Hello,
I had an iCOMEN boiler switch that worked for many years. And I used iCOMEN app on my phone to manage it. Short time ago app started to have an error message that it cannot connect to the server, and after some time the device also stopped working.
Some of you may know that I took at shot at building an alternate geofencing solution for Vera. The core of it was system agnostic, using the OwnTracks application and AWS lambdas to track devices and keep a central data, then disseminate that to the Vera via a websocket-based plugin. It worked with other apps as well, including Tasker and GPSLogger, but of the dozen people that were testing it, most used OwnTracks.
A lot was learned in the process, not the least of which is that the success of any such solution is highly dependent on the phone and its settings. Phone manufacturers love to set things up for the longest battery life, of course, but that's usually very anti-geofencing behavior. In the case of at least one brand, it was unusable and the settings could not be modified. It was also cost-prohibitive to maintain on Amazon, as AWS grabs a dime here and a dollar there and before you know it, it added $100/month to my AWS bill, which my wife deducted from my Scotch budget. Unacceptable.
But it's quite reasonable to use OwnTracks to a local endpoint, and I could pretty easily replicate the functionality as a local application, or maybe even as an additional endpoint built into MSR's API (still separate port and process, but in the package).
So the question really is... would you do it, or would you be too concerned about the security risks associated (e.g., dynamic DNS and NAT mapping in the firewall necessary for the phone to contact the service when not on LAN)?
Hello forum instigators.
Not sure who host/runs the forum software but a couple of challenges:
The chat is not currently usable, as the scrolling is all not right and it's not possible to read chats or send chats reliably.
There are a lot of female members that should perhaps be on another forum; where they can advertise their skills more appropriately. Note: I agree it's a job, like any other.
Whoever you are - thank you for your invaluable work.
I run a B&B and am looking for a way to turn the lights off whenever a room is unoccupied for X amount of time. The guest should still be able to turn the lights on and off manually, but should not be able to disable the auto turn off feature if the room is unoccupied.
I guess I am looking for a light switch with a built in presence sensor? I guess a presence sensor would be better as if it is a motion sensor, the lights may go off unwanted if the guest fails to make sufficient movement e.g. if the guest is lying down watching a film.
Are there any products on the market that would work for my application?
I currently have an HVAC system in the attic - for heating and A/C. 120v is supplied to the unit to run the gas heating. A/C uses 240v. I have an ecobee thermostat...which sometimes goes offline....not often. When it goes offline, I need to turn the 120v power to the HVAC system off and then back on (the ecobee gets its power from the HVAC system). That resets the ecobee and all is fine. I spend the summer away from this house and if the ecobee goes offine..I have no current method to reset the HVAC 120v power remotely. My idea is to replace the current 120v plug in the attic with a smart plug...then I can remotely turn the 120v power off and the ecobee will reset and come back online. I use Wyze and Lutron Casita in the house currently and was hoping I could find an in-wall smart plug from Wyze or Lutron. Obviously, I don't need diming, etc...just the ability to turn the plug power on/off. I've seen some options...but one problem I have is the attic can reach up to 135F in the summer...many of the smart plugs I've seen are not rated for that temperature. Might any of you have any thoughts on a smart plug I might want to look at? I don't want to invest in anything that would require a new hub - so either WiFi based or Casita HUB based. I need 120v and 15amp ratings. Thanks in advance.
Hello,
I am in search of a device capable of using Bluetooth to connect with a smartphone and serve as its primary sound source on demand. This device should function similarly to conventional Bluetooth headphones, which automatically become the phone's sound output upon activation. However, this device should differ in that it transmits the audio signal to an amplifier via a jack, SPDIF, or similar connection. Alternatively, it could be an integrated amplifier that directly sends the signal to passive speakers.
The control of this process should be manageable through an API such as MQTT, REST, MODBUS, or similar. Are you aware of any devices that operate in this manner?
The concept is as follows: upon entering the bathroom, I would press a wall-mounted switch. This switch would send a signal to the Bluetooth device, prompting it to connect to my smartphone and seamlessly continue playing the audiobook I am currently listening to. Instead of using the phone's speakers, it would seamlessly start playing through ceiling-mounted speakers.
Many thanks 🙂
Hi folks,
I currently have some cheap Zigbee hub and some Amazon Alexas running my smart home which mostly consists of Zigbee power strips and Zigbee battery powered switches.
It all worked OK originally, but now whenever I press a Zigbee switch the light in the corresponding plug switches on then immediately off again.
If I ask Alexa to turn the light on it works fine. Likewise if I switch it on from my phone.
Any ideas what the issue could be?
I've tried unplugging the hub a number of times but that doesn't seem to fix it.
I was thinking about getting a Homey Pro 2023 to speed things up (tmas the Zigbee hub seems to be really slow now as well, for some reason) but I'm not sure about that either.
Any suggestions greatly appreciated!
Looking for a recommendation:
Locksmith is trying to talk me into the Yale Assure Lock Touchscreen with Wi-Fi and Bluetooth - the original 1st generation because they said it's built better than the Assure Lock 2. Any thoughts on this? Which would you recommend?
I see Mul T Lock makes a cylinder (KW-KIDYRL) for Yale Smart Locks. Would this fit the 1st gen Assure Lock, as well as Assure Lock 2? Has anyone tried replacing the cylinder with this on either lock?
Other smart lock I was considering is the Schlage Encode Plus.
Thanks!
Hi. So when I had my house build I ran a bunch of stuff, one of which being two pairs of speaker wires to each bedroom and to 4 spots around my living room… Over the years I have used them here and there with different success.. But today they sit in my walls just unused.
I converted all the cat6 or 5e (I don’t remember) over to basically eithernet jacks. The cable coaxial well it’s there but now unused. But I was thinking there has got to be some use for two pairs of speaker wires to each room. Can I make them usb plugs? Not sure so looking for ideas.
Thanks in advance for your thoughts on this.
Kevin
Hey guys...
We are replacing the heat pump and furnace this week and I will also need to replace my nest thermostat at the same time 'cause Nest is ending the cloud thing end of the month.
Anyway, I'm looking to use the
T6 Pro Z-Wave Programmable Thermostat | Smart Home | Honeywell HomeThat's what the heat pump installer recommend BUT, using Nest I was also using it to control the home humidifier using a single wire connected to nest... but no low voltage thermostat is able to do that, I checked all of them...
So I need some help on how I can do that, to connect the home humidifier using zwave also....
Hi
We are looking for a solution where we can detect presence of a «thing» (people , car , dog, cat, and more..
We need:
fast detections, 1-3 seconds in range from 0 to 20 m from «base» fysical «client» , chip , transmitter , unit. base , receiver placed at a door, gate, house, etc uniq Identifying wirelessThe client:
no need for pressing any thing (no buttons) battery , hoply 2-5 years battery time.Have someone done anything like this?
What technologi will be best?
Hey everyone, I'm currently working on developing a bed sensor that can detect when you're out of bed. It could be used to trigger other smart home gadgets, like lights or blinds, temperature etc.
The sensors are placed under the legs of your bed post. Should look and feel like "smart furniture pads" with size 2 inches in diameter and 1/4 inch thick.
Before we go any further, I'd love to get your thoughts on this - would a bed sensor like this be something you'd find useful? We're still in the early stages of development, so any feedback you have would be greatly appreciated. Thanks in advance!
@DesT, fenced code blocks display differently after the upgrade.
abc defThe above should display as abc and def on two separate lines. This works. But this fails:
verbose: true config: data: "auto"The above should display as three lines, verbose: true, config: and data: "auto", but this fails. In order to make it display properly, I now have to open the fenced code block with ```text (specify language, generic text). This displays without highlighting. The words yml and yaml (and the all-caps versions) don't seem to be recognized. I can also use js to get JavaScript highlighting, but this isn't great for YAML. Here's the same block with the language (text) specifier added (no other changes):
verbose: true config: data: "auto"Sure, we can start adding language specifiers to our new posts, but I suspect if we start digging around old posts, we're going to find a lot of broken display of the fenced code blocks (plain ``` at the start with no language specifier) in the thousands of old posts in these forums, upon which people still rely for answers and information.
Log file snippets also get similarly brutalized:
[###BUILDVERSION###]2023-04-26T19:41:51.683Z <ZWaveJSController:NOTICE> ZWaveJSController#zwavejs added file logger to zwavejs.log [###BUILDVERSION###]2023-04-26T19:41:51.747Z <ZWaveJSController:WARN> zwavejs_capabilities defines x_zwave_device_cfg, which is not consistent with the recommended naming [###BUILDVERSION###]2023-04-26T19:41:51.747Z <ZWaveJSController:WARN> zwavejs_capabilities defines x_zwave_mfg_spec, which is not consistent with the recommended naming [###BUILDVERSION###]2023-04-26T19:41:51.747Z <ZWaveJSController:WARN> zwavejs_capabilities defines x_zwave_device_ver, which is not consistent with the recommended naming [###BUILDVERSION###]2023-04-26T19:41:51.747Z <ZWaveJSController:WARN> zwavejs_capabilities defines x_zwave_values, which is not consistent with the recommended naming [###BUILDVERSION###]2023-04-26T19:41:51.837Z <ZWaveJSController:INFO> ZWaveJSController#zwavejs connecting to ws://192.168.0.10:3000 [###BUILDVERSION###]2023-04-26T19:41:51.874Z <ZWaveJSController:NOTICE> ZWaveJSController#zwavejs connected [###BUILDVERSION###]2023-04-26T19:41:51.874Z <ZWaveJSController:INFO> ZWaveJSController#zwavejs sending connection initialization [###BUILDVERSION###]2023-04-26T19:41:51.931Z <ZWaveJSController:INFO> ZWaveJSController#zwavejs greeting from server: [Object]{ "type": "version", "driverVersion": "10.16.0", "serverVersion": "1.28.0", "homeId": 3631280043, "minSchemaVersion": 0, "maxSchemaVersion": 28 } [###BUILDVERSION###]2023-04-26T19:41:51.932Z <ZWaveJSController:INFO> ZWaveJSController#zwavejs performing initial inventory [###BUILDVERSION###]2023-04-26T19:41:52.325Z <ZWaveJSController:INFO> ZWaveJSController#zwavejs manufacturer-specific data for 134 (AEON Labs) from package ver 22315.1 [###BUILDVERSION###]2023-04-26T19:41:52.328Z <ZWaveJSController:INFO> ZWaveJSController#zwavejs configuring node 1 endpoint 0 (entity "1-0") [###BUILDVERSION###]2023-04-26T19:41:52.339Z <ZWaveJSController:INFO> ZWaveJSController#zwavejs manufacturer-specific data for 543 (Elexa Consumer Products Inc.)I think this is going to be a problem. Is there a way in NodeBB to configure the default language for fenced code block markdown for the entire forum so that these display more as they did before the upgrade?
EDIT: Examples below of old posts with corrupt formatting now:
https://smarthome.community/topic/1101/dynamic-groups-controller-filter-expressions
https://smarthome.community/post/11362
This last old post is interesting, because the first block displays incorrectly, but the second block is OK. In playing around, there seem to be triggering character sequences, suggesting that the markdown processor is trying to "guess" the language but not getting it right, perhaps:
Can anyone help with the MIOS UI5 weblink? Not the getvera one.
Still running UI5 on a couple of sensors & lights and need to tweak PLEG but for the life of me I can't remember the link to tunnel back to the trusty machine....
The wifi on my router is turned off, and wifi around the house is provided using a mesh - 3 units altogether (one connected directly to the router) that are spread around the house.
I would like to start automating certain tasks around the house and intend to try adding a few smart sockets to my setup.
The mesh system I have supports both 2.4GHz and 5GHz, and does not provide me with the option to control them - i.e. turn one or both on/off, give each a different SSID, etc.
The devices I wish to purchase/use only support 2.4GHz.
Will turning the mesh units off and temporarily turning the 2.4GHz wifi on the router to allow me to set them up be enough? Will I then be able to return to my usual setup and everything will work as it should?
Many thanks in advance
ChatGPT samples:
Me:
Tell me about an iot program called openLuup.
It:
OpenLuup is an open source home automation system that is built on the VeraLuup platform. It is designed to be easy to install and configure, and provides users with a powerful and versatile way to control their home automation devices. OpenLuup offers a wide range of features, including support for many popular home automation devices, scheduling, scripting, and integration with other services. OpenLuup is designed to be customizable, allowing users to create their own home automation systems. It is an excellent choice for those looking to create their own home automation system without spending a lot of money.
Me:
Write an iot program using openLuup.
It:
--openLuup IoT Program-- -- Initialize Variables -- local device_id = "MyHomeDevice" local temperature_sensor_id = "MyTemperatureSensor" local temperature_threshold = 75 -- Create Devices -- luup.create_device("OpenLuup Temperature Sensor", 0, device_id, "D_GenericSensor1.xml", "I_GenericSensor1.xml", "S_TemperatureSensor1.xml", "") luup.variable_set("urn:upnp-org:serviceId:TemperatureSensor1", "CurrentTemperature", 0, device_id) -- Start Timer -- luup.call_delay("check_temperature", 10, "", false) --Function to Check Temperature-- function check_temperature() local current_temperature = luup.variable_get(temperature_sensor_id, "CurrentTemperature", 0) --Check Temperature Threshold-- if current_temperature >= temperature_threshold then --Send Alert-- luup.call_action("urn:micasaverde-com:serviceId:HomeAutomationGateway1", "SendTextMessage", {PhoneNumber="1234567890", Message="ALERT! Temperature exceeded threshold!"}, 0) end --Reset Timer-- luup.call_delay("check_temperature", 10, "", false) endMe:
Write an iot program using openLuup.
It:
Write an iot program using openLuup. -- openLuup IOT Program -- -- Variables local lampState = false local lampTime = 0 -- Functions function lampTimer() if lampTime > 0 then lampTime = lampTime - 1 if lampTime == 0 then luup.variable_set('urn:upnp-org:serviceId:SwitchPower1', 'Status', 0, lampDeviceID) lampState = false end end end -- Setup luup.call_delay('lampTimer', 60, 0) -- Main Loop while true do -- Check for motion if luup.variable_get('urn:micasaverde-com:serviceId:MotionSensor1', 'Tripped', motionSensorDeviceID) == '1' then if not lampState then luup.variable_set('urn:upnp-org:serviceId:SwitchPower1', 'Status', 1, lampDeviceID) lampState = true -- Set lamp timer to 5 minutes lampTime = 300 end end luup.sleep(1) endWhat??
luup.sleep(1)Not good - looks like I still have some semblance of a job to fulfill.
Me:
An iot program called openLuup was written by akbooer. Who is akbooer?
It: (note: answer redacted and as I understand it, also incorrect re: AltUI):
akbooer is the pseudonym of the software developer and home automation enthusiast. He is the creator of the openLuup home automation software, which is an open-source version of the Vera home automation system. He is also the creator of the AltUI graphical user interface for openLuup.
Me:
Who created of the AltUI graphical user interface for openLuup.
and
Me:
Who created of the AltUI graphical user interface for the home automation system Vera.
Names two different people - mmmm.
Regardless very impressive - give it a few more years.
...which I'd like to do. I know I go about these things all wrong (namely think of something I'd like to do, then try and work out what I need to know) but that's me 🙂
Just looking for some pointers on what I should google for really:
What I'd like is to provide a selection of (basically two word) phases which I can select from randomly (or even pseudo randomly) and pass to Alexa to be spoken. There are 10 such phrases only.
So what should I be reading up on to get me started?
TIA for any guidance
C
The Home Automation Controller Pyramid
-
@CatmanV2 said in The Home Automation Controller Pyramid:
But what they (appear) to be shipping a beta seems way too immature. When would you think there's a production product? Feels to me like 2021 some time?
yes. current system is barely usable. They are targeting next September, and they can improve fast, because they want to release a new build every 2 weeks. The real problem is their priorities: in order to migrate, you have to unpair and pair again all your devices. It's impossible for me (70+ devices, sometimes buried into boxes I really don't know where, since they were first installed by my electricians when building the house) and for many more people.
The concerning problem is that it's quite impossible for them to have plug-ins ready, because their new runtime is completely different and porting is not easy. But from a Zwave standpoint, they seem to have learned the lesson, by decoupling devices from implementation, and by allowing device definition to be updated separately. We'll see, it's probably too early and a lot of customers will migrate to anything better when the product will be really ready. -
@therealdb said in The Home Automation Controller Pyramid:
next September
2020 or 2021? 2021 seems more likely. Short sprints only means lots of progress if you're actually capable of writing code. Given the number of recurring issues, this seems something that may be beyond them.
And who's going to hang around for 2021?C
-
@rafale77 said in The Home Automation Controller Pyramid:
I just started learning a little python because all the machine learning libraries seem to have a python API so it makes things much easier... But for home automation, I for one am way too invested in lua and two, don't see python as being suitable...
My view entirely! Python is a huge language compared to Lua. Its real plus is the vast number of libraries, but the huge minus is the size of the system. Parts of openLuup (the Historian's
graphite_cgi
module, and theWhisper
database were translated from Graphite's Python code, so I had to learn it a bit.@CatmanV2 said in The Home Automation Controller Pyramid:
I think part of the problem is that there are too many standards to chose from.
Indeed... always the problem with 'Standards'.
-
@rafale77 said in The Home Automation Controller Pyramid:
all the machine learning libraries seem to have a python API so it makes things much easier...
Yes, that seems to be the case. One AI application I use applies neural nets to image processing for astro-photography.
However...
... another big project at the moment (which has been on the “to do” list for a very long time), is a Prolog interpreter (written in Lua, of course.) I’m currently catching up on the last 30 year’s worth of scientific papers in the field of logic and constraint programming. Recently came across a 2017 paper outlining, what I consider to be, a real breakthrough in implementing the Prolog language, so that’s where my time is going.
If it all turns out well, it may even be included as an openLuup plugin! It also touches on this project...
-
@therealdb said in The Home Automation Controller Pyramid:
to be fair, ezlo seems to have implemented Zwave (and Zigbee) stack in a modern way. but I'm not convinced at all by their new programming environment. they're adopting an approach very similar to HA's, where you can launch scripts to intercept events, instead of having services always executing. So, openluup it's probably the safest bet in terms of features and stability for luup refugees.
More modern way than vera, no question. Anything else would have been pretty difficult to do but from my observation has been that they are still basing a lot of their focus on addressing the vera problems... which are very vera centric and no other platform has: They still want to go after devices one by one rather than look at zwave command class overall. I heard from other device vendors that they want to charge them to test their devices. They appear to be looking at a very closed and controlled device support environment and the whole idea of having a collocated mesh of controllers connected over IP as I discussed back at the old place displays their ignorance of how Zwave works. Again it is focused on fixing vera problems no other zwave system has, in a complicated way, "vera style".
But what made me walk away is the significant downgrade in the hardware vs. vera. A huge disappointment showing clearly that they tried to use the cheapest possible, ignoring reliability and future scalability (the i/o capability ranging from the bus to the ethernet chipset and the grade of the cpu and memory silicon are all downgraded vs the vera plus) and second the huge changes in the API which I felt was unnecessary and requiring a lot of work to adjust to the discontinuity to adopt something which is unreliable, not as mature in terms of feature and absolutely less scalable than what we have while many other solutions are available on the market. What is the point? They also seem to insisted on building their firmware backwards starting from the bling bling, eye candies at the top of the pyramid from 2 years ago and only now working on the core base which of course will delay everything because of the dependencies. They also definitely have gone cloud first which will makes the vision of having a cloud independent system much more challenging to implement. So indeed lots of pain (exclude include), lots of changes (plugins and API), to downgrade a system (hardware) to get a less reliable and scalable system which for now remains cloud dependent... no thank you. In comparison my migration to zway on openluup, though not plug and play involved none of the exclusion/inclusion, very few plugin and no API changes to get to much more scalable system on my own hardware (which I can later upgrade and move around) and has been cloud independent from day 1. It is much faster, more reliable, more integrated and scalable than ezlo can ever be.What they should have done was to put design a core firmware from the beginning (the base of the pyramid), release it on a much more modern and scalable hardware (something like an atomic pi or an nvidia jetson, or even stay on the vera plus hardware rather than a $7 board used for middle school lego projects), put all these UI and mobile app work on the back-burner and put their efforts on making the core radio control stack work on the same API as vera (put the second layer on top of the base of the pyramid). Then work on migrating all the existing plugin and integrations. These should have been done last year... and now they could have had a product upon which they could build further integrations, UI and mobile app at their leisure, having migrated over the existing vera customer base. They are currently a competitor for no one... though they see themselves as being competitors to even this forum which sells nothing... I have not followed any of their progress but really have lost interest since I felt they were heading full speed towards a dead end.
-
@akbooer said in The Home Automation Controller Pyramid:
@rafale77 said in The Home Automation Controller Pyramid:
all the machine learning libraries seem to have a python API so it makes things much easier...
Yes, that seems to be the case. One AI application I use applies neural nets to image processing for astro-photography.
However...
... another big project at the moment (which has been on the “to do” list for a very long time), is a Prolog interpreter (written in Lua, of course.) I’m currently catching up on the last 30 year’s worth of scientific papers in the field of logic and constraint programming. Recently came across a 2017 paper outlining, what I consider to be, a real breakthrough in implementing the Prolog language, so that’s where my time is going.
If it all turns out well, it may even be included as an openLuup plugin! It also touches on this project...
That would be awesome, I am myself thinking about eventually getting some of the video processing working directly on openLuup rather than going through home assistant...
-
@CatmanV2 said in The Home Automation Controller Pyramid:
2020 or 2021? 2021 seems more likely. Short sprints only means lots of progress if you're actually capable of writing code. Given the number of recurring issues, this seems something that may be beyond them.
- Short sprints mean more bugs for sure, but better ability to fix them as well. I prefer over the previous approach, we'll see.
@rafale77 said in The Home Automation Controller Pyramid:
What they should have done was to put design a core firmware from the beginning
we all know. I was just reporting that they did a good thing. It doesn't mean that the results will be enough, or in time to retain theri customer base.
Openluup seems to be the best viable solution for a smooth transition.
-
It’s doable when you have engineers focused on things. I build complex systems for a living and with talented people you can write a lot of things in two months. Plus, it’s difficult to start. Once you have a codebase, bugs can be closed fast and features can be added easily.
I’m generalizing and I’m not sure they will, but, I’ll repeat myself, it’s doable. I think next two weeks they’re gonna release a lot of new features. The problem is some parts of their design choices are questionable, as @rigpapa already suggested in the old place. -
@therealdb said in The Home Automation Controller Pyramid:
It’s doable when you have engineers focused on things. I build complex systems for a living and with talented people you can write a lot of things in two months. Plus, it’s difficult to start. Once you have a codebase, bugs can be closed fast and features can be added easily.
I’m generalizing and I’m not sure they will, but, I’ll repeat myself, it’s doable. I think next two weeks they’re gonna release a lot of new features. The problem is some parts of their design choices are questionable, as @rigpapa already suggested in the old place.Oh for sure. I absorb(ed) the product for years. Yes it's hard to start, but if I was sitting in show and tell and hearing that feedback I'd be 'doubtful'
We shall see
C
-
Hi @rafale77,
Thanks for the diagram, it's helpful. But can you maybe tell me some more on the integration of Hubitat and Openluup? What is the best way to do it? I'm considering the move away from Vera, but don't know what to choose yet, Zway or Hubitat. Zway seems an easier migration, but Hubitat seems a great and easy all-in solution.
-
Hubitat will give you access to both zigbee and zwave but there is no bridge for it on openluup. This would mean that you would have to start everything from scratch and redo all of your home automation and go through a new learning curve. I have a few friends who run it and are reasonably happy with it. It isn't without its own minor quirks and is a relatively closed environment. It definitely isn't open source. A number of users have integrated it with home assistant to overcome some of its limitations and then used node-red on top for full control (thus completing the pyramid)
If you have devoted a lot your time developing your system, on vera then you are much better off with openLuup/ z-way which has very little learning curve except for the initial installation, which is more linux learning than anything, offers more flexibility and allows you to migrate all your scenes and plugins over to openLuup.