times that one of the areas where SDN and NfV (Network function Virtualization) paradigms will exploit at best their fueling force will be the “edge” of current networks. This is where an incredible amount of communications, processing and storage resources is progressively accumulating. Actually the edge is also where “intelligence” has migrated, and it is where innovation is more urgently needed to overcome current “ossifications”.

So it’s quite simple and straightforward predicting that the edge will be the most active and critical segment of the networks, in terms of innovation, strategy, and investment. Services and traffic dynamics will be more and more in the hands of Users ! This is like saying that in the future it is likely that we’ll see a transition towards a network controlled by applications. This transition will destroy the principle of the central control in delivering end-to-end quality and hence the very foundations of today’s networks. Even  more, we may sat that big data will be found more and more at the edge, i.e., in the Users’ devices, rather than in the Data Centers.

This interesting piece of news goes in this direction: indeed the idea of deploying SDN-like capabilities and protocols into Users’ devices Operating System (e.g., Android) is a way to reach the very edge of the network, for example the Users’ mobile phones. Imagine each device becoming like a “mini blade” of virtual global data centers at the edge!

As Roberto pointed out, in yesterday post, the tremendous amount of processing and storage capacity potentially made available (just waiting to be harvested) by cell phones spread everywhere, will become a sort of nervous systems capable of harvesting (also through sensors networks) a huge variety of data.

It becomes then easy predicting that future networks and services management will be more and more controlled by applications, i.e., through the use of the big data available at the edge of the networks (i.e., up to terminals/environment). And when SDN-like capabilities and protocols will enter into Users’ devices Operating System, the edge will become a virtual global data center offering tremendous amount of processing and storage capacity. This probably represents a cultural challenge for Network Operators, but there are huge biz opportunities for us in this transformation.